[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79PBF7R3P3QJ58WY2MSCANR":3,"skill-same:01M79PBF7R3P3QJ58WY2MSCANR":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M79PBF7R3P3QJ58WY2MSCANR","gds-create-story",null,"Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says \"create the next story\" or \"create story [story identifier]\"","OrigoStudio\u002Forigo-design","OrigoStudio","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F256943203?v=4","01M79P1MQHVZ4PTXBQVM11Q00S","Origo Studio","01M79P1MR8S30QEEM0Z6MGX1MA",1,"MIT","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-story\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gds-create-story\ndescription: 'Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says \"create the next story\" or \"create story [story identifier]\"'\n---\n\n# Create Story Workflow\n\n**Goal:** Create a comprehensive story file that gives the dev agent everything needed for flawless implementation.\n\n**Your Role:** Story context engine that prevents LLM developer mistakes, omissions, or disasters.\n\n- Communicate all responses in {communication_language} and language MUST be tailored to {game_dev_experience}\n- Generate all documents in {document_output_language}\n- Your purpose is NOT to copy from epics - it's to create a comprehensive, optimized story file that gives the DEV agent EVERYTHING needed for flawless implementation\n- COMMON LLM MISTAKES TO PREVENT: reinventing wheels, wrong libraries, wrong file locations, breaking regressions, ignoring UX, vague implementations, lying about completion, not learning from past work\n- EXHAUSTIVE ANALYSIS REQUIRED: You must thoroughly analyze ALL artifacts to extract critical context - do NOT be lazy or skim! This is the most important function in the entire development process!\n- UTILIZE SUBPROCESSES AND SUBAGENTS: Use research subagents, subprocesses or parallel processing if available to thoroughly analyze different artifacts simultaneously and thoroughly\n- SAVE QUESTIONS: If you think of questions or clarifications during analysis, save them for the end after the complete story is written\n- ZERO USER INTERVENTION: Process should be fully automated except for initial epic\u002Fstory selection or missing documents\n\n## Paths\n\n- `sprint_status` = `{implementation_artifacts}\u002Fsprint-status.yaml`\n- `epics_file` = `{planning_artifacts}\u002Fepics.md`\n- `gdd_file` = `{planning_artifacts}\u002Fgdd.md`\n- `architecture_file` = `{planning_artifacts}\u002Farchitecture.md`\n- `ux_file` = `{planning_artifacts}\u002F*ux*.md`\n- `story_title` = \"\" (will be elicited if not derivable)\n- `project_context` = `**\u002Fproject-context.md` (load if exists)\n- `default_output_file` = `{implementation_artifacts}\u002F{{story_key}}.md`\n\n## Input Files\n\n| Input           | Description                                                                          | Path Pattern(s)                                                                                      | Load Strategy  |\n| --------------- | ------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------- | -------------- |\n| gdd             | Game Design Document (fallback - epics file should have most content)                | whole: `{planning_artifacts}\u002F*gdd*.md`, sharded: `{planning_artifacts}\u002F*gdd*\u002F*.md`                   | SELECTIVE_LOAD |\n| architecture    | Architecture (fallback - epics file should have relevant sections)                   | whole: `{planning_artifacts}\u002F*architecture*.md`, sharded: `{planning_artifacts}\u002F*architecture*\u002F*.md` | SELECTIVE_LOAD |\n| ux              | UX design (fallback - epics file should have relevant sections)                      | whole: `{planning_artifacts}\u002F*ux*.md`, sharded: `{planning_artifacts}\u002F*ux*\u002F*.md`                     | SELECTIVE_LOAD |\n| epics           | Enhanced epics+stories file with BDD and source hints                                | whole: `{planning_artifacts}\u002F*epic*.md`, sharded: `{planning_artifacts}\u002F*epic*\u002F*.md`                 | SELECTIVE_LOAD |\n| project_context | Project-wide rules, conventions, MCP configs, and third-party framework requirements | `**\u002Fproject-context.md`                                                                              | FULL_LOAD      |\n\n---\n\n## Conventions\n\n- Bare paths (e.g. `template.md`) resolve from the skill root.\n- `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).\n- `{project-root}`-prefixed paths resolve from the project working directory.\n- `{skill-name}` resolves to the skill directory's basename.\n\n## On Activation\n\n### Step 1: Resolve the Workflow Block\n\nRun: `python3 {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_customization.py --skill {skill-root} --key workflow`\n\n**If the script fails**, resolve the `workflow` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:\n\n1. `{skill-root}\u002Fcustomize.toml` — defaults\n2. `{project-root}\u002F_bmad\u002Fcustom\u002F{skill-name}.toml` — team overrides\n3. `{project-root}\u002F_bmad\u002Fcustom\u002F{skill-name}.user.toml` — personal overrides\n\nAny missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.\n\n### Step 2: Execute Prepend Steps\n\nExecute each entry in `{workflow.activation_steps_prepend}` in order before proceeding.\n\n### Step 3: Load Persistent Facts\n\nTreat every entry in `{workflow.persistent_facts}` as foundational context you carry for the rest of the workflow run. Entries prefixed `file:` are paths or globs under `{project-root}` — load the referenced contents as facts. All other entries are facts verbatim.\n\n### Step 4: Load Config\n\nLoad config from `{project-root}\u002F_bmad\u002Fgds\u002Fconfig.yaml` and resolve:\n\n- `user_name`\n- `communication_language`\n- `document_output_language`\n- `game_dev_experience`\n- `planning_artifacts`\n- `implementation_artifacts`\n- `sprint_status`\n\n### Step 5: Greet the User\n\nGreet `{user_name}`, speaking in `{communication_language}`.\n\n### Step 6: Execute Append Steps\n\nExecute each entry in `{workflow.activation_steps_append}` in order.\n\nActivation is complete. If `activation_steps_prepend` or `activation_steps_append` were non-empty, confirm every entry was executed in order before proceeding. Do not begin the main workflow until all activation steps have been completed.\n\n## EXECUTION\n\n\u003Cworkflow>\n\n\u003Cstep n=\"1\" goal=\"Determine target story\">\n  \u003Ccheck if=\"{{story_path}} is provided by user or user provided the epic and story number such as 2-4 or 1.6 or epic 1 story 5\">\n    \u003Caction>Parse user-provided story path: extract epic_num, story_num, story_title from format like \"1-2-user-auth\"\u003C\u002Faction>\n    \u003Caction>Set {{epic_num}}, {{story_num}}, {{story_key}} from user input\u003C\u002Faction>\n    \u003Caction>GOTO step 2a\u003C\u002Faction>\n  \u003C\u002Fcheck>\n\n\u003Caction>Check if {{sprint_status}} file exists for auto discover\u003C\u002Faction>\n\u003Ccheck if=\"sprint status file does NOT exist\">\n\u003Coutput>🚫 No sprint status file found and no story specified\u003C\u002Foutput>\n\u003Coutput>\n**Required Options:** 1. Run `sprint-planning` to initialize sprint tracking (recommended) 2. Provide specific epic-story number to create (e.g., \"1-2-user-auth\") 3. Provide path to story documents if sprint status doesn't exist yet\n\u003C\u002Foutput>\n\u003Cask>Choose option [1], provide epic-story number, path to story docs, or [q] to quit:\u003C\u002Fask>\n\n    \u003Ccheck if=\"user chooses 'q'\">\n      \u003Caction>HALT - No work needed\u003C\u002Faction>\n    \u003C\u002Fcheck>\n\n    \u003Ccheck if=\"user chooses '1'\">\n      \u003Coutput>Run sprint-planning workflow first to create sprint-status.yaml\u003C\u002Foutput>\n      \u003Caction>HALT - User needs to run sprint-planning\u003C\u002Faction>\n    \u003C\u002Fcheck>\n\n    \u003Ccheck if=\"user provides epic-story number\">\n      \u003Caction>Parse user input: extract epic_num, story_num, story_title\u003C\u002Faction>\n      \u003Caction>Set {{epic_num}}, {{story_num}}, {{story_key}} from user input\u003C\u002Faction>\n      \u003Caction>GOTO step 2a\u003C\u002Faction>\n    \u003C\u002Fcheck>\n\n    \u003Ccheck if=\"user provides story docs path\">\n      \u003Caction>Use user-provided path for story documents\u003C\u002Faction>\n      \u003Caction>GOTO step 2a\u003C\u002Faction>\n    \u003C\u002Fcheck>\n\n  \u003C\u002Fcheck>\n\n  \u003C!-- Auto-discover from sprint status only if no user input -->\n  \u003Ccheck if=\"no user input provided\">\n    \u003Ccritical>MUST read COMPLETE {sprint_status} file from start to end to preserve order\u003C\u002Fcritical>\n    \u003Caction>Load the FULL file: {{sprint_status}}\u003C\u002Faction>\n    \u003Caction>Read ALL lines from beginning to end - do not skip any content\u003C\u002Faction>\n    \u003Caction>Parse the development_status section completely\u003C\u002Faction>\n\n    \u003Caction>Find the FIRST story (by reading in order from top to bottom) where:\n      - Key matches pattern: number-number-name (e.g., \"1-2-user-auth\")\n      - NOT an epic key (epic-X) or retrospective (epic-X-retrospective)\n      - Status value equals \"backlog\"\n    \u003C\u002Faction>\n\n    \u003Ccheck if=\"no backlog story found\">\n      \u003Coutput>📋 No backlog stories found in sprint-status.yaml\n\n        All stories are either already created, in progress, or done.\n\n        **Options:**\n        1. Run sprint-planning to refresh story tracking\n        2. Load PM agent and run correct-course to add more stories\n        3. Check if current sprint is complete and run retrospective\n      \u003C\u002Foutput>\n      \u003Caction>HALT\u003C\u002Faction>\n    \u003C\u002Fcheck>\n\n    \u003Caction>Extract from found story key (e.g., \"1-2-user-authentication\"):\n      - epic_num: first number before dash (e.g., \"1\")\n      - story_num: second number after first dash (e.g., \"2\")\n      - story_title: remainder after second dash (e.g., \"user-authentication\")\n    \u003C\u002Faction>\n    \u003Caction>Set {{story_id}} = \"{{epic_num}}.{{story_num}}\"\u003C\u002Faction>\n    \u003Caction>Store story_key for later use (e.g., \"1-2-user-authentication\")\u003C\u002Faction>\n\n    \u003C!-- Mark epic as in-progress if this is first story -->\n    \u003Caction>Check if this is the first story in epic {{epic_num}} by looking for {{epic_num}}-1-* pattern\u003C\u002Faction>\n    \u003Ccheck if=\"this is first story in epic {{epic_num}}\">\n      \u003Caction>Load {{sprint_status}} and check epic-{{epic_num}} status\u003C\u002Faction>\n      \u003Caction>If epic status is \"backlog\" → update to \"in-progress\"\u003C\u002Faction>\n      \u003Caction>If epic status is \"contexted\" (legacy status) → update to \"in-progress\" (backward compatibility)\u003C\u002Faction>\n      \u003Caction>If epic status is \"in-progress\" → no change needed\u003C\u002Faction>\n      \u003Ccheck if=\"epic status is 'done'\">\n        \u003Coutput>🚫 ERROR: Cannot create story in completed epic\u003C\u002Foutput>\n        \u003Coutput>Epic {{epic_num}} is marked as 'done'. All stories are complete.\u003C\u002Foutput>\n        \u003Coutput>If you need to add more work, either:\u003C\u002Foutput>\n        \u003Coutput>1. Manually change epic status back to 'in-progress' in sprint-status.yaml\u003C\u002Foutput>\n        \u003Coutput>2. Create a new epic for additional work\u003C\u002Foutput>\n        \u003Caction>HALT - Cannot proceed\u003C\u002Faction>\n      \u003C\u002Fcheck>\n      \u003Ccheck if=\"epic status is not one of: backlog, contexted, in-progress, done\">\n        \u003Coutput>🚫 ERROR: Invalid epic status '{{epic_status}}'\u003C\u002Foutput>\n        \u003Coutput>Epic {{epic_num}} has invalid status. Expected: backlog, in-progress, or done\u003C\u002Foutput>\n        \u003Coutput>Please fix sprint-status.yaml manually or run sprint-planning to regenerate\u003C\u002Foutput>\n        \u003Caction>HALT - Cannot proceed\u003C\u002Faction>\n      \u003C\u002Fcheck>\n      \u003Coutput>📊 Epic {{epic_num}} status updated to in-progress\u003C\u002Foutput>\n    \u003C\u002Fcheck>\n\n    \u003Caction>GOTO step 2a\u003C\u002Faction>\n\n  \u003C\u002Fcheck>\n  \u003Caction>Load the FULL file: {{sprint_status}}\u003C\u002Faction>\n  \u003Caction>Read ALL lines from beginning to end - do not skip any content\u003C\u002Faction>\n  \u003Caction>Parse the development_status section completely\u003C\u002Faction>\n\n\u003Caction>Find the FIRST story (by reading in order from top to bottom) where: - Key matches pattern: number-number-name (e.g., \"1-2-user-auth\") - NOT an epic key (epic-X) or retrospective (epic-X-retrospective) - Status value equals \"backlog\"\n\u003C\u002Faction>\n\n  \u003Ccheck if=\"no backlog story found\">\n    \u003Coutput>No backlog stories found in sprint-status.yaml\n\n      All stories are either already created, in progress, or done.\n\n      **Options:**\n      1. Run sprint-planning to refresh story tracking\n      2. Load PM agent and run correct-course to add more stories\n      3. Check if current sprint is complete and run retrospective\n    \u003C\u002Foutput>\n    \u003Caction>HALT\u003C\u002Faction>\n\n  \u003C\u002Fcheck>\n\n\u003Caction>Extract from found story key (e.g., \"1-2-user-authentication\"): - epic_num: first number before dash (e.g., \"1\") - story_num: second number after first dash (e.g., \"2\") - story_title: remainder after second dash (e.g., \"user-authentication\")\n\u003C\u002Faction>\n\u003Caction>Set {{story_id}} = \"{{epic_num}}.{{story_num}}\"\u003C\u002Faction>\n\u003Caction>Store story_key for later use (e.g., \"1-2-user-authentication\")\u003C\u002Faction>\n\n  \u003C!-- Mark epic as in-progress if this is first story -->\n\n\u003Caction>Check if this is the first story in epic {{epic_num}} by looking for {{epic_num}}-1-\\* pattern\u003C\u002Faction>\n\u003Ccheck if=\"this is first story in epic {{epic_num}}\">\n\u003Caction>Load {{sprint_status}} and check epic-{{epic_num}} status\u003C\u002Faction>\n\u003Caction>If epic status is \"backlog\" → update to \"in-progress\"\u003C\u002Faction>\n\u003Caction>If epic status is \"contexted\" (legacy status) → update to \"in-progress\" (backward compatibility)\u003C\u002Faction>\n\u003Caction>If epic status is \"in-progress\" → no change needed\u003C\u002Faction>\n\u003Ccheck if=\"epic status is 'done'\">\n\u003Coutput>ERROR: Cannot create story in completed epic\u003C\u002Foutput>\n\u003Coutput>Epic {{epic_num}} is marked as 'done'. All stories are complete.\u003C\u002Foutput>\n\u003Coutput>If you need to add more work, either:\u003C\u002Foutput>\n\u003Coutput>1. Manually change epic status back to 'in-progress' in sprint-status.yaml\u003C\u002Foutput>\n\u003Coutput>2. Create a new epic for additional work\u003C\u002Foutput>\n\u003Caction>HALT - Cannot proceed\u003C\u002Faction>\n\u003C\u002Fcheck>\n\u003Ccheck if=\"epic status is not one of: backlog, contexted, in-progress, done\">\n\u003Coutput>ERROR: Invalid epic status '{{epic_status}}'\u003C\u002Foutput>\n\u003Coutput>Epic {{epic_num}} has invalid status. Expected: backlog, in-progress, or done\u003C\u002Foutput>\n\u003Coutput>Please fix sprint-status.yaml manually or run sprint-planning to regenerate\u003C\u002Foutput>\n\u003Caction>HALT - Cannot proceed\u003C\u002Faction>\n\u003C\u002Fcheck>\n\u003Coutput>Epic {{epic_num}} status updated to in-progress\u003C\u002Foutput>\n\u003C\u002Fcheck>\n\n\u003Caction>GOTO step 2a\u003C\u002Faction>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"2\" goal=\"Load and analyze core artifacts\">\n  \u003Ccritical>🔬 EXHAUSTIVE ARTIFACT ANALYSIS - This is where you prevent future developer mistakes!\u003C\u002Fcritical>\n\n  \u003C!-- Load all available content through discovery protocol -->\n\n\u003Caction>Read fully and follow `.\u002Fdiscover-inputs.md` to load all input files\u003C\u002Faction>\n\u003Cnote>Available content: {epics_content}, {gdd_content}, {architecture_content}, {ux_content},\n{project_context}\u003C\u002Fnote>\n\n  \u003C!-- Analyze epics file for story foundation -->\n\n\u003Caction>From {epics_content}, extract Epic {{epic_num}} complete context:\u003C\u002Faction> **EPIC ANALYSIS:** - Epic\nobjectives and business value - ALL stories in this epic for cross-story context - Our specific story's requirements, user story\nstatement, acceptance criteria - Technical requirements and constraints - Dependencies on other stories\u002Fepics - Source hints pointing to\noriginal documents \u003C!-- Extract specific story requirements -->\n\u003Caction>Extract our story ({{epic_num}}-{{story_num}}) details:\u003C\u002Faction> **STORY FOUNDATION:** - User story statement\n(As a, I want, so that) - Detailed acceptance criteria (already BDD formatted) - Technical requirements specific to this story -\nBusiness context and value - Success criteria \u003C!-- Previous story analysis for context continuity -->\n\u003Ccheck if=\"story_num > 1\">\n\u003Caction>Find {{previous_story_num}}: scan {implementation_artifacts} for the story file in epic {{epic_num}} with the highest story number less than {{story_num}}\u003C\u002Faction>\n\u003Caction>Load previous story file: {implementation_artifacts}\u002F{{epic_num}}-{{previous_story_num}}-\\*.md\u003C\u002Faction> **PREVIOUS STORY INTELLIGENCE:** -\nDev notes and learnings from previous story - Review feedback and corrections needed - Files that were created\u002Fmodified and their\npatterns - Testing approaches that worked\u002Fdidn't work - Problems encountered and solutions found - Code patterns established \u003Caction>Extract\nall learnings that could impact current story implementation\u003C\u002Faction>\n\u003C\u002Fcheck>\n\n  \u003C!-- Project context analysis (game-dev extension for project-context.md extraction) -->\n  \u003Ccheck if=\"{project_context} was loaded and is not empty\">\n    \u003Caction>Analyze {project_context} for story-relevant rules and constraints:\u003C\u002Faction>\n    **PROJECT CONTEXT EXTRACTION:**\n    - Third-party frameworks and libraries required by the project\n    - MCP server configurations and integrations to use\n    - Coding conventions and patterns to follow\n    - Project-wide constraints (e.g., specific APIs, deployment targets)\n    - Any rules that apply to this story's implementation domain\n    \u003Caction>Store extracted project rules as {{project_rules}} for embedding in the story file\u003C\u002Faction>\n  \u003C\u002Fcheck>\n\n  \u003C!-- Git intelligence for previous work patterns -->\n\n\u003Ccheck\n    if=\"previous story exists AND git repository detected\">\n\u003Caction>Get last 5 commit titles to understand recent work patterns\u003C\u002Faction>\n\u003Caction>Analyze 1-5 most recent commits for relevance to current story: - Files created\u002Fmodified - Code patterns and conventions used - Library dependencies added\u002Fchanged - Architecture decisions implemented - Testing approaches used\n\u003C\u002Faction>\n\u003Caction>Extract actionable insights for current story implementation\u003C\u002Faction>\n\u003C\u002Fcheck>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"3\" goal=\"Architecture analysis for developer guardrails\">\n  \u003Ccritical>🏗️ ARCHITECTURE INTELLIGENCE - Extract everything the developer MUST follow!\u003C\u002Fcritical> **ARCHITECTURE DOCUMENT ANALYSIS:** \u003Caction>Systematically\n  analyze architecture content for story-relevant requirements:\u003C\u002Faction>\n\n  \u003C!-- Load architecture - single file or sharded -->\n  \u003Ccheck if=\"architecture file is single file\">\n    \u003Caction>Load complete {architecture_content}\u003C\u002Faction>\n  \u003C\u002Fcheck>\n  \u003Ccheck if=\"architecture is sharded to folder\">\n    \u003Caction>Load architecture index and scan all architecture files\u003C\u002Faction>\n  \u003C\u002Fcheck> **CRITICAL ARCHITECTURE EXTRACTION:** \u003Caction>For\n  each architecture section, determine if relevant to this story:\u003C\u002Faction> - **Technical Stack:** Languages, frameworks, libraries with\n  versions - **Code Structure:** Folder organization, naming conventions, file patterns - **API Patterns:** Service structure, endpoint\n  patterns, data contracts - **Database Schemas:** Tables, relationships, constraints relevant to story - **Security Requirements:**\n  Authentication patterns, authorization rules - **Performance Requirements:** Caching strategies, optimization patterns - **Testing\n  Standards:** Testing frameworks, coverage expectations, test patterns - **Deployment Patterns:** Environment configurations, build\n  processes - **Integration Patterns:** External service integrations, data flows \u003Caction>Extract any story-specific requirements that the\n  developer MUST follow\u003C\u002Faction>\n  \u003Caction>Identify any architectural decisions that override previous patterns\u003C\u002Faction>\n\n  \u003C!-- Read existing code being modified — non-negotiable -->\n\n\u003Ccritical>📂 READ FILES BEING MODIFIED — skipping this is the primary cause of implementation failures and review cycles\u003C\u002Fcritical>\n\u003Caction>From the architecture directory structure, identify every file marked UPDATE (not NEW) that this story will touch\u003C\u002Faction>\n\u003Caction>Read each relevant UPDATE file completely. For each one, document in dev notes: - Current state: what it does today (state machine, API calls, data shapes, existing behaviors) - What this story changes: the specific sections or behaviors being modified - What must be preserved: existing interactions and behaviors the story must not break\n\u003C\u002Faction>\n\u003Ccritical>A story implementation must leave the system working end-to-end — not just satisfy its stated ACs.\nIf a behavior is required for the feature to work correctly in the existing system, it is a requirement\nwhether or not it is explicitly written in the story. The dev agent owns this.\u003C\u002Fcritical>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"4\" goal=\"Web research for latest technical specifics\">\n  \u003Ccritical>🌐 ENSURE LATEST TECH KNOWLEDGE - Prevent outdated implementations!\u003C\u002Fcritical> **WEB INTELLIGENCE:** \u003Caction>Identify specific\n  technical areas that require latest version knowledge:\u003C\u002Faction>\n\n  \u003C!-- Check for libraries\u002Fframeworks mentioned in architecture -->\n\n\u003Caction>From architecture analysis, identify specific libraries, APIs, or\nframeworks\u003C\u002Faction>\n\u003Caction>For each critical technology, research latest stable version and key changes: - Latest API documentation and breaking changes - Security vulnerabilities or updates - Performance improvements or deprecations - Best practices for current version\n\u003C\u002Faction>\n**EXTERNAL CONTEXT INCLUSION:** \u003Caction>Include in story any critical latest information the developer needs: - Specific library versions and why chosen - API endpoints with parameters and authentication - Recent security patches or considerations - Performance optimization techniques - Migration considerations if upgrading\n\u003C\u002Faction>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"5\" goal=\"Create comprehensive story file\">\n  \u003Ccritical>📝 CREATE ULTIMATE STORY FILE - The developer's master implementation guide!\u003C\u002Fcritical>\n\n\u003Caction>Initialize from template.md:\n{default_output_file}\u003C\u002Faction>\n\u003Ctemplate-output file=\"{default_output_file}\">story_header\u003C\u002Ftemplate-output>\n\n  \u003C!-- Story foundation from epics analysis -->\n\n\u003Ctemplate-output\n    file=\"{default_output_file}\">story_requirements\u003C\u002Ftemplate-output>\n\n  \u003C!-- Developer context section - MOST IMPORTANT PART -->\n  \u003Ctemplate-output file=\"{default_output_file}\">\n  developer_context_section\u003C\u002Ftemplate-output> **DEV AGENT GUARDRAILS:** \u003Ctemplate-output file=\"{default_output_file}\">\n  technical_requirements\u003C\u002Ftemplate-output>\n  \u003Ctemplate-output file=\"{default_output_file}\">architecture_compliance\u003C\u002Ftemplate-output>\n  \u003Ctemplate-output\n    file=\"{default_output_file}\">library_framework_requirements\u003C\u002Ftemplate-output>\n  \u003Ctemplate-output file=\"{default_output_file}\">\n  file_structure_requirements\u003C\u002Ftemplate-output>\n  \u003Ctemplate-output file=\"{default_output_file}\">testing_requirements\u003C\u002Ftemplate-output>\n\n  \u003C!-- Previous story intelligence -->\n\n\u003Ccheck\n    if=\"previous story learnings available\">\n\u003Ctemplate-output file=\"{default_output_file}\">previous_story_intelligence\u003C\u002Ftemplate-output>\n\u003C\u002Fcheck>\n\n  \u003C!-- Git intelligence -->\n\n\u003Ccheck\n    if=\"git analysis completed\">\n\u003Ctemplate-output file=\"{default_output_file}\">git_intelligence_summary\u003C\u002Ftemplate-output>\n\u003C\u002Fcheck>\n\n  \u003C!-- Latest technical specifics -->\n  \u003Ccheck if=\"web research completed\">\n    \u003Ctemplate-output file=\"{default_output_file}\">latest_tech_information\u003C\u002Ftemplate-output>\n  \u003C\u002Fcheck>\n\n  \u003C!-- Project context rules - embed extracted rules from project-context.md (game-dev extension) -->\n  \u003Ccheck if=\"{{project_rules}} is not empty\">\n    \u003Ctemplate-output file=\"{default_output_file}\">project_context_reference\u003C\u002Ftemplate-output>\n    \u003Caction>Populate the Project Context Rules section with ALL extracted {{project_rules}} including:\n      - Required third-party frameworks and how they apply to this story\n      - MCP integrations the developer must use\n      - Project-wide conventions and constraints\n      - Any domain-specific rules relevant to this story's tasks\u003C\u002Faction>\n  \u003C\u002Fcheck>\n\n  \u003C!-- Final status update -->\n  \u003Ctemplate-output file=\"{default_output_file}\">\n  story_completion_status\u003C\u002Ftemplate-output>\n\n  \u003C!-- CRITICAL: Set status to ready-for-dev -->\n\n\u003Caction>Set story Status to: \"ready-for-dev\"\u003C\u002Faction>\n\u003Caction>Add completion note: \"Ultimate\ncontext engine analysis completed - comprehensive developer guide created\"\u003C\u002Faction>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"6\" goal=\"Update sprint status and finalize\">\n  \u003Caction>Validate the newly created story file {default_output_file} against `.\u002Fchecklist.md` and apply any required fixes before finalizing\u003C\u002Faction>\n  \u003Caction>Save story document unconditionally\u003C\u002Faction>\n\n  \u003C!-- Update sprint status -->\n  \u003Ccheck if=\"sprint status file exists\">\n    \u003Caction>Update {{sprint_status}}\u003C\u002Faction>\n    \u003Caction>Load the FULL file and read all development_status entries\u003C\u002Faction>\n    \u003Caction>Find development_status key matching {{story_key}}\u003C\u002Faction>\n    \u003Caction>Verify current status is \"backlog\" (expected previous state)\u003C\u002Faction>\n    \u003Caction>Update development_status[{{story_key}}] = \"ready-for-dev\"\u003C\u002Faction>\n    \u003Caction>Update last_updated field to current date\u003C\u002Faction>\n    \u003Caction>Save file, preserving ALL comments and structure including STATUS DEFINITIONS\u003C\u002Faction>\n  \u003C\u002Fcheck>\n\n\u003Caction>Report completion\u003C\u002Faction>\n\u003Coutput>**🎯 ULTIMATE BMad Method STORY CONTEXT CREATED, {user_name}!**\n\n    **Story Details:**\n    - Story ID: {{story_id}}\n    - Story Key: {{story_key}}\n    - File: {{story_file}}\n    - Status: ready-for-dev\n\n    **Next Steps:**\n    1. Review the comprehensive story in {{story_file}}\n    2. Run dev agents `dev-story` for optimized implementation\n    3. Run `code-review` when complete (auto-marks done)\n    4. Optional: If Test Architect module installed, run `\u002Fbmad:tea:automate` after `dev-story` to generate guardrail tests\n\n    **The developer now has everything needed for flawless implementation!**\n\n  \u003C\u002Foutput>\n\u003Caction>Run: `python3 {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_customization.py --skill {skill-root} --key workflow.on_complete` — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.\u003C\u002Faction>\n\u003C\u002Fstep>\n\n\u003C\u002Fworkflow>\n","# Create Story Workflow\n\n**Goal:** Create a comprehensive story file that gives the dev agent everything needed for flawless implementation.\n\n**Your Role:** Story context engine that prevents LLM developer mistakes, omissions, or disasters.\n\n- Communicate all responses in {communication_language} and language MUST be tailored to {game_dev_experience}\n- Generate all documents in {document_output_language}\n- Your purpose is NOT to copy from epics - it's to create a comprehensive, optimized story file that gives the DEV agent EVERYTHING needed for flawless implementation\n- COMMON LLM MISTAKES TO PREVENT: reinventing wheels, wrong libraries, wrong file locations, breaking regressions, ignoring UX, vague implementations, lying about completion, not learning from past work\n- EXHAUSTIVE ANALYSIS REQUIRED: You must thoroughly analyze ALL artifacts to extract critical context - do NOT be lazy or skim! This is the most important function in the entire development process!\n- UTILIZE SUBPROCESSES AND SUBAGENTS: Use research subagents, subprocesses or parallel processing if available to thoroughly analyze different artifacts simultaneously and thoroughly\n- SAVE QUESTIONS: If you think of questions or clarifications during analysis, save them for the end after the complete story is written\n- ZERO USER INTERVENTION: Process should be fully automated except for initial epic\u002Fstory selection or missing documents\n\n## Paths\n\n- `sprint_status` = `{implementation_artifacts}\u002Fsprint-status.yaml`\n- `epics_file` = `{planning_artifacts}\u002Fepics.md`\n- `gdd_file` = `{planning_artifacts}\u002Fgdd.md`\n- `architecture_file` = `{planning_artifacts}\u002Farchitecture.md`\n- `ux_file` = `{planning_artifacts}\u002F*ux*.md`\n- `story_title` = \"\" (will be elicited if not derivable)\n- `project_context` = `**\u002Fproject-context.md` (load if exists)\n- `default_output_file` = `{implementation_artifacts}\u002F{{story_key}}.md`\n\n## Input Files\n\n| Input           | Description                                                                          | Path Pattern(s)                                                                                      | Load Strategy  |\n| --------------- | ------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------- | -------------- |\n| gdd             | Game Design Document (fallback - epics file should have most content)                | whole: `{planning_artifacts}\u002F*gdd*.md`, sharded: `{planning_artifacts}\u002F*gdd*\u002F*.md`                   | SELECTIVE_LOAD |\n| architecture    | Architecture (fallback - epics file should have relevant sections)                   | whole: `{planning_artifacts}\u002F*architecture*.md`, sharded: `{planning_artifacts}\u002F*architecture*\u002F*.md` | SELECTIVE_LOAD |\n| ux              | UX design (fallback - epics file should have relevant sections)                      | whole: `{planning_artifacts}\u002F*ux*.md`, sharded: `{planning_artifacts}\u002F*ux*\u002F*.md`                     | SELECTIVE_LOAD |\n| epics           | Enhanced epics+stories file with BDD and source hints                                | whole: `{planning_artifacts}\u002F*epic*.md`, sharded: `{planning_artifacts}\u002F*epic*\u002F*.md`                 | SELECTIVE_LOAD |\n| project_context | Project-wide rules, conventions, MCP configs, and third-party framework requirements | `**\u002Fproject-context.md`                                                                              | FULL_LOAD      |\n\n---\n\n## Conventions\n\n- Bare paths (e.g. `template.md`) resolve from the skill root.\n- `{skill-root}` resolves to this skill's installed directory (where `customize.toml` lives).\n- `{project-root}`-prefixed paths resolve from the project working directory.\n- `{skill-name}` resolves to the skill directory's basename.\n\n## On Activation\n\n### Step 1: Resolve the Workflow Block\n\nRun: `python3 {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_customization.py --skill {skill-root} --key workflow`\n\n**If the script fails**, resolve the `workflow` block yourself by reading these three files in base → team → user order and applying the same structural merge rules as the resolver:\n\n1. `{skill-root}\u002Fcustomize.toml` — defaults\n2. `{project-root}\u002F_bmad\u002Fcustom\u002F{skill-name}.toml` — team overrides\n3. `{project-root}\u002F_bmad\u002Fcustom\u002F{skill-name}.user.toml` — personal overrides\n\nAny missing file is skipped. Scalars override, tables deep-merge, arrays of tables keyed by `code` or `id` replace matching entries and append new entries, and all other arrays append.\n\n### Step 2: Execute Prepend Steps\n\nExecute each entry in `{workflow.activation_steps_prepend}` in order before proceeding.\n\n### Step 3: Load Persistent Facts\n\nTreat every entry in `{workflow.persistent_facts}` as foundational context you carry for the rest of the workflow run. Entries prefixed `file:` are paths or globs under `{project-root}` — load the referenced contents as facts. All other entries are facts verbatim.\n\n### Step 4: Load Config\n\nLoad config from `{project-root}\u002F_bmad\u002Fgds\u002Fconfig.yaml` and resolve:\n\n- `user_name`\n- `communication_language`\n- `document_output_language`\n- `game_dev_experience`\n- `planning_artifacts`\n- `implementation_artifacts`\n- `sprint_status`\n\n### Step 5: Greet the User\n\nGreet `{user_name}`, speaking in `{communication_language}`.\n\n### Step 6: Execute Append Steps\n\nExecute each entry in `{workflow.activation_steps_append}` in order.\n\nActivation is complete. If `activation_steps_prepend` or `activation_steps_append` were non-empty, confirm every entry was executed in order before proceeding. Do not begin the main workflow until all activation steps have been completed.\n\n## EXECUTION\n\n\u003Cworkflow>\n\n\u003Cstep n=\"1\" goal=\"Determine target story\">\n  \u003Ccheck if=\"{{story_path}} is provided by user or user provided the epic and story number such as 2-4 or 1.6 or epic 1 story 5\">\n    \u003Caction>Parse user-provided story path: extract epic_num, story_num, story_title from format like \"1-2-user-auth\"\u003C\u002Faction>\n    \u003Caction>Set {{epic_num}}, {{story_num}}, {{story_key}} from user input\u003C\u002Faction>\n    \u003Caction>GOTO step 2a\u003C\u002Faction>\n  \u003C\u002Fcheck>\n\n\u003Caction>Check if {{sprint_status}} file exists for auto discover\u003C\u002Faction>\n\u003Ccheck if=\"sprint status file does NOT exist\">\n\u003Coutput>🚫 No sprint status file found and no story specified\u003C\u002Foutput>\n\u003Coutput>\n**Required Options:** 1. Run `sprint-planning` to initialize sprint tracking (recommended) 2. Provide specific epic-story number to create (e.g., \"1-2-user-auth\") 3. Provide path to story documents if sprint status doesn't exist yet\n\u003C\u002Foutput>\n\u003Cask>Choose option [1], provide epic-story number, path to story docs, or [q] to quit:\u003C\u002Fask>\n\n    \u003Ccheck if=\"user chooses 'q'\">\n      \u003Caction>HALT - No work needed\u003C\u002Faction>\n    \u003C\u002Fcheck>\n\n    \u003Ccheck if=\"user chooses '1'\">\n      \u003Coutput>Run sprint-planning workflow first to create sprint-status.yaml\u003C\u002Foutput>\n      \u003Caction>HALT - User needs to run sprint-planning\u003C\u002Faction>\n    \u003C\u002Fcheck>\n\n    \u003Ccheck if=\"user provides epic-story number\">\n      \u003Caction>Parse user input: extract epic_num, story_num, story_title\u003C\u002Faction>\n      \u003Caction>Set {{epic_num}}, {{story_num}}, {{story_key}} from user input\u003C\u002Faction>\n      \u003Caction>GOTO step 2a\u003C\u002Faction>\n    \u003C\u002Fcheck>\n\n    \u003Ccheck if=\"user provides story docs path\">\n      \u003Caction>Use user-provided path for story documents\u003C\u002Faction>\n      \u003Caction>GOTO step 2a\u003C\u002Faction>\n    \u003C\u002Fcheck>\n\n  \u003C\u002Fcheck>\n\n  \u003C!-- Auto-discover from sprint status only if no user input -->\n  \u003Ccheck if=\"no user input provided\">\n    \u003Ccritical>MUST read COMPLETE {sprint_status} file from start to end to preserve order\u003C\u002Fcritical>\n    \u003Caction>Load the FULL file: {{sprint_status}}\u003C\u002Faction>\n    \u003Caction>Read ALL lines from beginning to end - do not skip any content\u003C\u002Faction>\n    \u003Caction>Parse the development_status section completely\u003C\u002Faction>\n\n    \u003Caction>Find the FIRST story (by reading in order from top to bottom) where:\n      - Key matches pattern: number-number-name (e.g., \"1-2-user-auth\")\n      - NOT an epic key (epic-X) or retrospective (epic-X-retrospective)\n      - Status value equals \"backlog\"\n    \u003C\u002Faction>\n\n    \u003Ccheck if=\"no backlog story found\">\n      \u003Coutput>📋 No backlog stories found in sprint-status.yaml\n\n        All stories are either already created, in progress, or done.\n\n        **Options:**\n        1. Run sprint-planning to refresh story tracking\n        2. Load PM agent and run correct-course to add more stories\n        3. Check if current sprint is complete and run retrospective\n      \u003C\u002Foutput>\n      \u003Caction>HALT\u003C\u002Faction>\n    \u003C\u002Fcheck>\n\n    \u003Caction>Extract from found story key (e.g., \"1-2-user-authentication\"):\n      - epic_num: first number before dash (e.g., \"1\")\n      - story_num: second number after first dash (e.g., \"2\")\n      - story_title: remainder after second dash (e.g., \"user-authentication\")\n    \u003C\u002Faction>\n    \u003Caction>Set {{story_id}} = \"{{epic_num}}.{{story_num}}\"\u003C\u002Faction>\n    \u003Caction>Store story_key for later use (e.g., \"1-2-user-authentication\")\u003C\u002Faction>\n\n    \u003C!-- Mark epic as in-progress if this is first story -->\n    \u003Caction>Check if this is the first story in epic {{epic_num}} by looking for {{epic_num}}-1-* pattern\u003C\u002Faction>\n    \u003Ccheck if=\"this is first story in epic {{epic_num}}\">\n      \u003Caction>Load {{sprint_status}} and check epic-{{epic_num}} status\u003C\u002Faction>\n      \u003Caction>If epic status is \"backlog\" → update to \"in-progress\"\u003C\u002Faction>\n      \u003Caction>If epic status is \"contexted\" (legacy status) → update to \"in-progress\" (backward compatibility)\u003C\u002Faction>\n      \u003Caction>If epic status is \"in-progress\" → no change needed\u003C\u002Faction>\n      \u003Ccheck if=\"epic status is 'done'\">\n        \u003Coutput>🚫 ERROR: Cannot create story in completed epic\u003C\u002Foutput>\n        \u003Coutput>Epic {{epic_num}} is marked as 'done'. All stories are complete.\u003C\u002Foutput>\n        \u003Coutput>If you need to add more work, either:\u003C\u002Foutput>\n        \u003Coutput>1. Manually change epic status back to 'in-progress' in sprint-status.yaml\u003C\u002Foutput>\n        \u003Coutput>2. Create a new epic for additional work\u003C\u002Foutput>\n        \u003Caction>HALT - Cannot proceed\u003C\u002Faction>\n      \u003C\u002Fcheck>\n      \u003Ccheck if=\"epic status is not one of: backlog, contexted, in-progress, done\">\n        \u003Coutput>🚫 ERROR: Invalid epic status '{{epic_status}}'\u003C\u002Foutput>\n        \u003Coutput>Epic {{epic_num}} has invalid status. Expected: backlog, in-progress, or done\u003C\u002Foutput>\n        \u003Coutput>Please fix sprint-status.yaml manually or run sprint-planning to regenerate\u003C\u002Foutput>\n        \u003Caction>HALT - Cannot proceed\u003C\u002Faction>\n      \u003C\u002Fcheck>\n      \u003Coutput>📊 Epic {{epic_num}} status updated to in-progress\u003C\u002Foutput>\n    \u003C\u002Fcheck>\n\n    \u003Caction>GOTO step 2a\u003C\u002Faction>\n\n  \u003C\u002Fcheck>\n  \u003Caction>Load the FULL file: {{sprint_status}}\u003C\u002Faction>\n  \u003Caction>Read ALL lines from beginning to end - do not skip any content\u003C\u002Faction>\n  \u003Caction>Parse the development_status section completely\u003C\u002Faction>\n\n\u003Caction>Find the FIRST story (by reading in order from top to bottom) where: - Key matches pattern: number-number-name (e.g., \"1-2-user-auth\") - NOT an epic key (epic-X) or retrospective (epic-X-retrospective) - Status value equals \"backlog\"\n\u003C\u002Faction>\n\n  \u003Ccheck if=\"no backlog story found\">\n    \u003Coutput>No backlog stories found in sprint-status.yaml\n\n      All stories are either already created, in progress, or done.\n\n      **Options:**\n      1. Run sprint-planning to refresh story tracking\n      2. Load PM agent and run correct-course to add more stories\n      3. Check if current sprint is complete and run retrospective\n    \u003C\u002Foutput>\n    \u003Caction>HALT\u003C\u002Faction>\n\n  \u003C\u002Fcheck>\n\n\u003Caction>Extract from found story key (e.g., \"1-2-user-authentication\"): - epic_num: first number before dash (e.g., \"1\") - story_num: second number after first dash (e.g., \"2\") - story_title: remainder after second dash (e.g., \"user-authentication\")\n\u003C\u002Faction>\n\u003Caction>Set {{story_id}} = \"{{epic_num}}.{{story_num}}\"\u003C\u002Faction>\n\u003Caction>Store story_key for later use (e.g., \"1-2-user-authentication\")\u003C\u002Faction>\n\n  \u003C!-- Mark epic as in-progress if this is first story -->\n\n\u003Caction>Check if this is the first story in epic {{epic_num}} by looking for {{epic_num}}-1-\\* pattern\u003C\u002Faction>\n\u003Ccheck if=\"this is first story in epic {{epic_num}}\">\n\u003Caction>Load {{sprint_status}} and check epic-{{epic_num}} status\u003C\u002Faction>\n\u003Caction>If epic status is \"backlog\" → update to \"in-progress\"\u003C\u002Faction>\n\u003Caction>If epic status is \"contexted\" (legacy status) → update to \"in-progress\" (backward compatibility)\u003C\u002Faction>\n\u003Caction>If epic status is \"in-progress\" → no change needed\u003C\u002Faction>\n\u003Ccheck if=\"epic status is 'done'\">\n\u003Coutput>ERROR: Cannot create story in completed epic\u003C\u002Foutput>\n\u003Coutput>Epic {{epic_num}} is marked as 'done'. All stories are complete.\u003C\u002Foutput>\n\u003Coutput>If you need to add more work, either:\u003C\u002Foutput>\n\u003Coutput>1. Manually change epic status back to 'in-progress' in sprint-status.yaml\u003C\u002Foutput>\n\u003Coutput>2. Create a new epic for additional work\u003C\u002Foutput>\n\u003Caction>HALT - Cannot proceed\u003C\u002Faction>\n\u003C\u002Fcheck>\n\u003Ccheck if=\"epic status is not one of: backlog, contexted, in-progress, done\">\n\u003Coutput>ERROR: Invalid epic status '{{epic_status}}'\u003C\u002Foutput>\n\u003Coutput>Epic {{epic_num}} has invalid status. Expected: backlog, in-progress, or done\u003C\u002Foutput>\n\u003Coutput>Please fix sprint-status.yaml manually or run sprint-planning to regenerate\u003C\u002Foutput>\n\u003Caction>HALT - Cannot proceed\u003C\u002Faction>\n\u003C\u002Fcheck>\n\u003Coutput>Epic {{epic_num}} status updated to in-progress\u003C\u002Foutput>\n\u003C\u002Fcheck>\n\n\u003Caction>GOTO step 2a\u003C\u002Faction>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"2\" goal=\"Load and analyze core artifacts\">\n  \u003Ccritical>🔬 EXHAUSTIVE ARTIFACT ANALYSIS - This is where you prevent future developer mistakes!\u003C\u002Fcritical>\n\n  \u003C!-- Load all available content through discovery protocol -->\n\n\u003Caction>Read fully and follow `.\u002Fdiscover-inputs.md` to load all input files\u003C\u002Faction>\n\u003Cnote>Available content: {epics_content}, {gdd_content}, {architecture_content}, {ux_content},\n{project_context}\u003C\u002Fnote>\n\n  \u003C!-- Analyze epics file for story foundation -->\n\n\u003Caction>From {epics_content}, extract Epic {{epic_num}} complete context:\u003C\u002Faction> **EPIC ANALYSIS:** - Epic\nobjectives and business value - ALL stories in this epic for cross-story context - Our specific story's requirements, user story\nstatement, acceptance criteria - Technical requirements and constraints - Dependencies on other stories\u002Fepics - Source hints pointing to\noriginal documents \u003C!-- Extract specific story requirements -->\n\u003Caction>Extract our story ({{epic_num}}-{{story_num}}) details:\u003C\u002Faction> **STORY FOUNDATION:** - User story statement\n(As a, I want, so that) - Detailed acceptance criteria (already BDD formatted) - Technical requirements specific to this story -\nBusiness context and value - Success criteria \u003C!-- Previous story analysis for context continuity -->\n\u003Ccheck if=\"story_num > 1\">\n\u003Caction>Find {{previous_story_num}}: scan {implementation_artifacts} for the story file in epic {{epic_num}} with the highest story number less than {{story_num}}\u003C\u002Faction>\n\u003Caction>Load previous story file: {implementation_artifacts}\u002F{{epic_num}}-{{previous_story_num}}-\\*.md\u003C\u002Faction> **PREVIOUS STORY INTELLIGENCE:** -\nDev notes and learnings from previous story - Review feedback and corrections needed - Files that were created\u002Fmodified and their\npatterns - Testing approaches that worked\u002Fdidn't work - Problems encountered and solutions found - Code patterns established \u003Caction>Extract\nall learnings that could impact current story implementation\u003C\u002Faction>\n\u003C\u002Fcheck>\n\n  \u003C!-- Project context analysis (game-dev extension for project-context.md extraction) -->\n  \u003Ccheck if=\"{project_context} was loaded and is not empty\">\n    \u003Caction>Analyze {project_context} for story-relevant rules and constraints:\u003C\u002Faction>\n    **PROJECT CONTEXT EXTRACTION:**\n    - Third-party frameworks and libraries required by the project\n    - MCP server configurations and integrations to use\n    - Coding conventions and patterns to follow\n    - Project-wide constraints (e.g., specific APIs, deployment targets)\n    - Any rules that apply to this story's implementation domain\n    \u003Caction>Store extracted project rules as {{project_rules}} for embedding in the story file\u003C\u002Faction>\n  \u003C\u002Fcheck>\n\n  \u003C!-- Git intelligence for previous work patterns -->\n\n\u003Ccheck\n    if=\"previous story exists AND git repository detected\">\n\u003Caction>Get last 5 commit titles to understand recent work patterns\u003C\u002Faction>\n\u003Caction>Analyze 1-5 most recent commits for relevance to current story: - Files created\u002Fmodified - Code patterns and conventions used - Library dependencies added\u002Fchanged - Architecture decisions implemented - Testing approaches used\n\u003C\u002Faction>\n\u003Caction>Extract actionable insights for current story implementation\u003C\u002Faction>\n\u003C\u002Fcheck>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"3\" goal=\"Architecture analysis for developer guardrails\">\n  \u003Ccritical>🏗️ ARCHITECTURE INTELLIGENCE - Extract everything the developer MUST follow!\u003C\u002Fcritical> **ARCHITECTURE DOCUMENT ANALYSIS:** \u003Caction>Systematically\n  analyze architecture content for story-relevant requirements:\u003C\u002Faction>\n\n  \u003C!-- Load architecture - single file or sharded -->\n  \u003Ccheck if=\"architecture file is single file\">\n    \u003Caction>Load complete {architecture_content}\u003C\u002Faction>\n  \u003C\u002Fcheck>\n  \u003Ccheck if=\"architecture is sharded to folder\">\n    \u003Caction>Load architecture index and scan all architecture files\u003C\u002Faction>\n  \u003C\u002Fcheck> **CRITICAL ARCHITECTURE EXTRACTION:** \u003Caction>For\n  each architecture section, determine if relevant to this story:\u003C\u002Faction> - **Technical Stack:** Languages, frameworks, libraries with\n  versions - **Code Structure:** Folder organization, naming conventions, file patterns - **API Patterns:** Service structure, endpoint\n  patterns, data contracts - **Database Schemas:** Tables, relationships, constraints relevant to story - **Security Requirements:**\n  Authentication patterns, authorization rules - **Performance Requirements:** Caching strategies, optimization patterns - **Testing\n  Standards:** Testing frameworks, coverage expectations, test patterns - **Deployment Patterns:** Environment configurations, build\n  processes - **Integration Patterns:** External service integrations, data flows \u003Caction>Extract any story-specific requirements that the\n  developer MUST follow\u003C\u002Faction>\n  \u003Caction>Identify any architectural decisions that override previous patterns\u003C\u002Faction>\n\n  \u003C!-- Read existing code being modified — non-negotiable -->\n\n\u003Ccritical>📂 READ FILES BEING MODIFIED — skipping this is the primary cause of implementation failures and review cycles\u003C\u002Fcritical>\n\u003Caction>From the architecture directory structure, identify every file marked UPDATE (not NEW) that this story will touch\u003C\u002Faction>\n\u003Caction>Read each relevant UPDATE file completely. For each one, document in dev notes: - Current state: what it does today (state machine, API calls, data shapes, existing behaviors) - What this story changes: the specific sections or behaviors being modified - What must be preserved: existing interactions and behaviors the story must not break\n\u003C\u002Faction>\n\u003Ccritical>A story implementation must leave the system working end-to-end — not just satisfy its stated ACs.\nIf a behavior is required for the feature to work correctly in the existing system, it is a requirement\nwhether or not it is explicitly written in the story. The dev agent owns this.\u003C\u002Fcritical>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"4\" goal=\"Web research for latest technical specifics\">\n  \u003Ccritical>🌐 ENSURE LATEST TECH KNOWLEDGE - Prevent outdated implementations!\u003C\u002Fcritical> **WEB INTELLIGENCE:** \u003Caction>Identify specific\n  technical areas that require latest version knowledge:\u003C\u002Faction>\n\n  \u003C!-- Check for libraries\u002Fframeworks mentioned in architecture -->\n\n\u003Caction>From architecture analysis, identify specific libraries, APIs, or\nframeworks\u003C\u002Faction>\n\u003Caction>For each critical technology, research latest stable version and key changes: - Latest API documentation and breaking changes - Security vulnerabilities or updates - Performance improvements or deprecations - Best practices for current version\n\u003C\u002Faction>\n**EXTERNAL CONTEXT INCLUSION:** \u003Caction>Include in story any critical latest information the developer needs: - Specific library versions and why chosen - API endpoints with parameters and authentication - Recent security patches or considerations - Performance optimization techniques - Migration considerations if upgrading\n\u003C\u002Faction>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"5\" goal=\"Create comprehensive story file\">\n  \u003Ccritical>📝 CREATE ULTIMATE STORY FILE - The developer's master implementation guide!\u003C\u002Fcritical>\n\n\u003Caction>Initialize from template.md:\n{default_output_file}\u003C\u002Faction>\n\u003Ctemplate-output file=\"{default_output_file}\">story_header\u003C\u002Ftemplate-output>\n\n  \u003C!-- Story foundation from epics analysis -->\n\n\u003Ctemplate-output\n    file=\"{default_output_file}\">story_requirements\u003C\u002Ftemplate-output>\n\n  \u003C!-- Developer context section - MOST IMPORTANT PART -->\n  \u003Ctemplate-output file=\"{default_output_file}\">\n  developer_context_section\u003C\u002Ftemplate-output> **DEV AGENT GUARDRAILS:** \u003Ctemplate-output file=\"{default_output_file}\">\n  technical_requirements\u003C\u002Ftemplate-output>\n  \u003Ctemplate-output file=\"{default_output_file}\">architecture_compliance\u003C\u002Ftemplate-output>\n  \u003Ctemplate-output\n    file=\"{default_output_file}\">library_framework_requirements\u003C\u002Ftemplate-output>\n  \u003Ctemplate-output file=\"{default_output_file}\">\n  file_structure_requirements\u003C\u002Ftemplate-output>\n  \u003Ctemplate-output file=\"{default_output_file}\">testing_requirements\u003C\u002Ftemplate-output>\n\n  \u003C!-- Previous story intelligence -->\n\n\u003Ccheck\n    if=\"previous story learnings available\">\n\u003Ctemplate-output file=\"{default_output_file}\">previous_story_intelligence\u003C\u002Ftemplate-output>\n\u003C\u002Fcheck>\n\n  \u003C!-- Git intelligence -->\n\n\u003Ccheck\n    if=\"git analysis completed\">\n\u003Ctemplate-output file=\"{default_output_file}\">git_intelligence_summary\u003C\u002Ftemplate-output>\n\u003C\u002Fcheck>\n\n  \u003C!-- Latest technical specifics -->\n  \u003Ccheck if=\"web research completed\">\n    \u003Ctemplate-output file=\"{default_output_file}\">latest_tech_information\u003C\u002Ftemplate-output>\n  \u003C\u002Fcheck>\n\n  \u003C!-- Project context rules - embed extracted rules from project-context.md (game-dev extension) -->\n  \u003Ccheck if=\"{{project_rules}} is not empty\">\n    \u003Ctemplate-output file=\"{default_output_file}\">project_context_reference\u003C\u002Ftemplate-output>\n    \u003Caction>Populate the Project Context Rules section with ALL extracted {{project_rules}} including:\n      - Required third-party frameworks and how they apply to this story\n      - MCP integrations the developer must use\n      - Project-wide conventions and constraints\n      - Any domain-specific rules relevant to this story's tasks\u003C\u002Faction>\n  \u003C\u002Fcheck>\n\n  \u003C!-- Final status update -->\n  \u003Ctemplate-output file=\"{default_output_file}\">\n  story_completion_status\u003C\u002Ftemplate-output>\n\n  \u003C!-- CRITICAL: Set status to ready-for-dev -->\n\n\u003Caction>Set story Status to: \"ready-for-dev\"\u003C\u002Faction>\n\u003Caction>Add completion note: \"Ultimate\ncontext engine analysis completed - comprehensive developer guide created\"\u003C\u002Faction>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"6\" goal=\"Update sprint status and finalize\">\n  \u003Caction>Validate the newly created story file {default_output_file} against `.\u002Fchecklist.md` and apply any required fixes before finalizing\u003C\u002Faction>\n  \u003Caction>Save story document unconditionally\u003C\u002Faction>\n\n  \u003C!-- Update sprint status -->\n  \u003Ccheck if=\"sprint status file exists\">\n    \u003Caction>Update {{sprint_status}}\u003C\u002Faction>\n    \u003Caction>Load the FULL file and read all development_status entries\u003C\u002Faction>\n    \u003Caction>Find development_status key matching {{story_key}}\u003C\u002Faction>\n    \u003Caction>Verify current status is \"backlog\" (expected previous state)\u003C\u002Faction>\n    \u003Caction>Update development_status[{{story_key}}] = \"ready-for-dev\"\u003C\u002Faction>\n    \u003Caction>Update last_updated field to current date\u003C\u002Faction>\n    \u003Caction>Save file, preserving ALL comments and structure including STATUS DEFINITIONS\u003C\u002Faction>\n  \u003C\u002Fcheck>\n\n\u003Caction>Report completion\u003C\u002Faction>\n\u003Coutput>**🎯 ULTIMATE BMad Method STORY CONTEXT CREATED, {user_name}!**\n\n    **Story Details:**\n    - Story ID: {{story_id}}\n    - Story Key: {{story_key}}\n    - File: {{story_file}}\n    - Status: ready-for-dev\n\n    **Next Steps:**\n    1. Review the comprehensive story in {{story_file}}\n    2. Run dev agents `dev-story` for optimized implementation\n    3. Run `code-review` when complete (auto-marks done)\n    4. Optional: If Test Architect module installed, run `\u002Fbmad:tea:automate` after `dev-story` to generate guardrail tests\n\n    **The developer now has everything needed for flawless implementation!**\n\n  \u003C\u002Foutput>\n\u003Caction>Run: `python3 {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_customization.py --skill {skill-root} --key workflow.on_complete` — if the resolved value is non-empty, follow it as the final terminal instruction before exiting.\u003C\u002Faction>\n\u003C\u002Fstep>\n\n\u003C\u002Fworkflow>\n",{"name":5,"description":7},"main","5d8b301b16a0b47e4c97f8c6d68ad82e0f86be2c",".agent\u002Fskills\u002Fgds-create-story",0,"https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design","https:\u002F\u002Fgithub.com\u002FOrigoStudio","Engineering ideas into products","2026-10-23 00:02:46",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add OrigoStudio\u002Forigo-design --skill gds-create-story",{"tool":38,"command":39},"bunx","bunx skills add OrigoStudio\u002Forigo-design --skill gds-create-story",{"tool":41,"command":42},"pnpm","pnpm dlx skills add OrigoStudio\u002Forigo-design --skill gds-create-story","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-story\u002FSKILL.md",true,[46,52,58,62],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"checklist.md","REFERENCE","参考文档",14379,"https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-story\u002Fchecklist.md",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"customize.toml","OTHER","其他",1641,"https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-story\u002Fcustomize.toml",{"path":59,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":60,"sourceHtmlUrl":61},"discover-inputs.md",3911,"https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-story\u002Fdiscover-inputs.md",{"path":63,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":64,"sourceHtmlUrl":65},"template.md",1158,"https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Fgds-create-story\u002Ftemplate.md",[67,74,81,88,95,102],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M79PWH7HW9TE5FTCHJ1W968C","wds-agent-saga-analyst","Strategic business analyst and product discovery partner for WDS. Use when the user asks to talk to Saga or requests the WDS analyst.","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwds-agent-saga-analyst\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M79PWF5EAQTMC3XZBEFGP3HW","wds-agent-mimir-builder","Implementation agent. Owns the tech audit, the PRD, and the build. Reads Freya's Work Orders and turns them into working code — one verified task at a time.","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwds-agent-mimir-builder\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M79PWCR1845ETM01V6SKVDMN","wds-agent-freya-ux","Strategic UX designer and design thinking partner for WDS. Use when the user asks to talk to Freya or requests the WDS designer.","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwds-agent-freya-ux\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M79PW9MEM3299WHP4DN0AS46","wds-8-product-evolution","Brownfield improvements — the full WDS pipeline in miniature for existing products","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwds-8-product-evolution\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M79PW81V0VQJJP0A9A47WR8N","wds-7-design-system","Create, import, browse, and maintain design system components and tokens","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwds-7-design-system\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M79PW550F0KPHSWF5Z8Z529B","wds-6-asset-generation","Generate visual and text assets from specifications through AI-powered creative production","https:\u002F\u002Fgithub.com\u002FOrigoStudio\u002Forigo-design\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwds-6-asset-generation\u002FSKILL.md",[],[]]