[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M781SCPR1XDVM09M43160276":3,"skill-same:01M781SCPR1XDVM09M43160276":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},"01M781SCPR1XDVM09M43160276","spec-kitty.tasks-finalize",null,"Validate dependencies, finalize WP metadata, and commit all task artifacts.","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.tasks-finalize\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: spec-kitty.tasks-finalize\ndescription: \"Validate dependencies, finalize WP metadata, and commit all task artifacts.\"\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# \u002Fspec-kitty.tasks-finalize - Finalize Tasks\n\n**Version**: 3.2.0\n\n## Purpose\n\nRun the finalization command to parse dependencies from `tasks.md`, validate\nthem, update WP frontmatter, and commit all task artifacts to the target branch.\n\n---\n\n## 📍 WORKING DIRECTORY: Stay in the repository root checkout\n\n**IMPORTANT**: This step works in the repository root checkout. NO worktrees created.\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## Steps\n\n### 1. Run Validate-Only Preflight\n\n**CRITICAL**: Run this preflight command from repo root before any mutating\nfinalization:\n\n```bash\nspec-kitty agent mission finalize-tasks --validate-only --mission \u003Cmission-slug> --json\n```\n\nThis command will:\n\n- Parse dependencies from tasks.md\n- Parse `Requirement Refs` from tasks.md\n- Preview WP frontmatter updates without writing files\n- Validate dependencies (check for cycles, invalid references)\n- Validate requirement mapping:\n  - Every WP has at least one accepted requirement reference (a declared FR, NFR, C or SC; a `\u003Cmission-slug>#\u003CID>` citation does not count)\n  - Every ref gets one verdict: `malformed` and `unknown_spec_id` fail; `foreign_qualified` (another mission's ID) never fails; valid refs always count\n  - Every functional requirement declared in spec.md (`FR-###`, including one with a lowercase letter suffix such as `FR-###a`) is mapped to at least one WP\n  - Declared success criteria (`SC-###`) are tracked, not gating: they appear in `success_criteria_coverage` but never fail validation\n- Keep every authored `requirement_refs` item: finalize never erases or rewrites refs\n\nIf the JSON output contains `\"error\": \"Requirement mapping validation failed\"`,\ndo **not** run finalization. Report the blocking fields\n(`missing_requirement_refs_wps`, `unknown_requirement_refs`,\n`unmapped_functional_requirements`, and `rejected_requirement_refs` with each\nref's reason), compare them with `parsed_spec_ids` (the IDs finalize read from\nspec.md, grouped by kind), then fix mappings with\n`spec-kitty agent tasks map-requirements --mission \u003Cmission-slug> --json` or by\nupdating WP `requirement_refs`.\n\n### 1b. Ownership Overlap — domain-focused \u002F refactor missions\n\nIf validate-only fails with `\"error\": \"Ownership validation failed\"` and\n`ownership_errors` listing overlapping `owned_files`:\n\n**Ownership collisions are EXPECTED for domain-focused and refactor-oriented\nmissions** (cross-cutting strangler work, repo-wide migrations, boundary\nenforcement) where many work packages legitimately edit the same files. This is\nnot a defect in the slicing. Handle it as follows:\n\n1. **Linearize shared surfaces (execution safety).** Work packages that touch the\n   same files MUST be made dependent\u002Flinear (via `Depends on WPxx`) so they\n   execute sequentially in one lane and **share a single worktree** (or run\n   direct-to-branch). Limited parallelism is acceptable and expected for these\n   missions — do not force artificial parallelism. Note: linearization protects\n   the *worktree* from concurrent edits; it does **not** by itself satisfy\n   ownership validation (see step 3).\n2. **Declare cross-cutting WPs codebase-wide (the exemption).** A WP that is\n   expected to overlap broadly should carry `scope: codebase-wide` in its\n   frontmatter; the ownership validator exempts codebase-wide WPs from overlap\n   and authoritative-surface checks. Keep the genuinely-targeted WPs (single test\n   file, single module) narrow and mutually disjoint.\n3. **`codebase-wide` is the ONLY exemption.** Two *narrow* WPs that claim the same\n   files **always** fail ownership validation — regardless of whether they sit in\n   different lanes or are linked in a dependency hierarchy. Dependency\u002Flane\n   structure never bypasses the overlap check. If WPs legitimately share a\n   surface, mark the broadly-overlapping one `scope: codebase-wide`; otherwise\n   re-slice so the narrow WPs are disjoint.\n\nDo **not** fabricate disjoint `owned_files` that misrepresent which WP edits\nwhich files solely to pass validation — linearize and\u002For declare codebase-wide\ninstead.\n\n### 2. Run Finalization Command\n\nOnly after validate-only exits successfully, run the mutating finalization\ncommand from repo root:\n\n```bash\nspec-kitty agent mission finalize-tasks --mission \u003Cmission-slug> --json\n```\n\nThis command will update WP frontmatter, compute lanes, and commit all tasks to\nthe target branch.\n\n### 3. Check Output\n\nThe JSON output includes:\n\n- `\"commit_created\": true\u002Ffalse` — whether a commit was made\n- `\"commit_hash\"` — the commit hash if created\n- `\"wp_count\"` — number of WP files processed\n- `\"dependencies_parsed\"` — dependency relationships found\n- `\"requirement_refs_parsed\"` — requirement reference mapping found\n- `\"ownership_warnings\"` — soft warnings (glob-pattern zero-match, audit coverage)\n- `\"parsed_spec_ids\"` — requirement IDs parsed from spec.md, grouped as `functional`, `non_functional`, `constraint`, `success_criteria`\n- `\"rejected_requirement_refs\"` — per WP, each unusable ref with one reason: `malformed`, `unknown_spec_id` or `foreign_qualified`\n- `\"success_criteria_coverage\"` — informational: `referenced` (SC → WPs) and `unreferenced`; never fails the run\n- Validation details when checks fail (`missing_requirement_refs_wps`, `unknown_requirement_refs`, `unmapped_functional_requirements`, `rejected_requirement_refs`)\n\n**CRITICAL — Ownership warnings require action before proceeding:**\n\nIf `ownership_warnings` is non-empty, or if the command emits `ERROR: Ownership`\nlines to stderr, you MUST act on each issue before starting implementation:\n\n- **Hard error** (`ownership_literal_path_errors` present, exit 1): A\n  `owned_files` entry is a literal file path that does not exist in the\n  repository. Fix by:\n  1. Correcting the path (typo \u002F wrong relative path), or\n  2. Adding the path to `create_intent` in the WP frontmatter if the file will\n     be created by this WP (planned-new-file).\n\n  **Do NOT proceed to implement while any hard error is present.**\n\n- **Soft warning** (`ownership_warnings` non-empty, exit 0): A `owned_files`\n  glob pattern matched zero files. This may indicate in-flight work. Verify the\n  pattern is correct and adjust if needed before starting implementation.\n\nExample `create_intent` frontmatter for a planned-new-file entry:\n\n```yaml\nowned_files:\n  - \"src\u002Fapp\u002Fnew_module.py\"\ncreate_intent:\n  - \"src\u002Fapp\u002Fnew_module.py\"  # will be created by this WP\n```\n\n### 4. Verify\n\n**IMPORTANT — DO NOT COMMIT AGAIN AFTER THIS COMMAND**:\n\n- `finalize-tasks` commits the files automatically\n- If `commit_created=true`, files are ALREADY committed — do not run `git commit` again\n- Other dirty files shown by `git status` (templates, config) are UNRELATED\n- Verify using the `commit_hash` from JSON output, not by running `git add\u002Fcommit` again\n\n### 5. Report\n\nProvide a concise outcome summary:\n\n- Path to `tasks.md`\n- Work package count and per-package subtask tallies\n- Parallelization highlights\n- MVP scope recommendation\n- Finalization status (dependencies parsed, X WP files updated, committed to target branch)\n\n**Required next step — run `\u002Fspec-kitty.analyze` before `\u002Fspec-kitty.implement`.**\n`\u002Fspec-kitty.analyze` persists an `analysis-report.md` and reviews spec\u002Fplan\u002Ftasks\nconsistency; `\u002Fspec-kitty.implement` refuses to claim a work package\n(`analysis_report_required`) until that report exists — analyze is not optional, it\nis the readiness gate implement enforces. The report is current only while the\nspec, plan, tasks and charter are unchanged: editing any of them after analyze\nmakes the report stale, and implement refuses again until you re-run\n`\u002Fspec-kitty.analyze`.\n\n## Output\n\nAfter completing this step:\n\n- All WP files have `dependencies` field in frontmatter\n- All WP files have `requirement_refs` field in frontmatter\n- Dependencies are validated (no cycles, no invalid references)\n- Requirement references are validated against spec.md\n- Task artifacts are committed to the target branch\n\n**Next step**: run `\u002Fspec-kitty.analyze` — the required pre-implementation gate —\nthen `\u002Fspec-kitty.implement`.\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# \u002Fspec-kitty.tasks-finalize - Finalize Tasks\n\n**Version**: 3.2.0\n\n## Purpose\n\nRun the finalization command to parse dependencies from `tasks.md`, validate\nthem, update WP frontmatter, and commit all task artifacts to the target branch.\n\n---\n\n## 📍 WORKING DIRECTORY: Stay in the repository root checkout\n\n**IMPORTANT**: This step works in the repository root checkout. NO worktrees created.\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## Steps\n\n### 1. Run Validate-Only Preflight\n\n**CRITICAL**: Run this preflight command from repo root before any mutating\nfinalization:\n\n```bash\nspec-kitty agent mission finalize-tasks --validate-only --mission \u003Cmission-slug> --json\n```\n\nThis command will:\n\n- Parse dependencies from tasks.md\n- Parse `Requirement Refs` from tasks.md\n- Preview WP frontmatter updates without writing files\n- Validate dependencies (check for cycles, invalid references)\n- Validate requirement mapping:\n  - Every WP has at least one accepted requirement reference (a declared FR, NFR, C or SC; a `\u003Cmission-slug>#\u003CID>` citation does not count)\n  - Every ref gets one verdict: `malformed` and `unknown_spec_id` fail; `foreign_qualified` (another mission's ID) never fails; valid refs always count\n  - Every functional requirement declared in spec.md (`FR-###`, including one with a lowercase letter suffix such as `FR-###a`) is mapped to at least one WP\n  - Declared success criteria (`SC-###`) are tracked, not gating: they appear in `success_criteria_coverage` but never fail validation\n- Keep every authored `requirement_refs` item: finalize never erases or rewrites refs\n\nIf the JSON output contains `\"error\": \"Requirement mapping validation failed\"`,\ndo **not** run finalization. Report the blocking fields\n(`missing_requirement_refs_wps`, `unknown_requirement_refs`,\n`unmapped_functional_requirements`, and `rejected_requirement_refs` with each\nref's reason), compare them with `parsed_spec_ids` (the IDs finalize read from\nspec.md, grouped by kind), then fix mappings with\n`spec-kitty agent tasks map-requirements --mission \u003Cmission-slug> --json` or by\nupdating WP `requirement_refs`.\n\n### 1b. Ownership Overlap — domain-focused \u002F refactor missions\n\nIf validate-only fails with `\"error\": \"Ownership validation failed\"` and\n`ownership_errors` listing overlapping `owned_files`:\n\n**Ownership collisions are EXPECTED for domain-focused and refactor-oriented\nmissions** (cross-cutting strangler work, repo-wide migrations, boundary\nenforcement) where many work packages legitimately edit the same files. This is\nnot a defect in the slicing. Handle it as follows:\n\n1. **Linearize shared surfaces (execution safety).** Work packages that touch the\n   same files MUST be made dependent\u002Flinear (via `Depends on WPxx`) so they\n   execute sequentially in one lane and **share a single worktree** (or run\n   direct-to-branch). Limited parallelism is acceptable and expected for these\n   missions — do not force artificial parallelism. Note: linearization protects\n   the *worktree* from concurrent edits; it does **not** by itself satisfy\n   ownership validation (see step 3).\n2. **Declare cross-cutting WPs codebase-wide (the exemption).** A WP that is\n   expected to overlap broadly should carry `scope: codebase-wide` in its\n   frontmatter; the ownership validator exempts codebase-wide WPs from overlap\n   and authoritative-surface checks. Keep the genuinely-targeted WPs (single test\n   file, single module) narrow and mutually disjoint.\n3. **`codebase-wide` is the ONLY exemption.** Two *narrow* WPs that claim the same\n   files **always** fail ownership validation — regardless of whether they sit in\n   different lanes or are linked in a dependency hierarchy. Dependency\u002Flane\n   structure never bypasses the overlap check. If WPs legitimately share a\n   surface, mark the broadly-overlapping one `scope: codebase-wide`; otherwise\n   re-slice so the narrow WPs are disjoint.\n\nDo **not** fabricate disjoint `owned_files` that misrepresent which WP edits\nwhich files solely to pass validation — linearize and\u002For declare codebase-wide\ninstead.\n\n### 2. Run Finalization Command\n\nOnly after validate-only exits successfully, run the mutating finalization\ncommand from repo root:\n\n```bash\nspec-kitty agent mission finalize-tasks --mission \u003Cmission-slug> --json\n```\n\nThis command will update WP frontmatter, compute lanes, and commit all tasks to\nthe target branch.\n\n### 3. Check Output\n\nThe JSON output includes:\n\n- `\"commit_created\": true\u002Ffalse` — whether a commit was made\n- `\"commit_hash\"` — the commit hash if created\n- `\"wp_count\"` — number of WP files processed\n- `\"dependencies_parsed\"` — dependency relationships found\n- `\"requirement_refs_parsed\"` — requirement reference mapping found\n- `\"ownership_warnings\"` — soft warnings (glob-pattern zero-match, audit coverage)\n- `\"parsed_spec_ids\"` — requirement IDs parsed from spec.md, grouped as `functional`, `non_functional`, `constraint`, `success_criteria`\n- `\"rejected_requirement_refs\"` — per WP, each unusable ref with one reason: `malformed`, `unknown_spec_id` or `foreign_qualified`\n- `\"success_criteria_coverage\"` — informational: `referenced` (SC → WPs) and `unreferenced`; never fails the run\n- Validation details when checks fail (`missing_requirement_refs_wps`, `unknown_requirement_refs`, `unmapped_functional_requirements`, `rejected_requirement_refs`)\n\n**CRITICAL — Ownership warnings require action before proceeding:**\n\nIf `ownership_warnings` is non-empty, or if the command emits `ERROR: Ownership`\nlines to stderr, you MUST act on each issue before starting implementation:\n\n- **Hard error** (`ownership_literal_path_errors` present, exit 1): A\n  `owned_files` entry is a literal file path that does not exist in the\n  repository. Fix by:\n  1. Correcting the path (typo \u002F wrong relative path), or\n  2. Adding the path to `create_intent` in the WP frontmatter if the file will\n     be created by this WP (planned-new-file).\n\n  **Do NOT proceed to implement while any hard error is present.**\n\n- **Soft warning** (`ownership_warnings` non-empty, exit 0): A `owned_files`\n  glob pattern matched zero files. This may indicate in-flight work. Verify the\n  pattern is correct and adjust if needed before starting implementation.\n\nExample `create_intent` frontmatter for a planned-new-file entry:\n\n```yaml\nowned_files:\n  - \"src\u002Fapp\u002Fnew_module.py\"\ncreate_intent:\n  - \"src\u002Fapp\u002Fnew_module.py\"  # will be created by this WP\n```\n\n### 4. Verify\n\n**IMPORTANT — DO NOT COMMIT AGAIN AFTER THIS COMMAND**:\n\n- `finalize-tasks` commits the files automatically\n- If `commit_created=true`, files are ALREADY committed — do not run `git commit` again\n- Other dirty files shown by `git status` (templates, config) are UNRELATED\n- Verify using the `commit_hash` from JSON output, not by running `git add\u002Fcommit` again\n\n### 5. Report\n\nProvide a concise outcome summary:\n\n- Path to `tasks.md`\n- Work package count and per-package subtask tallies\n- Parallelization highlights\n- MVP scope recommendation\n- Finalization status (dependencies parsed, X WP files updated, committed to target branch)\n\n**Required next step — run `\u002Fspec-kitty.analyze` before `\u002Fspec-kitty.implement`.**\n`\u002Fspec-kitty.analyze` persists an `analysis-report.md` and reviews spec\u002Fplan\u002Ftasks\nconsistency; `\u002Fspec-kitty.implement` refuses to claim a work package\n(`analysis_report_required`) until that report exists — analyze is not optional, it\nis the readiness gate implement enforces. The report is current only while the\nspec, plan, tasks and charter are unchanged: editing any of them after analyze\nmakes the report stale, and implement refuses again until you re-run\n`\u002Fspec-kitty.analyze`.\n\n## Output\n\nAfter completing this step:\n\n- All WP files have `dependencies` field in frontmatter\n- All WP files have `requirement_refs` field in frontmatter\n- Dependencies are validated (no cycles, no invalid references)\n- Requirement references are validated against spec.md\n- Task artifacts are committed to the target branch\n\n**Next step**: run `\u002Fspec-kitty.analyze` — the required pre-implementation gate —\nthen `\u002Fspec-kitty.implement`.\n",{"name":5,"description":7,"user-invocable":24},true,"main","ab710df6d6db292abd3d1288d20f338eef0ee475",".agents\u002Fskills\u002Fspec-kitty.tasks-finalize",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.tasks-finalize",{"tool":39,"command":40},"bunx","bunx skills add spec-kitty\u002Fspec-kitty-open-packs --skill spec-kitty.tasks-finalize",{"tool":42,"command":43},"pnpm","pnpm dlx skills add spec-kitty\u002Fspec-kitty-open-packs --skill spec-kitty.tasks-finalize","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.tasks-finalize\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",[],[]]