[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AMAZYDTXJ40GEYNSCJMBQB":3,"skill-same:01M7AMAZYDTXJ40GEYNSCJMBQB":56},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7AMAZYDTXJ40GEYNSCJMBQB","bmad-correct-course",null,"Manage significant changes during sprint execution. Use when the user says \"correct course\" or \"propose sprint change\"","zaurakworks\u002Fagent-system","zaurakworks","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F317111357?v=4","01M7AM97CDHZBZWB7HQWS5KXTG","01M7AM97D2BT6WP9MT76TV8WGG",1,"MIT","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-correct-course\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bmad-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 PRD, 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: `uv run {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\u002Fbmm\u002Fconfig.yaml` and resolve:\n\n- `project_name`, `user_name`\n- `communication_language`, `document_output_language`\n- `user_skill_level`\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 `{user_skill_level}`\n- Generate all documents in `{document_output_language}`\n- DOCUMENT OUTPUT: Updated epics, stories, or PRD sections. Clear, actionable changes. User skill level (`{user_skill_level}`) 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. 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## 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| PRD | `{planning_artifacts}\u002F*prd*.md` (whole) or `{planning_artifacts}\u002F*prd*\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| Spec | `{planning_artifacts}\u002F*spec-*.md` (whole) | FULL_LOAD |\n| Project Context | `AGENTS.md` in the affected repo (the `bmad:context` block) | FULL_LOAD |\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 (PRD, Epics, Architecture, UX Design, Spec):**\n\n1. **Search for whole document first** - Look for files matching the whole-document pattern (e.g., `*prd*.md`, `*epic*.md`, `*architecture*.md`, `*ux*.md`, `*spec-*.md`)\n2. **Check for sharded version** - If whole document not found, look for a directory with `index.md` (e.g., `prd\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 Project Context:**\n\n1. **Read `AGENTS.md`** in the repo the change affects — the block between the `bmad:context` markers carries the policy, frozen paths, and conventions a course correction must respect.\n2. **Follow only the pointers that relate to the impacted areas** — nested component files or linked rule files listed under \"Where things are\". Do not load them all.\n3. **This document is optional** — skip if the repo has no `AGENTS.md` (greenfield projects).\n\n**Fuzzy matching**: Be flexible with document names — users may use variations like `prd.md`, `bmm-prd.md`, `product-requirements.md`, etc.\n\n**Missing documents**: Not all documents may exist. PRD and Epics are essential; Architecture, UX Design, Spec, and Document Project are loaded if available. HALT if PRD or Epics cannot be found.\n\n\u003Cworkflow>\n\n\u003Cstep n=\"1\" goal=\"Initialize Change Navigation\">\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 project documents:\u003C\u002Faction>\n    - PRD (Product Requirements Document) — required\n    - Current Epics and Stories — required\n    - Architecture documentation — optional, load if available\n    - UI\u002FUX specifications — optional, load if available\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=\"PRD or Epics are unavailable\">HALT: \"Need access to PRD and Epics to assess change impact. Please ensure these documents are accessible. Architecture and UI\u002FUX will be used if available.\"\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 PRD 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 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: PRD, 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, PRD, 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\u003Caction>Run: `uv run {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 PRD, 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: `uv run {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\u002Fbmm\u002Fconfig.yaml` and resolve:\n\n- `project_name`, `user_name`\n- `communication_language`, `document_output_language`\n- `user_skill_level`\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 `{user_skill_level}`\n- Generate all documents in `{document_output_language}`\n- DOCUMENT OUTPUT: Updated epics, stories, or PRD sections. Clear, actionable changes. User skill level (`{user_skill_level}`) 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. 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## 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| PRD | `{planning_artifacts}\u002F*prd*.md` (whole) or `{planning_artifacts}\u002F*prd*\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| Spec | `{planning_artifacts}\u002F*spec-*.md` (whole) | FULL_LOAD |\n| Project Context | `AGENTS.md` in the affected repo (the `bmad:context` block) | FULL_LOAD |\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 (PRD, Epics, Architecture, UX Design, Spec):**\n\n1. **Search for whole document first** - Look for files matching the whole-document pattern (e.g., `*prd*.md`, `*epic*.md`, `*architecture*.md`, `*ux*.md`, `*spec-*.md`)\n2. **Check for sharded version** - If whole document not found, look for a directory with `index.md` (e.g., `prd\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 Project Context:**\n\n1. **Read `AGENTS.md`** in the repo the change affects — the block between the `bmad:context` markers carries the policy, frozen paths, and conventions a course correction must respect.\n2. **Follow only the pointers that relate to the impacted areas** — nested component files or linked rule files listed under \"Where things are\". Do not load them all.\n3. **This document is optional** — skip if the repo has no `AGENTS.md` (greenfield projects).\n\n**Fuzzy matching**: Be flexible with document names — users may use variations like `prd.md`, `bmm-prd.md`, `product-requirements.md`, etc.\n\n**Missing documents**: Not all documents may exist. PRD and Epics are essential; Architecture, UX Design, Spec, and Document Project are loaded if available. HALT if PRD or Epics cannot be found.\n\n\u003Cworkflow>\n\n\u003Cstep n=\"1\" goal=\"Initialize Change Navigation\">\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 project documents:\u003C\u002Faction>\n    - PRD (Product Requirements Document) — required\n    - Current Epics and Stories — required\n    - Architecture documentation — optional, load if available\n    - UI\u002FUX specifications — optional, load if available\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=\"PRD or Epics are unavailable\">HALT: \"Need access to PRD and Epics to assess change impact. Please ensure these documents are accessible. Architecture and UI\u002FUX will be used if available.\"\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 PRD 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 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: PRD, 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, PRD, 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\u003Caction>Run: `uv run {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","8d56565809c4907cf7c91fff18c6dc19fc15676a",".agents\u002Fskills\u002Fbmad-correct-course",2,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system","https:\u002F\u002Fgithub.com\u002Fzaurakworks","2026-08-25 20:02:23",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add zaurakworks\u002Fagent-system --skill bmad-correct-course",{"tool":36,"command":37},"bunx","bunx skills add zaurakworks\u002Fagent-system --skill bmad-correct-course",{"tool":39,"command":40},"pnpm","pnpm dlx skills add zaurakworks\u002Fagent-system --skill bmad-correct-course","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-correct-course\u002FSKILL.md",true,[44,50],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"checklist.md","REFERENCE","参考文档",11634,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-correct-course\u002Fchecklist.md",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"customize.toml","OTHER","其他",1640,"https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-correct-course\u002Fcustomize.toml",[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M7AMNEBBK6MPZFW7PAXPB65C","skill-maintenance","创建、审计、修正、拆分、升级、迁移或退役 Skill，或其合同／入口已漂移时，先恢复行为、授权与预算，再同步正文、调用者、版本、生成物和验证。普通业务维护、纯格式修正、承载位置未定的纠正不触发。Use for explicit Skill maintenance, not carrier choice.","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-maintenance\u002Fskills\u002Fskill-maintenance\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M7AMN8D2VGEE8AX3T4B6ANWT","skill-appraisal","判定一个 Skill 组该不该进当前装配、归哪些事项、与谁重叠，或对已判定过的组按节拍复核。三种进入：首次判定新候选、补判早已在用但从未判定过的组、按失效条件复核。判定单位是组不是单个 Skill；产出必须留下失效条件与下次最少复核步骤。用于外部来源、他人所写、疑似重复或从未被判定过的组。从零设计新 Skill 用 agent-skill-design；已定下后的改造、迁移、退役用 skill-maintenance；只要外部标准与版本事实用 capability-lifecycle；对象是 knowledge 用 knowledge-maintenance。本 Skill 只产出判定，不安装、不写配置、不改 profile。Appraise a Skill group, or recheck an adopted one. Judgement only, never installs.","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002Fplugins\u002Fskill-appraisal\u002Fskills\u002Fskill-appraisal\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"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":77,"publishedAt":18},"01M7AMN45ZD6C1BN60Q55RG345","self-improvement","当用户指出 Agent 漂移、误解、重复犯错，要求把任务经验固化为系统改进，或讨论只增概念却不减关键未知、形成决定或可检验资产时，只暂停依赖被推翻假设的路径，重锚原问题、持久记录纠正、诊断原因，并在授权内改进入口提示词或 Skill。最小实验不能验收产品交付；普通一次性错误、偏好或任务内修复不触发完整自我优化。Use for reported drift, misunderstanding, repeated mistakes, durable Agent improvement, or abstraction loops without decisions or testable assets. Freeze only affected paths and avoid a full detour for ordinary one-off corrections.","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002Fplugins\u002Fself-improvement\u002Fskills\u002Fself-improvement\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M7AMMXZ9PNV3H53GFNBF6Y9B","resource-observability","当用户查询 Codex／Claude 账户额度、重置时间、Codex 重置券、单 Session Token，或高成本／多 Agent 工作要决定启动、并行、降级、延后或停止时，按需读取 Orca 账户快照与固定 ccusage 回执，区分状态、来源、可信度和未知值。不要用于低风险任务、轮询、自动调度／消费权益、账单推断或长期保存快照。Use for account capacity, reset times, credits, session tokens, or consequential resource decisions. Skip routine work, polling, scheduling, automatic credit use, billing inference, and durable snapshot storage.","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002Fplugins\u002Fresource-observability\u002Fskills\u002Fresource-observability\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M7AMMRGYZ3629M4EJPPBSNKX","orchestrated-collaboration","当用户明确要求多 Agent／多 Session／跨 Provider 协作、任务已授权委派，或活动 Session 发生共享写入碰撞时，建立目标来源、排他所有权、可追踪交付、独立验收与综合；按共享资源和 Issue 子树确定唯一协调者，只冻结重叠或受推翻假设影响的路径。协调者参与高价值多交付件能力的拆分或设计时，由未参与者复核父目标；使用已选后端，选 Orca 时动态读 orchestration 指南。不要因复杂、额度或空闲 Agent 擅自并行，也不把试用变成长期依赖。Use for authorized multi-agent work, cross-session delegation, or shared-write collisions. Establish exclusive ownership, traceable delivery, independent acceptance, and bounded synthesis; add parent-goal review when required and avoid invented coordination or permanent platform commitments.","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002Fplugins\u002Forchestrated-collaboration\u002Fskills\u002Forchestrated-collaboration\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M7AMMJXXSA6WFAAJCQE8JY1A","knowledge-maintenance","用于多来源调研、可重复实验、会影响权威／Agent 配置／重要决定的研究，或用户要求复用、复核、更新当前知识时：先找已认可知识和失效条件，只补变化、冲突与缺口，再经价值门和可信门更新。不用于低成本一次性事实、原始材料／研发过程留存、私域结构设计、定时全量重查或旧仓导入。Use before multi-source research, repeatable experiments, consequential authority\u002Fconfiguration decisions, or explicit knowledge reuse. Skip cheap one-off facts, raw retention, private architecture, scheduled full re-research, and bulk legacy imports.","https:\u002F\u002Fgithub.com\u002Fzaurakworks\u002Fagent-system\u002Fblob\u002Fmain\u002Fplugins\u002Fknowledge-maintenance\u002Fskills\u002Fknowledge-maintenance\u002FSKILL.md",[],[]]