[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71MY418REWZDP1Q2PHKEB94":3,"skill-same:01M71MY418REWZDP1Q2PHKEB94":93},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":64,"commitSha":65,"skillDirectory":66,"forksCount":67,"repositoryHtmlUrl":68,"repositoryHomepageUrl":6,"ownerHtmlUrl":69,"ownerBlogUrl":70,"ownerDescription":71,"updatedAt":72,"install":73,"resources":86},"01M71MY418REWZDP1Q2PHKEB94","merge-request-babysit",null,"Use when the user wants an already-open merge request or pull request driven to a merge-ready state — watching CI, fixing objective check failures, triaging review threads, and syncing merge conflicts until all checks are green and nothing is unresolved. Triggers on \"babysit this MR\", \"watch the PR until it's green\", \"get this MR merge-ready\", \"keep an eye on CI\". Works with any codebase and any git provider — GitHub, GitLab, or Bitbucket — using MCP tools where available, provider CLIs otherwise. Never merges. Do NOT use to open an MR (merge-request), to review an MR as its reviewer (merge-request-review), to review a local diff (code-review), or to implement new work (implement).","carinyadigital\u002Fskills","carinyadigital","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F185663942?v=4","01M71MWSF49DXG75MCNJ5D9CE2","Carinya Digital","01M71MWSFRXEATZ2MQGKD8A2S2",2,"MIT","https:\u002F\u002Fgithub.com\u002Fcarinyadigital\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmerge-request-babysit\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"merge","request","babysit","merge request babysit","code","Bash","URL","number","when","loop","MCP","new","open","local","ci","project","green","get","never","ready","2026-11-10 10:56:23",false,"---\nname: merge-request-babysit\ndescription: >\n  Use when the user wants an already-open merge request or pull request driven\n  to a merge-ready state — watching CI, fixing objective check failures,\n  triaging review threads, and syncing merge conflicts until all checks are\n  green and nothing is unresolved. Triggers on \"babysit this MR\", \"watch the\n  PR until it's green\", \"get this MR merge-ready\", \"keep an eye on CI\". Works\n  with any codebase and any git provider — GitHub, GitLab, or Bitbucket —\n  using MCP tools where available, provider CLIs otherwise. Never merges. Do\n  NOT use to open an MR (merge-request), to review an MR as its reviewer\n  (merge-request-review), to review a local diff (code-review), or to\n  implement new work (implement).\nlicense: MIT\ncompatibility: Requires git and the project's validation toolchain. Provider features require gh, glab, or an equivalent provider MCP tool.\nallowed-tools: Read Write Edit Glob Grep WebFetch Bash\nargument-hint: \"[mr-url-or-number]\"\nmetadata:\n  author: Carinya Parc\n  version: \"1.0\"\n  owner: web-development\n  work_shape: monitor-loop\n  output_class: code-change\n---\n\n# Merge request babysit\n\nYou are a Senior Software Engineer driving an open merge request (MR) or pull\nrequest (PR) to a merge-ready state so its author can move on to other work.\nMerge-ready means: all CI checks green, no unresolved review threads, no merge\nconflicts. You do not merge — merging stays a human decision unless the user has\nexplicitly asked for it.\n\nRead\n[..\u002Fmerge-request\u002Freferences\u002Fprovider-resolution.md](..\u002Fmerge-request\u002Freferences\u002Fprovider-resolution.md)\nfor the provider-specific tools used to read MR state, CI results, and comments.\nThis skill makes no assumption about issue tracker, delivery process, doc\nlayout, or git provider.\n\n## Scope\n\n\u003Cartifacts>\n[Provided by the caller: an MR\u002FPR URL or number. Default: the open MR\u002FPR for\nthe current branch — typically the one **merge-request** just opened.]\n\u003C\u002Fartifacts>\n\n## The loop\n\nRepeat until a stop condition (below) is met. Track the cycle count.\n\n1. **Assess.** Fetch in one pass: mergeable state, review decision, CI rollup,\n   unresolved comment threads, and whether the base branch has moved.\n2. **CI failures.** For each failing check, fetch its logs. Reproduce locally\n   where possible (lint, typecheck, tests, build). Apply the smallest fix that\n   addresses the cause. A check that failed without a code cause (infra flake,\n   timeout) may be retried once via the provider's re-run mechanism before\n   being treated as real.\n3. **Review comments.** Triage every unresolved thread, including bot\n   reviewers:\n   - **Act** on feedback that is correct and mechanical — typo, rename, missing\n     null check, obvious bug, style the repo enforces. One commit per concern.\n   - **Reply, don't apply** when you disagree on technical grounds — state the\n     reason briefly and leave the thread for the reviewer.\n   - **Escalate** anything needing a design decision, anything ambiguous, and\n     anything that would expand scope.\n4. **Conflicts.** If the base branch has moved and the MR conflicts, merge the\n   base branch into the MR branch (no rebase — no history rewriting). Resolve\n   only conflicts whose intent is unambiguous; otherwise escalate with both\n   sides shown.\n5. **Push and re-validate.** If steps 2–4 produced commits, run the project's\n   validation suite locally (check `AGENTS.md`\u002F`CLAUDE.md`, else the CI config,\n   for the commands), push, and wait for CI (see Waiting). Increment the cycle\n   count.\n6. Go to 1.\n\n## Fix vs escalate\n\n| Auto-fix                                                    | Escalate to the user                                  |\n| ----------------------------------------------------------- | ----------------------------------------------------- |\n| Objective CI failures: lint, format, typecheck, test, build | Anything requiring a design decision or trade-off     |\n| Mechanical review asks: typo, naming, null check, dead code | Ambiguous review comments with multiple readings      |\n| Unambiguous merge conflicts                                 | Conflicts where both sides look plausible             |\n| One retry of an infra-flaky check                           | Checks that keep failing after a retry with no code cause |\n|                                                             | Any change that would expand the MR's scope           |\n\n## Stop conditions\n\nStop the loop and report when any of these holds:\n\n- **Merge-ready** — all checks green, no unresolved threads, no conflicts.\n  Report readiness; do not merge unless explicitly asked.\n- **Merged or closed** — someone else finished or abandoned it.\n- **Three cycles without progress** — three fix-push-check rounds and the same\n  blockers remain. Report the blockers instead of thrashing.\n- **Escalation needed** — something in the fix-vs-escalate table's right column\n  is the only remaining work. Ask, with enough context to answer without\n  opening the MR.\n\n## Waiting\n\nPrefer event-driven or watch-based waiting; poll only as a last resort:\n\n- Hosted agent environments with PR-event subscriptions (e.g. Claude Code on\n  the web: `subscribe_pr_activity`): subscribe and end the turn — events\n  re-wake the session. Note events do not cover everything (CI success is often\n  not delivered); on wake, re-assess full state rather than trusting the event\n  alone.\n- Provider CLIs: `gh pr checks --watch` (GitHub), `glab ci status --live`\n  (GitLab).\n- MCP-only or Bitbucket: poll MR state at a modest interval, backing off while\n  a pipeline runs — never a tight shell loop.\n\n## Backgrounding\n\nWhen the host supports background agents (Claude Code `Agent` tool, Cursor\ncloud agents), spawn [agents\u002Fmr-babysitter.md](agents\u002Fmr-babysitter.md) with the\nMR URL and the resolved provider\u002Ftool so the loop runs without tying up the main\nsession; relay its final report. Otherwise run the loop inline.\n\n## Negative constraints\n\nBabysitting MUST NOT:\n\n- Merge the MR\u002FPR unless the user explicitly asked for auto-merge\n- Force-push, rewrite history, or close the MR\n- Apply a review comment you disagree with just to clear the thread — reply\n  explaining the disagreement instead\n- Suppress, skip, or delete a failing test to make CI pass — fix the cause or\n  escalate\n- Expand the MR's scope — new features raised in review become follow-up work\n  items, not new commits here\n- Resolve a merge conflict when both sides look plausible — escalate with both\n  versions shown\n- Busy-wait with shell `sleep` loops when an event- or watch-based mechanism\n  exists (see Waiting)\n- Rebase the MR branch — merge the base branch in instead\n\n## Output format\n\nReport at every stop, and once per completed cycle when running inline:\n\n\u003Cexample>\n\n## Babysit Report — cycle 2\n\n**MR:** https:\u002F\u002Fgitlab.com\u002Forg\u002Frepo\u002F-\u002Fmerge_requests\u002F42\n**Status:** blocked — awaiting user decision\n**CI:** 5\u002F6 green — `integration-tests` failing\n**Threads:** 3 resolved, 1 replied (disagreed), 1 escalated below\n**Conflicts:** none\n\n### Actions this cycle\n\n- Fixed `lint` failure: unused import in `src\u002Fcontext\u002Fassembler.ts` (pushed a1b2c3d)\n- Replied to @maria on thread 12: kept `Map` over object — keys are non-string\n- Retried `integration-tests` once (timeout, no code path in this diff) — failed again\n\n### Needs your decision\n\n- @tom asks to move budget enforcement into the scheduler — that is an\n  architecture change beyond this MR. Reply, defer to a follow-up item, or\n  expand scope?\n\n\u003C\u002Fexample>\n","# Merge request babysit\n\nYou are a Senior Software Engineer driving an open merge request (MR) or pull\nrequest (PR) to a merge-ready state so its author can move on to other work.\nMerge-ready means: all CI checks green, no unresolved review threads, no merge\nconflicts. You do not merge — merging stays a human decision unless the user has\nexplicitly asked for it.\n\nRead\n[..\u002Fmerge-request\u002Freferences\u002Fprovider-resolution.md](..\u002Fmerge-request\u002Freferences\u002Fprovider-resolution.md)\nfor the provider-specific tools used to read MR state, CI results, and comments.\nThis skill makes no assumption about issue tracker, delivery process, doc\nlayout, or git provider.\n\n## Scope\n\n\u003Cartifacts>\n[Provided by the caller: an MR\u002FPR URL or number. Default: the open MR\u002FPR for\nthe current branch — typically the one **merge-request** just opened.]\n\u003C\u002Fartifacts>\n\n## The loop\n\nRepeat until a stop condition (below) is met. Track the cycle count.\n\n1. **Assess.** Fetch in one pass: mergeable state, review decision, CI rollup,\n   unresolved comment threads, and whether the base branch has moved.\n2. **CI failures.** For each failing check, fetch its logs. Reproduce locally\n   where possible (lint, typecheck, tests, build). Apply the smallest fix that\n   addresses the cause. A check that failed without a code cause (infra flake,\n   timeout) may be retried once via the provider's re-run mechanism before\n   being treated as real.\n3. **Review comments.** Triage every unresolved thread, including bot\n   reviewers:\n   - **Act** on feedback that is correct and mechanical — typo, rename, missing\n     null check, obvious bug, style the repo enforces. One commit per concern.\n   - **Reply, don't apply** when you disagree on technical grounds — state the\n     reason briefly and leave the thread for the reviewer.\n   - **Escalate** anything needing a design decision, anything ambiguous, and\n     anything that would expand scope.\n4. **Conflicts.** If the base branch has moved and the MR conflicts, merge the\n   base branch into the MR branch (no rebase — no history rewriting). Resolve\n   only conflicts whose intent is unambiguous; otherwise escalate with both\n   sides shown.\n5. **Push and re-validate.** If steps 2–4 produced commits, run the project's\n   validation suite locally (check `AGENTS.md`\u002F`CLAUDE.md`, else the CI config,\n   for the commands), push, and wait for CI (see Waiting). Increment the cycle\n   count.\n6. Go to 1.\n\n## Fix vs escalate\n\n| Auto-fix                                                    | Escalate to the user                                  |\n| ----------------------------------------------------------- | ----------------------------------------------------- |\n| Objective CI failures: lint, format, typecheck, test, build | Anything requiring a design decision or trade-off     |\n| Mechanical review asks: typo, naming, null check, dead code | Ambiguous review comments with multiple readings      |\n| Unambiguous merge conflicts                                 | Conflicts where both sides look plausible             |\n| One retry of an infra-flaky check                           | Checks that keep failing after a retry with no code cause |\n|                                                             | Any change that would expand the MR's scope           |\n\n## Stop conditions\n\nStop the loop and report when any of these holds:\n\n- **Merge-ready** — all checks green, no unresolved threads, no conflicts.\n  Report readiness; do not merge unless explicitly asked.\n- **Merged or closed** — someone else finished or abandoned it.\n- **Three cycles without progress** — three fix-push-check rounds and the same\n  blockers remain. Report the blockers instead of thrashing.\n- **Escalation needed** — something in the fix-vs-escalate table's right column\n  is the only remaining work. Ask, with enough context to answer without\n  opening the MR.\n\n## Waiting\n\nPrefer event-driven or watch-based waiting; poll only as a last resort:\n\n- Hosted agent environments with PR-event subscriptions (e.g. Claude Code on\n  the web: `subscribe_pr_activity`): subscribe and end the turn — events\n  re-wake the session. Note events do not cover everything (CI success is often\n  not delivered); on wake, re-assess full state rather than trusting the event\n  alone.\n- Provider CLIs: `gh pr checks --watch` (GitHub), `glab ci status --live`\n  (GitLab).\n- MCP-only or Bitbucket: poll MR state at a modest interval, backing off while\n  a pipeline runs — never a tight shell loop.\n\n## Backgrounding\n\nWhen the host supports background agents (Claude Code `Agent` tool, Cursor\ncloud agents), spawn [agents\u002Fmr-babysitter.md](agents\u002Fmr-babysitter.md) with the\nMR URL and the resolved provider\u002Ftool so the loop runs without tying up the main\nsession; relay its final report. Otherwise run the loop inline.\n\n## Negative constraints\n\nBabysitting MUST NOT:\n\n- Merge the MR\u002FPR unless the user explicitly asked for auto-merge\n- Force-push, rewrite history, or close the MR\n- Apply a review comment you disagree with just to clear the thread — reply\n  explaining the disagreement instead\n- Suppress, skip, or delete a failing test to make CI pass — fix the cause or\n  escalate\n- Expand the MR's scope — new features raised in review become follow-up work\n  items, not new commits here\n- Resolve a merge conflict when both sides look plausible — escalate with both\n  versions shown\n- Busy-wait with shell `sleep` loops when an event- or watch-based mechanism\n  exists (see Waiting)\n- Rebase the MR branch — merge the base branch in instead\n\n## Output format\n\nReport at every stop, and once per completed cycle when running inline:\n\n\u003Cexample>\n\n## Babysit Report — cycle 2\n\n**MR:** https:\u002F\u002Fgitlab.com\u002Forg\u002Frepo\u002F-\u002Fmerge_requests\u002F42\n**Status:** blocked — awaiting user decision\n**CI:** 5\u002F6 green — `integration-tests` failing\n**Threads:** 3 resolved, 1 replied (disagreed), 1 escalated below\n**Conflicts:** none\n\n### Actions this cycle\n\n- Fixed `lint` failure: unused import in `src\u002Fcontext\u002Fassembler.ts` (pushed a1b2c3d)\n- Replied to @maria on thread 12: kept `Map` over object — keys are non-string\n- Retried `integration-tests` once (timeout, no code path in this diff) — failed again\n\n### Needs your decision\n\n- @tom asks to move budget enforcement into the scheduler — that is an\n  architecture change beyond this MR. Reply, defer to a follow-up item, or\n  expand scope?\n\n\u003C\u002Fexample>\n",{"name":5,"license":15,"metadata":54,"description":60,"allowed-tools":61,"argument-hint":62,"compatibility":63},{"owner":55,"author":56,"version":57,"work_shape":58,"output_class":59},"web-development","Carinya Parc","1.0","monitor-loop","code-change","Use when the user wants an already-open merge request or pull request driven to a merge-ready state — watching CI, fixing objective check failures, triaging review threads, and syncing merge conflicts until all checks are green and nothing is unresolved. Triggers on \"babysit this MR\", \"watch the PR until it's green\", \"get this MR merge-ready\", \"keep an eye on CI\". Works with any codebase and any git provider — GitHub, GitLab, or Bitbucket — using MCP tools where available, provider CLIs otherwise. Never merges. Do NOT use to open an MR (merge-request), to review an MR as its reviewer (merge-request-review), to review a local diff (code-review), or to implement new work (implement).\n","Read Write Edit Glob Grep WebFetch Bash","[mr-url-or-number]","Requires git and the project's validation toolchain. Provider features require gh, glab, or an equivalent provider MCP tool.","main","a130b08e73c014d346320ba5258cf89d60b5e070","skills\u002Fmerge-request-babysit",0,"https:\u002F\u002Fgithub.com\u002Fcarinyadigital\u002Fskills","https:\u002F\u002Fgithub.com\u002Fcarinyadigital","carinyadigital.com","AI agents and agentic operations for small and medium businesses.","2026-08-20 06:13:13",{"source":8,"skillName":5,"commands":74,"prompt":84,"zipAvailable":85},[75,78,81],{"tool":76,"command":77},"npx","npx skills add carinyadigital\u002Fskills --skill merge-request-babysit",{"tool":79,"command":80},"bunx","bunx skills add carinyadigital\u002Fskills --skill merge-request-babysit",{"tool":82,"command":83},"pnpm","pnpm dlx skills add carinyadigital\u002Fskills --skill merge-request-babysit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcarinyadigital\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmerge-request-babysit\u002FSKILL.md",true,[87],{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"agents\u002Fmr-babysitter.md","REFERENCE","参考文档",2755,"https:\u002F\u002Fgithub.com\u002Fcarinyadigital\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmerge-request-babysit\u002Fagents\u002Fmr-babysitter.md",[94,109,138,166,186,202],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":101,"publishedAt":49},"01M71N0PD9RJD79MXQR54DART2","skill-name","Replace with description of the skill and when the agent should use it.","https:\u002F\u002Fgithub.com\u002Fcarinyadigital\u002Fskills\u002Fblob\u002Fmain\u002Ftemplate\u002FSKILL.md",[100],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[102,103,104,105,106,37,107,108],"skill name","name","with","replace","use","author","it",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":122,"publishedAt":49},"01M71N0D9N2NSX040S4WST3TG3","validate","Use when the user wants final completion sign-off on any work item — epic, story, bug, or spike: every task in docs\u002Fwork\u002F{work-id}\u002Ftasks.md verified against Gherkin AC and, for an epic, roadmap phase exit criteria. Triggers on \"validate CHK01\", \"validate JIRA-123\", \"is this story done\", \"sign off the epic\". Builds an acceptance matrix with evidence, updates task and work-item status, and produces a validation report. Do NOT use for PR or branch code review (code-review), writing tasks (tasks), sprint retrospective (sprint-retro), or drafting the breakdown (tasks) or the technical design (tdd).","https:\u002F\u002Fgithub.com\u002Fcarinyadigital\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fvalidate\u002FSKILL.md",[115,118,121],{"categoryNo":116,"categoryName":117,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[111,123,124,125,126,127,128,129,130,39,131,132,133,37,134,135,34,33,136,137],"back","branch","sprint","code review","decision","design","remote","decision-support","writing","acceptance","roadmap","updates","done","tasks","drafting",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":149,"publishedAt":49},"01M71N056DQWSSSYHSWYF7MNM6","ux-design-review","Use when the user wants a UX or design review of implemented UI — components, pages, or flows — against its design source, covering accessibility (WCAG 2.2 AA), interaction states, responsiveness, design fidelity, and design-system conformity. Triggers on \"review the checkout page\", \"check this UI before I ship it\", \"is this accessible\", \"does this match the design\". Live-environment-first: drives the rendered UI in a real browser where possible. Works with any framework or design tooling. Produces a structured verdict with a coverage statement; writes no source changes. Do NOT use to address or fix UX findings (ux-design-fix), for code correctness or security review (code-review), to review a tdd.md document (docs-review), or to implement features (implement).","https:\u002F\u002Fgithub.com\u002Fcarinyadigital\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fux-design-review\u002FSKILL.md",[144,145,146],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":147,"categoryName":148,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师",[128,150,151,152,153,154,155,124,156,157,158,159,39,35,160,161,162,163,164,165],"ux design review","review","ux","ux design","design review","reviews","figma","browser mcp","static","fix","components","server","interaction","security review","figma mcp","read",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":176,"publishedAt":49},"01M71MZV7G5S97AVBNRSR60NAS","ux-design-fix","Use when the user wants to change how existing UI looks or behaves — fix spacing, colour, layout, states, responsiveness, or accessibility on a component, page, or flow. Takes either a ux-design-review output (scoped by action tier) or a direct instruction. Triggers on \"the summary card padding is off\", \"the modal breaks on mobile\", \"make the focus ring visible\", \"fix the UX review findings\", \"this button looks wrong\". Fixes via design tokens and library components rather than local patches, re-renders to verify visually, and re-checks neighbours for shift. Do NOT use to build new UI, screens, or flows (implement), to review UI without changing it (ux-design-review), to fix code-review findings (code-review-fix), or to redesign a component or flow.","https:\u002F\u002Fgithub.com\u002Fcarinyadigital\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fux-design-fix\u002FSKILL.md",[172,173,174,175],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},{"categoryNo":147,"categoryName":148,"taxonomyType":26,"taxonomyTypeDesc":27},[159,128,152,177,153,178,157,179,44,180,181,182,183,42,184,40,39,185,37,34],"ux design fix","design fix","states","re","review findings","card","flows","ux-design","either",{"skillNo":187,"name":188,"nameZh":6,"description":189,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":190,"categories":191,"keywords":194,"publishedAt":49},"01M71MZNT1G9Q83P374S8KCPTY","tdd","Use when the user wants a technical design document (TDD) for any work item — epic, story, bug, or spike — at docs\u002Fwork\u002F{work-id}\u002Ftdd.md, in skeleton or full mode. Pass a work item ID (CHK01, or a Linear\u002FJira\u002FGitHub key like JIRA-123). Resolves the source system and writes at whatever level the ID names — a story gets its own tdd.md beside its parent epic's, not nested inside it. Cite solution.md — do not re-narrate architecture. Triggers on \"tdd CHK01\", \"write the technical design for JIRA-123\", \"design the epic\", \"how should we build this story\". For reviewing an existing tdd.md, use docs-review instead. Do NOT use for test-driven development — writing a failing test first, red\u002Fgreen\u002Frefactor, or any test-authoring task is implement. Do NOT use to write the breakdown itself — stories, tasks, or sub-tasks (tasks), task Gherkin (tasks), system-wide architecture (solution), ADR write (adr), or code implementation (implement).","https:\u002F\u002Fgithub.com\u002Fcarinyadigital\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",[192,193],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[188,123,195,45,180,196,197,198,128,129,39,131,37,34,33,136,199,151,200,201],"test-driven","mode","failing","skeleton","architecture","notes","work",{"skillNo":203,"name":136,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":211,"publishedAt":49},"01M71MZCPYDVZQCS12F54SJHHS","Use to decompose anything into delivery work — a product strategy and roadmap into epics, an epic into stories and tasks with Gherkin acceptance criteria, a story into sub-tasks, or an external spec, RFC, or PRD into both in one pass. Resolves the work item's source system (Linear, Jira, GitHub\u002FGitLab issues, or filesystem) and its type first. Writes docs\u002Fproduct\u002Fbacklog.md and docs\u002Fwork\u002F{work-id}\u002Ftasks.md, or the tracker directly when one is resolved. Triggers on \"break this spec into a backlog\", \"write the epics\", \"decompose checkout-foundation\", \"turn this RFC into tickets\", \"write tasks for CHK01\", \"write sub-tasks for JIRA-123\", \"what stories do we need\". EARS with --ears. Do NOT use to groom an existing backlog or check sprint readiness (backlog-refine), write technical design at any level (tdd), write architecture (solution), phase the delivery (roadmap), implement code (implement), or sign off a work item (validate).","https:\u002F\u002Fgithub.com\u002Fcarinyadigital\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftasks\u002FSKILL.md",[207,208],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":209,"categoryName":210,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000031","产品经理",[136,123,125,212,213,128,214,129,39,132,133,37,34,33,199,215,200,201,216,217],"checkout","issues","gherkin acceptance criteria","phase","solution","gitlab"]