[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71N06TXREPZ4F1PRR4V1RG6":3,"skill-same:01M71N06TXREPZ4F1PRR4V1RG6":72},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":45,"install":46,"resources":59},"01M71N06TXREPZ4F1PRR4V1RG6","gds-correct-course",null,"Manage significant changes during sprint execution. Use when the user says \"correct course\" or \"propose sprint change\"","developAgent\u002Fbmad-start","developAgent","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F264530239?v=4","01M71J8X6CY24V5ZZHFGETRMSW","01M71J8X739FS28DGQAAY7V4QR",1,"MIT","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.gemini\u002Fskills\u002Fgds-correct-course\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[23,24,25,26,27,28,29,30,31,32,33],"correct","gds correct course","course","change","execution","user","use","manage","sprint","changes","when","2026-11-10 10:56:23",false,"---\nname: gds-correct-course\ndescription: 'Manage significant changes during sprint execution. Use when the user says \"correct course\" or \"propose sprint change\"'\n---\n\n# Correct Course - Sprint Change Management Workflow\n\n**Goal:** Manage significant changes during sprint execution by analyzing impact across all project artifacts and producing a structured Sprint Change Proposal.\n\n**Your Role:** You are a Developer navigating change management. Analyze the triggering issue, assess impact across GDD, epics, architecture, and UX artifacts, and produce an actionable Sprint Change Proposal with clear handoff.\n\n## Conventions\n\n- Bare paths (e.g. `checklist.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- `project_name`, `user_name`\n- `communication_language`, `document_output_language`\n- `game_dev_experience`\n- `implementation_artifacts`\n- `planning_artifacts`\n- `project_knowledge`\n- `date` as system-generated current datetime\n- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`\n- Language MUST be tailored to `{game_dev_experience}`\n- Generate all documents in `{document_output_language}`\n- DOCUMENT OUTPUT: Updated epics, stories, or GDD sections. Clear, actionable changes. Game dev experience (`{game_dev_experience}`) affects conversation style ONLY, not document updates.\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. Begin the workflow below.\n\n## Paths\n\n- `default_output_file` = `{planning_artifacts}\u002Fsprint-change-proposal-{date}.md`\n\n## Input Files\n\n| Input | Path | Load Strategy |\n|-------|------|---------------|\n| GDD | `{planning_artifacts}\u002F*gdd*.md` (whole) or `{planning_artifacts}\u002F*gdd*\u002F*.md` (sharded) | FULL_LOAD |\n| Narrative | `{planning_artifacts}\u002F*narrative*.md` (whole) or `{planning_artifacts}\u002F*narrative*\u002F*.md` (sharded) | FULL_LOAD |\n| Epics | `{planning_artifacts}\u002F*epic*.md` (whole) or `{planning_artifacts}\u002F*epic*\u002F*.md` (sharded) | FULL_LOAD |\n| Architecture | `{planning_artifacts}\u002F*architecture*.md` (whole) or `{planning_artifacts}\u002F*architecture*\u002F*.md` (sharded) | FULL_LOAD |\n| UX Design | `{planning_artifacts}\u002F*ux*.md` (whole) or `{planning_artifacts}\u002F*ux*\u002F*.md` (sharded) | FULL_LOAD |\n| Tech Spec | `{planning_artifacts}\u002F*tech-spec*.md` (whole) or `{planning_artifacts}\u002F*spec-*.md` (whole) | FULL_LOAD |\n| Document Project | `{project_knowledge}\u002Findex.md` (sharded) | INDEX_GUIDED |\n\n### Context\n\n- Load `**\u002Fproject-context.md` if it exists\n\n## Execution\n\n### Document Discovery - Loading Project Artifacts\n\n**Strategy**: Course correction needs broad project context to assess change impact accurately. Load all available planning artifacts.\n\n**Discovery Process for FULL_LOAD documents (GDD, Narrative, Epics, Architecture, UX Design, Tech Spec):**\n\n1. **Search for whole document first** - Look for files matching the whole-document pattern (e.g., `*gdd*.md`, `*narrative*.md`, `*epic*.md`, `*architecture*.md`, `*ux*.md`, `*tech-spec*.md`)\n2. **Check for sharded version** - If whole document not found, look for a directory with `index.md` (e.g., `gdd\u002Findex.md`, `epics\u002Findex.md`)\n3. **If sharded version found**:\n   - Read `index.md` to understand the document structure\n   - Read ALL section files listed in the index\n   - Process the combined content as a single document\n4. **Priority**: If both whole and sharded versions exist, use the whole document\n\n**Discovery Process for INDEX_GUIDED documents (Document Project):**\n\n1. **Search for index file** - Look for `{project_knowledge}\u002Findex.md`\n2. **If found**: Read the index to understand available documentation sections\n3. **Selectively load sections** based on relevance to the change being analyzed — do NOT load everything, only sections that relate to the impacted areas\n4. **This document is optional** — skip if `{project_knowledge}` does not exist (greenfield projects)\n\n**Fuzzy matching**: Be flexible with document names — users may use variations like `gdd.md`, `game-design-document.md`, etc.\n\n**Missing documents**: Not all documents may exist. GDD and Epics are essential; Architecture, UX Design, Tech Spec, Narrative, and Document Project are loaded if available. HALT if GDD or Epics cannot be found.\n\n\u003Cworkflow>\n\n\u003Cstep n=\"1\" goal=\"Initialize Change Navigation\">\n  \u003Caction>Load **\u002Fproject-context.md for coding standards and project-wide patterns (if exists)\u003C\u002Faction>\n  \u003Caction>Confirm change trigger and gather user description of the issue\u003C\u002Faction>\n  \u003Caction>Ask: \"What specific issue or change has been identified that requires navigation?\"\u003C\u002Faction>\n  \u003Caction>Verify access to required project documents:\u003C\u002Faction>\n    - GDD (Game Design Document)\n    - Current Epics and Stories\n    - Architecture documentation\n    - UI\u002FUX specifications\n    - Narrative Design documentation\n  \u003Caction>Ask user for mode preference:\u003C\u002Faction>\n    - **Incremental** (recommended): Refine each edit collaboratively\n    - **Batch**: Present all changes at once for review\n  \u003Caction>Store mode selection for use throughout workflow\u003C\u002Faction>\n\n\u003Caction if=\"change trigger is unclear\">HALT: \"Cannot navigate change without clear understanding of the triggering issue. Please provide specific details about what needs to change and why.\"\u003C\u002Faction>\n\n\u003Caction if=\"core documents are unavailable\">HALT: \"Need access to project documents (GDD, Epics, Architecture, UI\u002FUX) to assess change impact. Please ensure these documents are accessible.\"\u003C\u002Faction>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"2\" goal=\"Execute Change Analysis Checklist\">\n  \u003Caction>Read fully and follow the systematic analysis from: checklist.md\u003C\u002Faction>\n  \u003Caction>Work through each checklist section interactively with the user\u003C\u002Faction>\n  \u003Caction>Record status for each checklist item:\u003C\u002Faction>\n    - [x] Done - Item completed successfully\n    - [N\u002FA] Skip - Item not applicable to this change\n    - [!] Action-needed - Item requires attention or follow-up\n  \u003Caction>Maintain running notes of findings and impacts discovered\u003C\u002Faction>\n  \u003Caction>Present checklist progress after each major section\u003C\u002Faction>\n\n\u003Caction if=\"checklist cannot be completed\">Identify blocking issues and work with user to resolve before continuing\u003C\u002Faction>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"3\" goal=\"Draft Specific Change Proposals\">\n\u003Caction>Based on checklist findings, create explicit edit proposals for each identified artifact\u003C\u002Faction>\n\n\u003Caction>For Story changes:\u003C\u002Faction>\n\n- Show old → new text format\n- Include story ID and section being modified\n- Provide rationale for each change\n- Example format:\n\n  ```\n  Story: [STORY-123] User Authentication\n  Section: Acceptance Criteria\n\n  OLD:\n  - User can log in with email\u002Fpassword\n\n  NEW:\n  - User can log in with email\u002Fpassword\n  - User can enable 2FA via authenticator app\n\n  Rationale: Security requirement identified during implementation\n  ```\n\n\u003Caction>For GDD modifications:\u003C\u002Faction>\n\n- Specify exact sections to update\n- Show current content and proposed changes\n- Explain impact on MVP scope and requirements\n\n\u003Caction>For Narrative Design modifications:\u003C\u002Faction>\n\n- Specify exact sections to update\n- Show current content and proposed changes\n- Explain impact on story, character, or world-building consistency\n\n\u003Caction>For Architecture changes:\u003C\u002Faction>\n\n- Identify affected components, patterns, or technology choices\n- Describe diagram updates needed\n- Note any ripple effects on other components\n\n\u003Caction>For UI\u002FUX specification updates:\u003C\u002Faction>\n\n- Reference specific screens or components\n- Show wireframe or flow changes needed\n- Connect changes to user experience impact\n\n\u003Ccheck if=\"mode is Incremental\">\n  \u003Caction>Present each edit proposal individually\u003C\u002Faction>\n  \u003Cask>Review and refine this change? Options: Approve [a], Edit [e], Skip [s]\u003C\u002Fask>\n  \u003Caction>Iterate on each proposal based on user feedback\u003C\u002Faction>\n\u003C\u002Fcheck>\n\n\u003Caction if=\"mode is Batch\">Collect all edit proposals and present together at end of step\u003C\u002Faction>\n\n\u003C\u002Fstep>\n\n\u003Cstep n=\"4\" goal=\"Generate Sprint Change Proposal\">\n\u003Caction>Compile comprehensive Sprint Change Proposal document with following sections:\u003C\u002Faction>\n\n\u003Caction>Section 1: Issue Summary\u003C\u002Faction>\n\n- Clear problem statement describing what triggered the change\n- Context about when\u002Fhow the issue was discovered\n- Evidence or examples demonstrating the issue\n\n\u003Caction>Section 2: Impact Analysis\u003C\u002Faction>\n\n- Epic Impact: Which epics are affected and how\n- Story Impact: Current and future stories requiring changes\n- Artifact Conflicts: GDD, Narrative, Architecture, UI\u002FUX documents needing updates\n- Technical Impact: Code, infrastructure, or deployment implications\n\n\u003Caction>Section 3: Recommended Approach\u003C\u002Faction>\n\n- Present chosen path forward from checklist evaluation:\n  - Direct Adjustment: Modify\u002Fadd stories within existing plan\n  - Potential Rollback: Revert completed work to simplify resolution\n  - MVP Review: Reduce scope or modify goals\n- Provide clear rationale for recommendation\n- Include effort estimate, risk assessment, and timeline impact\n\n\u003Caction>Section 4: Detailed Change Proposals\u003C\u002Faction>\n\n- Include all refined edit proposals from Step 3\n- Group by artifact type (Stories, GDD, Narrative, Architecture, UI\u002FUX)\n- Ensure each change includes before\u002Fafter and justification\n\n\u003Caction>Section 5: Implementation Handoff\u003C\u002Faction>\n\n- Categorize change scope:\n  - Minor: Direct implementation by Developer agent\n  - Moderate: Backlog reorganization needed (PO\u002FDEV)\n  - Major: Fundamental replan required (PM\u002FArchitect)\n- Specify handoff recipients and their responsibilities\n- Define success criteria for implementation\n\n\u003Caction>Present complete Sprint Change Proposal to user\u003C\u002Faction>\n\u003Caction>Write Sprint Change Proposal document to {default_output_file}\u003C\u002Faction>\n\u003Cask>Review complete proposal. Continue [c] or Edit [e]?\u003C\u002Fask>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"5\" goal=\"Finalize and Route for Implementation\">\n\u003Caction>Get explicit user approval for complete proposal\u003C\u002Faction>\n\u003Cask>Do you approve this Sprint Change Proposal for implementation? (yes\u002Fno\u002Frevise)\u003C\u002Fask>\n\n\u003Ccheck if=\"no or revise\">\n  \u003Caction>Gather specific feedback on what needs adjustment\u003C\u002Faction>\n  \u003Caction>Return to appropriate step to address concerns\u003C\u002Faction>\n  \u003Cgoto step=\"3\">If changes needed to edit proposals\u003C\u002Fgoto>\n  \u003Cgoto step=\"4\">If changes needed to overall proposal structure\u003C\u002Fgoto>\n\n\u003C\u002Fcheck>\n\n\u003Ccheck if=\"yes the proposal is approved by the user\">\n  \u003Caction>Finalize Sprint Change Proposal document\u003C\u002Faction>\n  \u003Caction>Determine change scope classification:\u003C\u002Faction>\n\n- **Minor**: Can be implemented directly by Developer agent\n- **Moderate**: Requires backlog reorganization and PO\u002FDEV coordination\n- **Major**: Needs fundamental replan with PM\u002FArchitect involvement\n\n\u003Caction>Provide appropriate handoff based on scope:\u003C\u002Faction>\n\n\u003C\u002Fcheck>\n\n\u003Ccheck if=\"Minor scope\">\n  \u003Caction>Route to: Developer agent for direct implementation\u003C\u002Faction>\n  \u003Caction>Deliverables: Finalized edit proposals and implementation tasks\u003C\u002Faction>\n\u003C\u002Fcheck>\n\n\u003Ccheck if=\"Moderate scope\">\n  \u003Caction>Route to: Product Owner \u002F Developer agents\u003C\u002Faction>\n  \u003Caction>Deliverables: Sprint Change Proposal + backlog reorganization plan\u003C\u002Faction>\n\u003C\u002Fcheck>\n\n\u003Ccheck if=\"Major scope\">\n  \u003Caction>Route to: Product Manager \u002F Solution Architect\u003C\u002Faction>\n  \u003Caction>Deliverables: Complete Sprint Change Proposal + escalation notice\u003C\u002Faction>\n\n\u003Caction>Confirm handoff completion and next steps with user\u003C\u002Faction>\n\u003Caction>Document handoff in workflow execution log\u003C\u002Faction>\n\u003C\u002Fcheck>\n\n\u003C\u002Fstep>\n\n\u003Cstep n=\"6\" goal=\"Workflow Completion\">\n\u003Caction>Summarize workflow execution:\u003C\u002Faction>\n  - Issue addressed: {{change_trigger}}\n  - Change scope: {{scope_classification}}\n  - Artifacts modified: {{list_of_artifacts}}\n  - Routed to: {{handoff_recipients}}\n\n\u003Caction>Confirm all deliverables produced:\u003C\u002Faction>\n\n- Sprint Change Proposal document\n- Specific edit proposals with before\u002Fafter\n- Implementation handoff plan\n\n\u003Caction>Report workflow completion to user with personalized message: \"Correct Course workflow complete, {user_name}!\"\u003C\u002Faction>\n\u003Caction>Remind user of success criteria and next steps for Developer agent\u003C\u002Faction>\n\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","# Correct Course - Sprint Change Management Workflow\n\n**Goal:** Manage significant changes during sprint execution by analyzing impact across all project artifacts and producing a structured Sprint Change Proposal.\n\n**Your Role:** You are a Developer navigating change management. Analyze the triggering issue, assess impact across GDD, epics, architecture, and UX artifacts, and produce an actionable Sprint Change Proposal with clear handoff.\n\n## Conventions\n\n- Bare paths (e.g. `checklist.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- `project_name`, `user_name`\n- `communication_language`, `document_output_language`\n- `game_dev_experience`\n- `implementation_artifacts`\n- `planning_artifacts`\n- `project_knowledge`\n- `date` as system-generated current datetime\n- YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}`\n- Language MUST be tailored to `{game_dev_experience}`\n- Generate all documents in `{document_output_language}`\n- DOCUMENT OUTPUT: Updated epics, stories, or GDD sections. Clear, actionable changes. Game dev experience (`{game_dev_experience}`) affects conversation style ONLY, not document updates.\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. Begin the workflow below.\n\n## Paths\n\n- `default_output_file` = `{planning_artifacts}\u002Fsprint-change-proposal-{date}.md`\n\n## Input Files\n\n| Input | Path | Load Strategy |\n|-------|------|---------------|\n| GDD | `{planning_artifacts}\u002F*gdd*.md` (whole) or `{planning_artifacts}\u002F*gdd*\u002F*.md` (sharded) | FULL_LOAD |\n| Narrative | `{planning_artifacts}\u002F*narrative*.md` (whole) or `{planning_artifacts}\u002F*narrative*\u002F*.md` (sharded) | FULL_LOAD |\n| Epics | `{planning_artifacts}\u002F*epic*.md` (whole) or `{planning_artifacts}\u002F*epic*\u002F*.md` (sharded) | FULL_LOAD |\n| Architecture | `{planning_artifacts}\u002F*architecture*.md` (whole) or `{planning_artifacts}\u002F*architecture*\u002F*.md` (sharded) | FULL_LOAD |\n| UX Design | `{planning_artifacts}\u002F*ux*.md` (whole) or `{planning_artifacts}\u002F*ux*\u002F*.md` (sharded) | FULL_LOAD |\n| Tech Spec | `{planning_artifacts}\u002F*tech-spec*.md` (whole) or `{planning_artifacts}\u002F*spec-*.md` (whole) | FULL_LOAD |\n| Document Project | `{project_knowledge}\u002Findex.md` (sharded) | INDEX_GUIDED |\n\n### Context\n\n- Load `**\u002Fproject-context.md` if it exists\n\n## Execution\n\n### Document Discovery - Loading Project Artifacts\n\n**Strategy**: Course correction needs broad project context to assess change impact accurately. Load all available planning artifacts.\n\n**Discovery Process for FULL_LOAD documents (GDD, Narrative, Epics, Architecture, UX Design, Tech Spec):**\n\n1. **Search for whole document first** - Look for files matching the whole-document pattern (e.g., `*gdd*.md`, `*narrative*.md`, `*epic*.md`, `*architecture*.md`, `*ux*.md`, `*tech-spec*.md`)\n2. **Check for sharded version** - If whole document not found, look for a directory with `index.md` (e.g., `gdd\u002Findex.md`, `epics\u002Findex.md`)\n3. **If sharded version found**:\n   - Read `index.md` to understand the document structure\n   - Read ALL section files listed in the index\n   - Process the combined content as a single document\n4. **Priority**: If both whole and sharded versions exist, use the whole document\n\n**Discovery Process for INDEX_GUIDED documents (Document Project):**\n\n1. **Search for index file** - Look for `{project_knowledge}\u002Findex.md`\n2. **If found**: Read the index to understand available documentation sections\n3. **Selectively load sections** based on relevance to the change being analyzed — do NOT load everything, only sections that relate to the impacted areas\n4. **This document is optional** — skip if `{project_knowledge}` does not exist (greenfield projects)\n\n**Fuzzy matching**: Be flexible with document names — users may use variations like `gdd.md`, `game-design-document.md`, etc.\n\n**Missing documents**: Not all documents may exist. GDD and Epics are essential; Architecture, UX Design, Tech Spec, Narrative, and Document Project are loaded if available. HALT if GDD or Epics cannot be found.\n\n\u003Cworkflow>\n\n\u003Cstep n=\"1\" goal=\"Initialize Change Navigation\">\n  \u003Caction>Load **\u002Fproject-context.md for coding standards and project-wide patterns (if exists)\u003C\u002Faction>\n  \u003Caction>Confirm change trigger and gather user description of the issue\u003C\u002Faction>\n  \u003Caction>Ask: \"What specific issue or change has been identified that requires navigation?\"\u003C\u002Faction>\n  \u003Caction>Verify access to required project documents:\u003C\u002Faction>\n    - GDD (Game Design Document)\n    - Current Epics and Stories\n    - Architecture documentation\n    - UI\u002FUX specifications\n    - Narrative Design documentation\n  \u003Caction>Ask user for mode preference:\u003C\u002Faction>\n    - **Incremental** (recommended): Refine each edit collaboratively\n    - **Batch**: Present all changes at once for review\n  \u003Caction>Store mode selection for use throughout workflow\u003C\u002Faction>\n\n\u003Caction if=\"change trigger is unclear\">HALT: \"Cannot navigate change without clear understanding of the triggering issue. Please provide specific details about what needs to change and why.\"\u003C\u002Faction>\n\n\u003Caction if=\"core documents are unavailable\">HALT: \"Need access to project documents (GDD, Epics, Architecture, UI\u002FUX) to assess change impact. Please ensure these documents are accessible.\"\u003C\u002Faction>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"2\" goal=\"Execute Change Analysis Checklist\">\n  \u003Caction>Read fully and follow the systematic analysis from: checklist.md\u003C\u002Faction>\n  \u003Caction>Work through each checklist section interactively with the user\u003C\u002Faction>\n  \u003Caction>Record status for each checklist item:\u003C\u002Faction>\n    - [x] Done - Item completed successfully\n    - [N\u002FA] Skip - Item not applicable to this change\n    - [!] Action-needed - Item requires attention or follow-up\n  \u003Caction>Maintain running notes of findings and impacts discovered\u003C\u002Faction>\n  \u003Caction>Present checklist progress after each major section\u003C\u002Faction>\n\n\u003Caction if=\"checklist cannot be completed\">Identify blocking issues and work with user to resolve before continuing\u003C\u002Faction>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"3\" goal=\"Draft Specific Change Proposals\">\n\u003Caction>Based on checklist findings, create explicit edit proposals for each identified artifact\u003C\u002Faction>\n\n\u003Caction>For Story changes:\u003C\u002Faction>\n\n- Show old → new text format\n- Include story ID and section being modified\n- Provide rationale for each change\n- Example format:\n\n  ```\n  Story: [STORY-123] User Authentication\n  Section: Acceptance Criteria\n\n  OLD:\n  - User can log in with email\u002Fpassword\n\n  NEW:\n  - User can log in with email\u002Fpassword\n  - User can enable 2FA via authenticator app\n\n  Rationale: Security requirement identified during implementation\n  ```\n\n\u003Caction>For GDD modifications:\u003C\u002Faction>\n\n- Specify exact sections to update\n- Show current content and proposed changes\n- Explain impact on MVP scope and requirements\n\n\u003Caction>For Narrative Design modifications:\u003C\u002Faction>\n\n- Specify exact sections to update\n- Show current content and proposed changes\n- Explain impact on story, character, or world-building consistency\n\n\u003Caction>For Architecture changes:\u003C\u002Faction>\n\n- Identify affected components, patterns, or technology choices\n- Describe diagram updates needed\n- Note any ripple effects on other components\n\n\u003Caction>For UI\u002FUX specification updates:\u003C\u002Faction>\n\n- Reference specific screens or components\n- Show wireframe or flow changes needed\n- Connect changes to user experience impact\n\n\u003Ccheck if=\"mode is Incremental\">\n  \u003Caction>Present each edit proposal individually\u003C\u002Faction>\n  \u003Cask>Review and refine this change? Options: Approve [a], Edit [e], Skip [s]\u003C\u002Fask>\n  \u003Caction>Iterate on each proposal based on user feedback\u003C\u002Faction>\n\u003C\u002Fcheck>\n\n\u003Caction if=\"mode is Batch\">Collect all edit proposals and present together at end of step\u003C\u002Faction>\n\n\u003C\u002Fstep>\n\n\u003Cstep n=\"4\" goal=\"Generate Sprint Change Proposal\">\n\u003Caction>Compile comprehensive Sprint Change Proposal document with following sections:\u003C\u002Faction>\n\n\u003Caction>Section 1: Issue Summary\u003C\u002Faction>\n\n- Clear problem statement describing what triggered the change\n- Context about when\u002Fhow the issue was discovered\n- Evidence or examples demonstrating the issue\n\n\u003Caction>Section 2: Impact Analysis\u003C\u002Faction>\n\n- Epic Impact: Which epics are affected and how\n- Story Impact: Current and future stories requiring changes\n- Artifact Conflicts: GDD, Narrative, Architecture, UI\u002FUX documents needing updates\n- Technical Impact: Code, infrastructure, or deployment implications\n\n\u003Caction>Section 3: Recommended Approach\u003C\u002Faction>\n\n- Present chosen path forward from checklist evaluation:\n  - Direct Adjustment: Modify\u002Fadd stories within existing plan\n  - Potential Rollback: Revert completed work to simplify resolution\n  - MVP Review: Reduce scope or modify goals\n- Provide clear rationale for recommendation\n- Include effort estimate, risk assessment, and timeline impact\n\n\u003Caction>Section 4: Detailed Change Proposals\u003C\u002Faction>\n\n- Include all refined edit proposals from Step 3\n- Group by artifact type (Stories, GDD, Narrative, Architecture, UI\u002FUX)\n- Ensure each change includes before\u002Fafter and justification\n\n\u003Caction>Section 5: Implementation Handoff\u003C\u002Faction>\n\n- Categorize change scope:\n  - Minor: Direct implementation by Developer agent\n  - Moderate: Backlog reorganization needed (PO\u002FDEV)\n  - Major: Fundamental replan required (PM\u002FArchitect)\n- Specify handoff recipients and their responsibilities\n- Define success criteria for implementation\n\n\u003Caction>Present complete Sprint Change Proposal to user\u003C\u002Faction>\n\u003Caction>Write Sprint Change Proposal document to {default_output_file}\u003C\u002Faction>\n\u003Cask>Review complete proposal. Continue [c] or Edit [e]?\u003C\u002Fask>\n\u003C\u002Fstep>\n\n\u003Cstep n=\"5\" goal=\"Finalize and Route for Implementation\">\n\u003Caction>Get explicit user approval for complete proposal\u003C\u002Faction>\n\u003Cask>Do you approve this Sprint Change Proposal for implementation? (yes\u002Fno\u002Frevise)\u003C\u002Fask>\n\n\u003Ccheck if=\"no or revise\">\n  \u003Caction>Gather specific feedback on what needs adjustment\u003C\u002Faction>\n  \u003Caction>Return to appropriate step to address concerns\u003C\u002Faction>\n  \u003Cgoto step=\"3\">If changes needed to edit proposals\u003C\u002Fgoto>\n  \u003Cgoto step=\"4\">If changes needed to overall proposal structure\u003C\u002Fgoto>\n\n\u003C\u002Fcheck>\n\n\u003Ccheck if=\"yes the proposal is approved by the user\">\n  \u003Caction>Finalize Sprint Change Proposal document\u003C\u002Faction>\n  \u003Caction>Determine change scope classification:\u003C\u002Faction>\n\n- **Minor**: Can be implemented directly by Developer agent\n- **Moderate**: Requires backlog reorganization and PO\u002FDEV coordination\n- **Major**: Needs fundamental replan with PM\u002FArchitect involvement\n\n\u003Caction>Provide appropriate handoff based on scope:\u003C\u002Faction>\n\n\u003C\u002Fcheck>\n\n\u003Ccheck if=\"Minor scope\">\n  \u003Caction>Route to: Developer agent for direct implementation\u003C\u002Faction>\n  \u003Caction>Deliverables: Finalized edit proposals and implementation tasks\u003C\u002Faction>\n\u003C\u002Fcheck>\n\n\u003Ccheck if=\"Moderate scope\">\n  \u003Caction>Route to: Product Owner \u002F Developer agents\u003C\u002Faction>\n  \u003Caction>Deliverables: Sprint Change Proposal + backlog reorganization plan\u003C\u002Faction>\n\u003C\u002Fcheck>\n\n\u003Ccheck if=\"Major scope\">\n  \u003Caction>Route to: Product Manager \u002F Solution Architect\u003C\u002Faction>\n  \u003Caction>Deliverables: Complete Sprint Change Proposal + escalation notice\u003C\u002Faction>\n\n\u003Caction>Confirm handoff completion and next steps with user\u003C\u002Faction>\n\u003Caction>Document handoff in workflow execution log\u003C\u002Faction>\n\u003C\u002Fcheck>\n\n\u003C\u002Fstep>\n\n\u003Cstep n=\"6\" goal=\"Workflow Completion\">\n\u003Caction>Summarize workflow execution:\u003C\u002Faction>\n  - Issue addressed: {{change_trigger}}\n  - Change scope: {{scope_classification}}\n  - Artifacts modified: {{list_of_artifacts}}\n  - Routed to: {{handoff_recipients}}\n\n\u003Caction>Confirm all deliverables produced:\u003C\u002Faction>\n\n- Sprint Change Proposal document\n- Specific edit proposals with before\u002Fafter\n- Implementation handoff plan\n\n\u003Caction>Report workflow completion to user with personalized message: \"Correct Course workflow complete, {user_name}!\"\u003C\u002Faction>\n\u003Caction>Remind user of success criteria and next steps for Developer agent\u003C\u002Faction>\n\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","1907bbe850fb749efa8b499b8da7ebb78a663519",".gemini\u002Fskills\u002Fgds-correct-course",0,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start","https:\u002F\u002Fgithub.com\u002FdevelopAgent","2026-07-19 05:19:22",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add developAgent\u002Fbmad-start --skill gds-correct-course",{"tool":52,"command":53},"bunx","bunx skills add developAgent\u002Fbmad-start --skill gds-correct-course",{"tool":55,"command":56},"pnpm","pnpm dlx skills add developAgent\u002Fbmad-start --skill gds-correct-course","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.gemini\u002Fskills\u002Fgds-correct-course\u002FSKILL.md",true,[60,66],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"checklist.md","REFERENCE","参考文档",11634,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.gemini\u002Fskills\u002Fgds-correct-course\u002Fchecklist.md",{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"customize.toml","OTHER","其他",1641,"https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.gemini\u002Fskills\u002Fgds-correct-course\u002Fcustomize.toml",[73,80,112,130,144,170],{"skillNo":74,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":78,"publishedAt":79},"01M71R3M9DJTTY0ARFQ6K04NMP","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.rovodev\u002Fskills\u002Fgds-correct-course\u002FSKILL.md",[77],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[24,25,23,28,32,26,33,29,27,30,31],"2026-11-10 13:02:02",{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":94,"publishedAt":79},"01M71R3GENSFD1A1XVZTTQG1KF","gds-code-review","Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says \"run code review\" or \"review this code\"","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.rovodev\u002Fskills\u002Fgds-code-review\u002FSKILL.md",[86,91],{"categoryNo":87,"categoryName":88,"taxonomyType":89,"taxonomyTypeDesc":90},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":92,"categoryName":93,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000030","开发工程师",[95,96,97,98,99,32,100,101,102,103,104,105,106,33,107,29,108,109,110,111],"code review","code","review","gds code review","categories","triage","review code","run","parallel","case","with","run code","acceptance","edge","actionable","layers","hunter",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":79},"01M71R3DD098MQRD6F8S4GG0AW","gds-check-implementation-readiness","Verify GDD, UX, Architecture, and Epics alignment before production. Use when the user says \"check readiness\" or \"implementation readiness\"","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.rovodev\u002Fskills\u002Fgds-check-implementation-readiness\u002FSKILL.md",[],[119,120,121,122,123,124,28,125,126,127,128,33,29,129],"check","readiness","Implementation Readiness","gds check implementation readiness","implementation","check readiness","Production","ux","verify","architecture","alignment",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":79},"01M71R3ACAA1G0NVQ330JQNJPK","gds-brainstorm-game","Facilitate game brainstorming sessions with game-specific techniques. Use when the user says \"brainstorm game\" or \"game ideas\"","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.rovodev\u002Fskills\u002Fgds-brainstorm-game\u002FSKILL.md",[],[137,138,139,28,140,105,33,29,141,142,143],"gds brainstorm game","game","brainstorm","brainstorming","techniques","sessions","ideas",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":153,"publishedAt":79},"01M71R377MJ6WJTTFARGKH3HX7","gds-agent-tech-writer","Technical documentation specialist and knowledge curator for game projects. Use when the user asks to talk to Paige or requests the Technical Writer.","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.rovodev\u002Fskills\u002Fgds-agent-tech-writer\u002FSKILL.md",[150],{"categoryNo":151,"categoryName":152,"taxonomyType":89,"taxonomyTypeDesc":90},"01JBSEEDCAT000000000000023","Skill与智能体开发",[154,155,156,157,29,158,159,160,161,33,28,162,163,164,165,166,167,168,138,169],"gds agent tech writer","tech","writer","technical writer","technical","knowledge","for","projects","technical documentation","talk","specialist","documentation specialist","knowledge curator","requests","documentation","curator",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":177,"publishedAt":79},"01M71R34RGT2ZX3TSFA2CRT0NC","gds-agent-game-solo-dev","Elite indie game developer for rapid prototyping and solo quick-flow development. Use when the user asks to talk to Indie or requests the Game Solo Dev.","https:\u002F\u002Fgithub.com\u002FdevelopAgent\u002Fbmad-start\u002Fblob\u002Fmain\u002F.rovodev\u002Fskills\u002Fgds-agent-game-solo-dev\u002FSKILL.md",[176],{"categoryNo":151,"categoryName":152,"taxonomyType":89,"taxonomyTypeDesc":90},[178,138,179,180,181,182,28,163,167,183,184,33,29,185,160,186,187],"solo","gds agent game solo dev","dev","flow","developer","RAPID","game developer","prototyping","development","quick"]