[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M781RG9R1ZN4ZE4GC6SFFVPC":3,"skill-same:01M781RG9R1ZN4ZE4GC6SFFVPC":46},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M781RG9R1ZN4ZE4GC6SFFVPC","spec-kitty.analyze",null,"Cross-artifact consistency and quality analysis","spec-kitty\u002Fspec-kitty-open-packs","spec-kitty","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F299193673?v=4","01M781PAHK4SK9KA0V4KT7R3XN","Spec Kitty","01M781PAJDDBGZA6R83VQKWW90",2,"MIT","https:\u002F\u002Fgithub.com\u002Fspec-kitty\u002Fspec-kitty-open-packs\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fspec-kitty.analyze\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: spec-kitty.analyze\ndescription: Cross-artifact consistency and quality analysis\nuser-invocable: true\n---\n## Startup Upgrade Check\n\nRun this at most once per active agent session before the first Spec Kitty command workflow.\nIf you already ran `spec-kitty upgrade --agent-check --json` in this session, reuse that result and skip this block.\nDo not run or announce an upgrade check again for later Spec Kitty commands in the same session.\nOtherwise, before continuing, run:\n\n```bash\nspec-kitty upgrade --agent-check --json\n```\n\nIf JSON `action` is `none`, continue.\nIf `action` is `auto_upgrade`, run `upgrade_command` before continuing. If it fails, tell the user and continue with the current Spec Kitty version.\nIf `action` is `guidance`, show `upgrade_note` briefly, then continue.\nIf `action` is `prompt`, ask the user with the host-native question UI when available:\n\n`Spec Kitty {latest_version} is available. You are on {installed_version}. Upgrade now?`\n\nUse these choices:\n\n1. Upgrade now (recommended) - record `upgrade_now`, run `upgrade_command`, then continue.\n2. Always keep me up to date - record `always`, run `upgrade_command`, then continue.\n3. Not now - record `not_now`, then continue.\n4. Never ask again - record `never_ask`, then continue.\n\nRecord the selected choice before continuing:\n\n```bash\nspec-kitty upgrade --agent-choice \u003Cupgrade_now|always|not_now|never_ask> --agent-latest \u003Clatest_version> --json\n```\n\nIf no host-native question UI is available, present the same four choices in plain text and wait for the user.\nIn non-interactive hosts, choose `not_now` and continue.\n\n\n## User Input\n\nThe content of the user's message that invoked this skill (everything after the skill invocation token, e.g. after `\u002Fspec-kitty.\u003Ccommand>` or `$spec-kitty.\u003Ccommand>`) is the User Input referenced elsewhere in these instructions.\n\nYou **MUST** consider this user input before proceeding (if not empty).\n\n## Goal\n\nIdentify inconsistencies, duplications, ambiguities, and underspecified items across the three core artifacts (`spec.md`, `plan.md`, `tasks.md`) before implementation. This command MUST run only after `\u002Ftasks` has successfully produced a complete `tasks.md`.\n\n## Operating Constraints\n\n**NON-REMEDIATING**: Do **not** modify `spec.md`, `plan.md`, `tasks.md`, WP files, source code, or any remediation target. The only permitted file mutation is persisting this command's report to `kitty-specs\u002F\u003Cmission>\u002Fanalysis-report.md` via `spec-kitty agent mission record-analysis`. Offer an optional remediation plan only after the report is persisted (user must explicitly approve before any follow-up editing commands would be invoked manually).\n\n**Charter Authority**: The project charter (`.kittify\u002Fcharter\u002Fcharter.md`) is **non-negotiable** within this analysis scope. Charter conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit charter update outside `\u002Fanalyze`.\n\n**Issue-Matrix Approval Heads-Up (non-gating, #3469)**: if any artifact cites a GitHub\nissue number (`#NNNN`), a bare\u002Funmarked reference will later require an issue-matrix row\nbefore its owning work package can be approved. A context-only citation (e.g.\n`Follow-up:`, `see #`, `parent`, `epic`) or a PR\u002Fcommit reference (`PR #NNNN`, a\n`\u002Fpull\u002FNNNN` URL) is non-gating and needs no row; if an issue genuinely owes the mission\nno work, it can later be recorded with the `not-applicable` verdict. This is\ninformational only — it does not gate `\u002Fspec-kitty.analyze`.\n\n## Execution Steps\n\n### 1. Initialize Analysis Context\n\nRun `spec-kitty agent mission check-prerequisites --json --include-tasks --mission \u003Cmission-slug>` once from repo root and parse JSON for mission_dir, available_docs, target_branch, and base_branch. Derive absolute paths:\n\n- SPEC = mission_dir\u002Fspec.md\n- PLAN = mission_dir\u002Fplan.md\n- TASKS = mission_dir\u002Ftasks.md\n\nAbort with an error message if any required file is missing (instruct the user to run missing prerequisite command).\n\n### 2. Load Artifacts (Progressive Disclosure)\n\nLoad only the minimal necessary context from each artifact:\n\n**From spec.md:**\n\n- Overview\u002FContext\n- Functional Requirements\n- Non-Functional Requirements\n- User Stories\n- Edge Cases (if present)\n\n**From plan.md:**\n\n- Architecture\u002Fstack choices\n- Data Model references\n- Phases\n- Technical constraints\n\n**From tasks.md:**\n\n- Task IDs\n- Descriptions\n- Phase grouping\n- Parallel markers [P]\n- Referenced file paths\n\n**From charter:**\n\n- Load `.kittify\u002Fcharter\u002Fcharter.md` for principle validation\n\n### 3. Build Semantic Models\n\nCreate internal representations (do not include raw artifacts in output):\n\n- **Requirements inventory**: Each functional + non-functional requirement with a stable key (derive slug based on imperative phrase; e.g., \"User can upload file\" → `user-can-upload-file`)\n- **User story\u002Faction inventory**: Discrete user actions with acceptance criteria\n- **Task coverage mapping**: Map each task to one or more requirements or stories (inference by keyword \u002F explicit reference patterns like IDs or key phrases)\n- **Charter rule set**: Extract principle names and MUST\u002FSHOULD normative statements\n\n### 4. Detection Passes (Token-Efficient Analysis)\n\nFocus on high-signal findings. Limit to 50 findings total; aggregate remainder in overflow summary.\n\n#### A. Duplication Detection\n\n- Identify near-duplicate requirements\n- Mark lower-quality phrasing for consolidation\n\n#### B. Ambiguity Detection\n\n- Flag vague adjectives (fast, scalable, secure, intuitive, robust) lacking measurable criteria\n- Flag unresolved placeholders (TODO, TKTK, ???, `\u003Cplaceholder>`, etc.)\n\n#### C. Underspecification\n\n- Requirements with verbs but missing object or measurable outcome\n- User stories missing acceptance criteria alignment\n- Tasks referencing files or components not defined in spec\u002Fplan\n\n#### D. Charter Alignment\n\n- Any requirement or plan element conflicting with a MUST principle\n- Missing mandated sections or quality gates from charter\n\n#### E. Coverage Gaps\n\n- Requirements with zero associated tasks\n- Tasks with no mapped requirement\u002Fstory\n- Non-functional requirements not reflected in tasks (e.g., performance, security)\n\n#### F. Inconsistency\n\n- Terminology drift (same concept named differently across files)\n- Data entities referenced in plan but absent in spec (or vice versa)\n- Task ordering contradictions (e.g., integration tasks before foundational setup tasks without dependency note)\n- Conflicting requirements (e.g., one requires Next.js while other specifies Vue)\n\n### 5. Severity Assignment\n\nUse this heuristic to prioritize findings:\n\n- **CRITICAL**: Violates charter MUST, missing core spec artifact, or requirement with zero coverage that blocks baseline functionality\n- **HIGH**: Duplicate or conflicting requirement, ambiguous security\u002Fperformance attribute, untestable acceptance criterion\n- **MEDIUM**: Terminology drift, missing non-functional task coverage, underspecified edge case\n- **LOW**: Style\u002Fwording improvements, minor redundancy not affecting execution order\n\n### 6. Produce Compact Analysis Report\n\nThe report MUST begin with a structured **`analysis-findings\u002Fv1`** YAML frontmatter carrier, immediately followed by the human-readable Markdown body. The recorder computes the verdict and issue counts **from this carrier only** — report prose is presentation and is NEVER parsed for severity. Emit the carrier exactly in this shape:\n\n```yaml\n---\nschema: analysis-findings\u002Fv1\nfindings:\n  - id: A1            # stable finding id (same id used in the body table)\n    severity: high    # one of: low | medium | high | critical (closed vocabulary; no other values)\n    category: coverage\n    summary: \"One-line description of the finding.\"\ncounts: {critical: 0, high: 1, medium: 0, low: 0, info: 0}   # MUST equal the findings[] tally per severity\nverdict_hint: blocked   # OPTIONAL author hint; the recorder COMPUTES the verdict — if your hint disagrees, recording FAILS LOUDLY\n---\n```\n\nCarrier rules (binding — a violation makes `record-analysis` fail on the write path):\n- `findings[].severity` MUST be one of `low`, `medium`, `high`, `critical`. Any other value fails schema validation.\n- `counts` per-severity values MUST equal the actual `findings[]` tally. `info` is a presentation-only bucket and never affects the verdict.\n- The verdict is derived from structure: **any `high` or `critical` finding → `blocked`; otherwise → `ready`.** Do not rely on prose wording.\n- If you include `verdict_hint`, it MUST match the computed verdict, or recording fails loudly.\n- A report with **no** findings emits `findings: []` and `counts: {critical: 0, high: 0, medium: 0, low: 0, info: 0}` → verdict `ready`.\n\nAfter the closing `---`, draft the Markdown body with the following structure:\n\n## Specification Analysis Report\n\n| ID | Category | Severity | Location(s) | Summary | Recommendation |\n|----|----------|----------|-------------|---------|----------------|\n| A1 | Duplication | HIGH | spec.md:L120-134 | Two similar requirements ... | Merge phrasing; keep clearer version |\n\n(Add one row per finding; generate stable IDs prefixed by category initial.)\n\n**Coverage Summary Table:**\n\n| Requirement Key | Has Task? | Task IDs | Notes |\n|-----------------|-----------|----------|-------|\n\n**Charter Alignment Issues:** (if any)\n\n**Unmapped Tasks:** (if any)\n\n**Metrics:**\n\n- Total Requirements\n- Total Tasks\n- Coverage % (requirements with >=1 task)\n- Ambiguity Count\n- Duplication Count\n- Critical Issues Count\n\n### 7. Persist Report Artifact\n\nSave the Markdown report body to `kitty-specs\u002F\u003Cmission>\u002Fanalysis-report.md` by running the recorder with a temp report file outside the repository checkout:\n\n```bash\nspec-kitty agent mission record-analysis --mission \u003Cmission-slug> --input-file \u003Cpath-to-temp-report.md> --json\n```\n\nIf your host supports piping reliable multiline stdin, this equivalent form is acceptable:\n\n```bash\nspec-kitty agent mission record-analysis --mission \u003Cmission-slug> --input-file - --json\n```\n\nThe report file you pass MUST start with the `analysis-findings\u002Fv1` carrier from step 6. The recorder derives the verdict and counts from it; a malformed carrier (unknown severity, `counts` not matching the `findings[]` tally, or a disagreeing `verdict_hint`) makes the recorder fail loudly — fix the carrier and re-run.\n\nTreat persistence failure as command failure. The command is not complete until the JSON response reports success and names `analysis-report.md`.\n\n> **⚠️ Caution — write the report to a path OUTSIDE the repository checkout**\n>\n> The `analysis-findings\u002Fv1` carrier (step 6) is the **input format** for `record-analysis`,\n> not the **persisted format**. `record-analysis` wraps the carrier in the outer-wrapper\n> format (`artifact_type: spec-kitty.analysis-report`) that the implement gate accepts.\n>\n> Write the report body to a scratch file **outside the repository checkout** (a temp or\n> scratch directory) and pass that path to `record-analysis`. Writing the report body into\n> the checkout — including writing `analysis-report.md` directly — both leaves the file in\n> carrier format (the implement gate then rejects it with `carrier_format_not_wrapped`) and\n> dirties the worktree, so `record-analysis` refuses with `DIRTY_WORKTREE`. Recover by\n> writing the body to a path outside the repository checkout and re-running `record-analysis`\n> against that path:\n> ```bash\n> TMP_REPORT=\"$(mktemp -t analysis-report.XXXXXX.md)\"   # outside the repository checkout\n> # write the report body (starting with the analysis-findings\u002Fv1 carrier) to \"$TMP_REPORT\"\n> spec-kitty agent mission record-analysis --mission \u003Cmission-slug> --input-file \"$TMP_REPORT\" --json\n> ```\n\n### 7a. Report Currency (staleness rule)\n\nThe recorded `analysis-report.md` is current only while the planning inputs it\nwas computed against are unchanged. Editing the spec, plan, tasks or the\ncharter after the report is recorded makes it **stale**. A stale (or missing)\nreport is refused downstream: `spec-kitty next` re-issues the analyze step, and\n`spec-kitty implement` refuses to claim a work package with\n`analysis_report_required`. Re-run `\u002Fspec-kitty.analyze` and record a fresh\nreport whenever any of those inputs change.\n\n### 8. Provide Next Actions\n\nAt end of report, output a concise Next Actions block:\n\n- If CRITICAL issues exist: Recommend resolving before `\u002Fimplement`\n- If only LOW\u002FMEDIUM: User may proceed, but provide improvement suggestions\n- Provide explicit command suggestions: e.g., \"Run \u002Fspec-kitty.specify with refinement\", \"Run \u002Fplan to adjust architecture\", \"Manually edit tasks.md to add coverage for 'performance-metrics'\"\n\n### 9. Offer Remediation\n\nAsk the user: \"Should all of these findings be addressed before moving on to implementation? I can suggest concrete remediation edits for the findings you want to resolve.\" (Do NOT apply edits automatically.)\n\n## Operating Principles\n\n### Context Efficiency\n\n- **Minimal high-signal tokens**: Focus on actionable findings, not exhaustive documentation\n- **Progressive disclosure**: Load artifacts incrementally; don't dump all content into analysis\n- **Token-efficient output**: Limit findings table to 50 rows; summarize overflow\n- **Deterministic results**: Rerunning without changes should produce consistent IDs and counts\n\n### Analysis Guidelines\n\n- **NEVER modify source\u002Fplanning files** other than the required `analysis-report.md` persistence step\n- **NEVER hallucinate missing sections** (if absent, report them accurately)\n- **Prioritize charter violations** (these are always CRITICAL)\n- **Use examples over exhaustive rules** (cite specific instances, not generic patterns)\n- **Report zero issues gracefully** (emit success report with coverage statistics)\n\n## Context\n\n(User's invocation context is provided in the User Input section above.)\n","## Startup Upgrade Check\n\nRun this at most once per active agent session before the first Spec Kitty command workflow.\nIf you already ran `spec-kitty upgrade --agent-check --json` in this session, reuse that result and skip this block.\nDo not run or announce an upgrade check again for later Spec Kitty commands in the same session.\nOtherwise, before continuing, run:\n\n```bash\nspec-kitty upgrade --agent-check --json\n```\n\nIf JSON `action` is `none`, continue.\nIf `action` is `auto_upgrade`, run `upgrade_command` before continuing. If it fails, tell the user and continue with the current Spec Kitty version.\nIf `action` is `guidance`, show `upgrade_note` briefly, then continue.\nIf `action` is `prompt`, ask the user with the host-native question UI when available:\n\n`Spec Kitty {latest_version} is available. You are on {installed_version}. Upgrade now?`\n\nUse these choices:\n\n1. Upgrade now (recommended) - record `upgrade_now`, run `upgrade_command`, then continue.\n2. Always keep me up to date - record `always`, run `upgrade_command`, then continue.\n3. Not now - record `not_now`, then continue.\n4. Never ask again - record `never_ask`, then continue.\n\nRecord the selected choice before continuing:\n\n```bash\nspec-kitty upgrade --agent-choice \u003Cupgrade_now|always|not_now|never_ask> --agent-latest \u003Clatest_version> --json\n```\n\nIf no host-native question UI is available, present the same four choices in plain text and wait for the user.\nIn non-interactive hosts, choose `not_now` and continue.\n\n\n## User Input\n\nThe content of the user's message that invoked this skill (everything after the skill invocation token, e.g. after `\u002Fspec-kitty.\u003Ccommand>` or `$spec-kitty.\u003Ccommand>`) is the User Input referenced elsewhere in these instructions.\n\nYou **MUST** consider this user input before proceeding (if not empty).\n\n## Goal\n\nIdentify inconsistencies, duplications, ambiguities, and underspecified items across the three core artifacts (`spec.md`, `plan.md`, `tasks.md`) before implementation. This command MUST run only after `\u002Ftasks` has successfully produced a complete `tasks.md`.\n\n## Operating Constraints\n\n**NON-REMEDIATING**: Do **not** modify `spec.md`, `plan.md`, `tasks.md`, WP files, source code, or any remediation target. The only permitted file mutation is persisting this command's report to `kitty-specs\u002F\u003Cmission>\u002Fanalysis-report.md` via `spec-kitty agent mission record-analysis`. Offer an optional remediation plan only after the report is persisted (user must explicitly approve before any follow-up editing commands would be invoked manually).\n\n**Charter Authority**: The project charter (`.kittify\u002Fcharter\u002Fcharter.md`) is **non-negotiable** within this analysis scope. Charter conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit charter update outside `\u002Fanalyze`.\n\n**Issue-Matrix Approval Heads-Up (non-gating, #3469)**: if any artifact cites a GitHub\nissue number (`#NNNN`), a bare\u002Funmarked reference will later require an issue-matrix row\nbefore its owning work package can be approved. A context-only citation (e.g.\n`Follow-up:`, `see #`, `parent`, `epic`) or a PR\u002Fcommit reference (`PR #NNNN`, a\n`\u002Fpull\u002FNNNN` URL) is non-gating and needs no row; if an issue genuinely owes the mission\nno work, it can later be recorded with the `not-applicable` verdict. This is\ninformational only — it does not gate `\u002Fspec-kitty.analyze`.\n\n## Execution Steps\n\n### 1. Initialize Analysis Context\n\nRun `spec-kitty agent mission check-prerequisites --json --include-tasks --mission \u003Cmission-slug>` once from repo root and parse JSON for mission_dir, available_docs, target_branch, and base_branch. Derive absolute paths:\n\n- SPEC = mission_dir\u002Fspec.md\n- PLAN = mission_dir\u002Fplan.md\n- TASKS = mission_dir\u002Ftasks.md\n\nAbort with an error message if any required file is missing (instruct the user to run missing prerequisite command).\n\n### 2. Load Artifacts (Progressive Disclosure)\n\nLoad only the minimal necessary context from each artifact:\n\n**From spec.md:**\n\n- Overview\u002FContext\n- Functional Requirements\n- Non-Functional Requirements\n- User Stories\n- Edge Cases (if present)\n\n**From plan.md:**\n\n- Architecture\u002Fstack choices\n- Data Model references\n- Phases\n- Technical constraints\n\n**From tasks.md:**\n\n- Task IDs\n- Descriptions\n- Phase grouping\n- Parallel markers [P]\n- Referenced file paths\n\n**From charter:**\n\n- Load `.kittify\u002Fcharter\u002Fcharter.md` for principle validation\n\n### 3. Build Semantic Models\n\nCreate internal representations (do not include raw artifacts in output):\n\n- **Requirements inventory**: Each functional + non-functional requirement with a stable key (derive slug based on imperative phrase; e.g., \"User can upload file\" → `user-can-upload-file`)\n- **User story\u002Faction inventory**: Discrete user actions with acceptance criteria\n- **Task coverage mapping**: Map each task to one or more requirements or stories (inference by keyword \u002F explicit reference patterns like IDs or key phrases)\n- **Charter rule set**: Extract principle names and MUST\u002FSHOULD normative statements\n\n### 4. Detection Passes (Token-Efficient Analysis)\n\nFocus on high-signal findings. Limit to 50 findings total; aggregate remainder in overflow summary.\n\n#### A. Duplication Detection\n\n- Identify near-duplicate requirements\n- Mark lower-quality phrasing for consolidation\n\n#### B. Ambiguity Detection\n\n- Flag vague adjectives (fast, scalable, secure, intuitive, robust) lacking measurable criteria\n- Flag unresolved placeholders (TODO, TKTK, ???, `\u003Cplaceholder>`, etc.)\n\n#### C. Underspecification\n\n- Requirements with verbs but missing object or measurable outcome\n- User stories missing acceptance criteria alignment\n- Tasks referencing files or components not defined in spec\u002Fplan\n\n#### D. Charter Alignment\n\n- Any requirement or plan element conflicting with a MUST principle\n- Missing mandated sections or quality gates from charter\n\n#### E. Coverage Gaps\n\n- Requirements with zero associated tasks\n- Tasks with no mapped requirement\u002Fstory\n- Non-functional requirements not reflected in tasks (e.g., performance, security)\n\n#### F. Inconsistency\n\n- Terminology drift (same concept named differently across files)\n- Data entities referenced in plan but absent in spec (or vice versa)\n- Task ordering contradictions (e.g., integration tasks before foundational setup tasks without dependency note)\n- Conflicting requirements (e.g., one requires Next.js while other specifies Vue)\n\n### 5. Severity Assignment\n\nUse this heuristic to prioritize findings:\n\n- **CRITICAL**: Violates charter MUST, missing core spec artifact, or requirement with zero coverage that blocks baseline functionality\n- **HIGH**: Duplicate or conflicting requirement, ambiguous security\u002Fperformance attribute, untestable acceptance criterion\n- **MEDIUM**: Terminology drift, missing non-functional task coverage, underspecified edge case\n- **LOW**: Style\u002Fwording improvements, minor redundancy not affecting execution order\n\n### 6. Produce Compact Analysis Report\n\nThe report MUST begin with a structured **`analysis-findings\u002Fv1`** YAML frontmatter carrier, immediately followed by the human-readable Markdown body. The recorder computes the verdict and issue counts **from this carrier only** — report prose is presentation and is NEVER parsed for severity. Emit the carrier exactly in this shape:\n\n```yaml\n---\nschema: analysis-findings\u002Fv1\nfindings:\n  - id: A1            # stable finding id (same id used in the body table)\n    severity: high    # one of: low | medium | high | critical (closed vocabulary; no other values)\n    category: coverage\n    summary: \"One-line description of the finding.\"\ncounts: {critical: 0, high: 1, medium: 0, low: 0, info: 0}   # MUST equal the findings[] tally per severity\nverdict_hint: blocked   # OPTIONAL author hint; the recorder COMPUTES the verdict — if your hint disagrees, recording FAILS LOUDLY\n---\n```\n\nCarrier rules (binding — a violation makes `record-analysis` fail on the write path):\n- `findings[].severity` MUST be one of `low`, `medium`, `high`, `critical`. Any other value fails schema validation.\n- `counts` per-severity values MUST equal the actual `findings[]` tally. `info` is a presentation-only bucket and never affects the verdict.\n- The verdict is derived from structure: **any `high` or `critical` finding → `blocked`; otherwise → `ready`.** Do not rely on prose wording.\n- If you include `verdict_hint`, it MUST match the computed verdict, or recording fails loudly.\n- A report with **no** findings emits `findings: []` and `counts: {critical: 0, high: 0, medium: 0, low: 0, info: 0}` → verdict `ready`.\n\nAfter the closing `---`, draft the Markdown body with the following structure:\n\n## Specification Analysis Report\n\n| ID | Category | Severity | Location(s) | Summary | Recommendation |\n|----|----------|----------|-------------|---------|----------------|\n| A1 | Duplication | HIGH | spec.md:L120-134 | Two similar requirements ... | Merge phrasing; keep clearer version |\n\n(Add one row per finding; generate stable IDs prefixed by category initial.)\n\n**Coverage Summary Table:**\n\n| Requirement Key | Has Task? | Task IDs | Notes |\n|-----------------|-----------|----------|-------|\n\n**Charter Alignment Issues:** (if any)\n\n**Unmapped Tasks:** (if any)\n\n**Metrics:**\n\n- Total Requirements\n- Total Tasks\n- Coverage % (requirements with >=1 task)\n- Ambiguity Count\n- Duplication Count\n- Critical Issues Count\n\n### 7. Persist Report Artifact\n\nSave the Markdown report body to `kitty-specs\u002F\u003Cmission>\u002Fanalysis-report.md` by running the recorder with a temp report file outside the repository checkout:\n\n```bash\nspec-kitty agent mission record-analysis --mission \u003Cmission-slug> --input-file \u003Cpath-to-temp-report.md> --json\n```\n\nIf your host supports piping reliable multiline stdin, this equivalent form is acceptable:\n\n```bash\nspec-kitty agent mission record-analysis --mission \u003Cmission-slug> --input-file - --json\n```\n\nThe report file you pass MUST start with the `analysis-findings\u002Fv1` carrier from step 6. The recorder derives the verdict and counts from it; a malformed carrier (unknown severity, `counts` not matching the `findings[]` tally, or a disagreeing `verdict_hint`) makes the recorder fail loudly — fix the carrier and re-run.\n\nTreat persistence failure as command failure. The command is not complete until the JSON response reports success and names `analysis-report.md`.\n\n> **⚠️ Caution — write the report to a path OUTSIDE the repository checkout**\n>\n> The `analysis-findings\u002Fv1` carrier (step 6) is the **input format** for `record-analysis`,\n> not the **persisted format**. `record-analysis` wraps the carrier in the outer-wrapper\n> format (`artifact_type: spec-kitty.analysis-report`) that the implement gate accepts.\n>\n> Write the report body to a scratch file **outside the repository checkout** (a temp or\n> scratch directory) and pass that path to `record-analysis`. Writing the report body into\n> the checkout — including writing `analysis-report.md` directly — both leaves the file in\n> carrier format (the implement gate then rejects it with `carrier_format_not_wrapped`) and\n> dirties the worktree, so `record-analysis` refuses with `DIRTY_WORKTREE`. Recover by\n> writing the body to a path outside the repository checkout and re-running `record-analysis`\n> against that path:\n> ```bash\n> TMP_REPORT=\"$(mktemp -t analysis-report.XXXXXX.md)\"   # outside the repository checkout\n> # write the report body (starting with the analysis-findings\u002Fv1 carrier) to \"$TMP_REPORT\"\n> spec-kitty agent mission record-analysis --mission \u003Cmission-slug> --input-file \"$TMP_REPORT\" --json\n> ```\n\n### 7a. Report Currency (staleness rule)\n\nThe recorded `analysis-report.md` is current only while the planning inputs it\nwas computed against are unchanged. Editing the spec, plan, tasks or the\ncharter after the report is recorded makes it **stale**. A stale (or missing)\nreport is refused downstream: `spec-kitty next` re-issues the analyze step, and\n`spec-kitty implement` refuses to claim a work package with\n`analysis_report_required`. Re-run `\u002Fspec-kitty.analyze` and record a fresh\nreport whenever any of those inputs change.\n\n### 8. Provide Next Actions\n\nAt end of report, output a concise Next Actions block:\n\n- If CRITICAL issues exist: Recommend resolving before `\u002Fimplement`\n- If only LOW\u002FMEDIUM: User may proceed, but provide improvement suggestions\n- Provide explicit command suggestions: e.g., \"Run \u002Fspec-kitty.specify with refinement\", \"Run \u002Fplan to adjust architecture\", \"Manually edit tasks.md to add coverage for 'performance-metrics'\"\n\n### 9. Offer Remediation\n\nAsk the user: \"Should all of these findings be addressed before moving on to implementation? I can suggest concrete remediation edits for the findings you want to resolve.\" (Do NOT apply edits automatically.)\n\n## Operating Principles\n\n### Context Efficiency\n\n- **Minimal high-signal tokens**: Focus on actionable findings, not exhaustive documentation\n- **Progressive disclosure**: Load artifacts incrementally; don't dump all content into analysis\n- **Token-efficient output**: Limit findings table to 50 rows; summarize overflow\n- **Deterministic results**: Rerunning without changes should produce consistent IDs and counts\n\n### Analysis Guidelines\n\n- **NEVER modify source\u002Fplanning files** other than the required `analysis-report.md` persistence step\n- **NEVER hallucinate missing sections** (if absent, report them accurately)\n- **Prioritize charter violations** (these are always CRITICAL)\n- **Use examples over exhaustive rules** (cite specific instances, not generic patterns)\n- **Report zero issues gracefully** (emit success report with coverage statistics)\n\n## Context\n\n(User's invocation context is provided in the User Input section above.)\n",{"name":5,"description":7,"user-invocable":24},true,"main","ab710df6d6db292abd3d1288d20f338eef0ee475",".agents\u002Fskills\u002Fspec-kitty.analyze",0,"https:\u002F\u002Fgithub.com\u002Fspec-kitty\u002Fspec-kitty-open-packs","https:\u002F\u002Fgithub.com\u002Fspec-kitty","https:\u002F\u002Fspec-kitty.ai","2026-11-15 03:23:45",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":24},[35,38,41],{"tool":36,"command":37},"npx","npx skills add spec-kitty\u002Fspec-kitty-open-packs --skill spec-kitty.analyze",{"tool":39,"command":40},"bunx","bunx skills add spec-kitty\u002Fspec-kitty-open-packs --skill spec-kitty.analyze",{"tool":42,"command":43},"pnpm","pnpm dlx skills add spec-kitty\u002Fspec-kitty-open-packs --skill spec-kitty.analyze","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fspec-kitty\u002Fspec-kitty-open-packs\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fspec-kitty.analyze\u002FSKILL.md",[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M781XGMZZ1J569VFF53BFFRX","kitty-semi-auto","Use to take a tracker issue or a coherent issue-set through a governed delivery run that works autonomously but pauses to escalate the operator's decisions. Runs BOTH ways — in this session (local) or handed to a fresh cloud runner (cloud) — from one set of standing orders covering orientation, code grounding first, Mission-vs-Ops, the pause-and-escalate contract, brownfield discipline, and the canonical closeout to a draft PR the operator merges. Triggers: semi-auto, semi-auto dispatch, run this semi-automatically, deliver these issues semi-auto, hand this to a cloud runner, dispatch semi-auto.","https:\u002F\u002Fgithub.com\u002Fspec-kitty\u002Fspec-kitty-open-packs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fkitty-semi-auto\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M781XCN71TH0P1AMK99MZ042","kitty-report-debrief","Use when a maintainer asks what happened or what is open (\"what landed since Friday\", \"WTF happened with X\", a milestone overview). Collects the facts from GitHub, writes a short branded debrief for named readers, and hands the PDF back without committing it. Triggers: what landed since, WTF happened, debrief the weekend, milestone overview, exec overview of open issues, write up what shipped.","https:\u002F\u002Fgithub.com\u002Fspec-kitty\u002Fspec-kitty-open-packs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fkitty-report-debrief\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M781X8MDSBSEFP7HDM65A89G","kitty-mission-from-issue","Use to take one or more GitHub issues through a full governed Mission (spec, plan, tasks, implementation, review) to a green pull request flipped to ready for review, which a maintainer then merges. Triggers: mission from issue, run a mission for this issue, drive issue to PR.","https:\u002F\u002Fgithub.com\u002Fspec-kitty\u002Fspec-kitty-open-packs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fkitty-mission-from-issue\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M781X574X27Q630CBWXEWMBC","kitty-land-pr","Use when a ready-for-review pull request needs a maintainer to get it ready to merge. Rebases it, fixes and reviews it, updates its description, changelog and docs, and hands it back without merging by hand. Triggers: land this PR, landing pass, land PR.","https:\u002F\u002Fgithub.com\u002Fspec-kitty\u002Fspec-kitty-open-packs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fkitty-land-pr\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M781X0KW55NB6G0P5FKGFEX0","kitty-issue-triage","Use to triage a batch of open GitHub issues on spec-kitty\u002Fspec-kitty (default, those opened in the last 7 days). Sets type, priority, domain, parent and milestone, and reports stale, duplicate or clustered issues for an operator decision. Triggers: triage issues, triage the tracker, triage new issues.","https:\u002F\u002Fgithub.com\u002Fspec-kitty\u002Fspec-kitty-open-packs\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fkitty-issue-triage\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":6,"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},"01M781WXTC0ACEC78PVXKB22YH","spk-team-tracker","https:\u002F\u002Fgithub.com\u002Fspec-kitty\u002Fspec-kitty-open-packs\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fspk-team-tracker\u002FSKILL.md",[],[]]