[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ATFAF9BMHWM0BVCQ80BEEH":3,"skill-same:01M7ATFAF9BMHWM0BVCQ80BEEH":50},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7ATFAF9BMHWM0BVCQ80BEEH","speckit-tdd-run",null,"Drive the red-green-refactor loop by delegating to zfa tdd run (deterministic engine); the LLM handles only honest stops — fixing genuine reds and remediation — never re-driving what zfa drives","arrrrny\u002Fzuraffa_agent","arrrrny","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F48218623?v=4","01M7AT2E1VCEKRXW66PKN6VF10","Ahmet TOK","01M7AT2E2G5Y64BP5K6H95AS5B",0,"MIT","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_agent\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fagy\u002Fspeckit-tdd-run\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: speckit-tdd-run\ndescription: Drive the red-green-refactor loop by delegating to zfa tdd run (deterministic\n  engine); the LLM handles only honest stops — fixing genuine reds and remediation\n  — never re-driving what zfa drives\ncompatibility: Requires spec-kit project structure with .specify\u002F directory\nmetadata:\n  author: github-spec-kit\n  source: tdd:commands\u002Fspeckit.tdd.run.md\n---\n\n# TDD Run (zfa-delegating)\n\nDrive every behavior in the feature's test list through\nred → green → refactor. When this project is zuraffa-wired, the loop is\n**deterministic** — dispatch to `zfa tdd run`. The LLM's role narrows to:\nfixing the code when zfa stops at an honest RED, and handling escape hatches.\n\n## User Input\n\n```text\n$ARGUMENTS\n```\n\nAccept: `all` (default), a behavior id, or `resume`.\n\n## Step 0 — Engine detection\n\n```bash\nzfa --version 2>\u002Fdev\u002Fnull && test -f .zfa.json && echo \"ZFA_OK\" || echo \"ZFA_MISSING\"\n```\n\n- `ZFA_OK` → Step 1\n- `ZFA_MISSING` → fall back to the original LLM-guided loop (see \"Fallback\n  Path\")\n\n## Step 1 — Resolve the feature\n\nStandard resolution: input → `.specify\u002Ffeature.json` → prerequisites script.\nSet `FEATURE_SLUG`.\n\n## Step 2 — Dispatch to zfa\n\n```bash\nzfa tdd run \"$FEATURE_SLUG\" --timeout 25 2>&1\n```\n\n(Adjust `--timeout` for the hardware; 25 minutes per step on an Intel Mac is\nthe measured safe ceiling.)\n\n## Step 3 — Handle the verdict\n\nThe command runs until complete or an honest stop. Interpret:\n\n### `result=complete pending=0 red=0 green=0 done=N`\n\nAll behaviors done. Report: behaviors driven, suite state, evidence path\n(`tdd\u002Fcycle-log.md`). Tick the corresponding `tasks.md` tasks.\n\n### `result=stopped stopped_at=\u003Cbehavior>:\u003Cstep>`\n\nzfa stopped honestly. The stops the LLM must handle:\n\n**`verify-red` with `classification=compile-error`**:\nThe generated test doesn't compile. This is a generator bug (or a spec\ngrammar edge) — report the error, fix the compile error (escaping, imports)\nWITHOUT changing the test's assertions, then resume.\n\n**`make` with `outcome=generation-error` or `not-certified-red`**:\nThe make path failed. Inspect the cycle-log for the reason. If the behavior's\nsubject needs a real implementation the generator can't express, implement\nthe minimal change that makes the certified-red test pass (this is the TDD\n\"smallest change\" step — the LLM writes it, the suite proves it).\n\n**`refactor` with `outcome=not-green` or `runner-error`**:\nThe suite went red during refactor. Inspect, fix, resume.\n\nAfter fixing any stop, **re-dispatch** — never continue by hand past a gate.\n\n### Any exit code 2 or 3\n\nGrammar or contract drift. Report verbatim with the fix line; these are spec\nor template problems, not loop problems.\n\n## Step 4 — Tick tasks and report\n\nFor each behavior zfa drove to done, tick the matching `[behavior: \u003Cid>]`\ntask in `tasks.md`. Report: behaviors completed (one line each with its\nred→green evidence summary), tasks ticked, final suite state.\n\n## Fallback Path (LLM-guided, non-zuraffa projects only)\n\nWhen zfa is unavailable, run the original red-green-refactor loop yourself:\npick the next PENDING behavior from `tdd\u002Ftest-list.md`, write one failing\ntest, prove it fails for the right reason, make it pass with the smallest\nchange, refactor while green, record evidence in `tdd\u002Fcycle-log.md`, tick\nthe tasks.md task, repeat.\n\nNever use the fallback when zfa is available — the deterministic loop is the\ncontract, and its evidence is the only kind verify accepts without penalty.","# TDD Run (zfa-delegating)\n\nDrive every behavior in the feature's test list through\nred → green → refactor. When this project is zuraffa-wired, the loop is\n**deterministic** — dispatch to `zfa tdd run`. The LLM's role narrows to:\nfixing the code when zfa stops at an honest RED, and handling escape hatches.\n\n## User Input\n\n```text\n$ARGUMENTS\n```\n\nAccept: `all` (default), a behavior id, or `resume`.\n\n## Step 0 — Engine detection\n\n```bash\nzfa --version 2>\u002Fdev\u002Fnull && test -f .zfa.json && echo \"ZFA_OK\" || echo \"ZFA_MISSING\"\n```\n\n- `ZFA_OK` → Step 1\n- `ZFA_MISSING` → fall back to the original LLM-guided loop (see \"Fallback\n  Path\")\n\n## Step 1 — Resolve the feature\n\nStandard resolution: input → `.specify\u002Ffeature.json` → prerequisites script.\nSet `FEATURE_SLUG`.\n\n## Step 2 — Dispatch to zfa\n\n```bash\nzfa tdd run \"$FEATURE_SLUG\" --timeout 25 2>&1\n```\n\n(Adjust `--timeout` for the hardware; 25 minutes per step on an Intel Mac is\nthe measured safe ceiling.)\n\n## Step 3 — Handle the verdict\n\nThe command runs until complete or an honest stop. Interpret:\n\n### `result=complete pending=0 red=0 green=0 done=N`\n\nAll behaviors done. Report: behaviors driven, suite state, evidence path\n(`tdd\u002Fcycle-log.md`). Tick the corresponding `tasks.md` tasks.\n\n### `result=stopped stopped_at=\u003Cbehavior>:\u003Cstep>`\n\nzfa stopped honestly. The stops the LLM must handle:\n\n**`verify-red` with `classification=compile-error`**:\nThe generated test doesn't compile. This is a generator bug (or a spec\ngrammar edge) — report the error, fix the compile error (escaping, imports)\nWITHOUT changing the test's assertions, then resume.\n\n**`make` with `outcome=generation-error` or `not-certified-red`**:\nThe make path failed. Inspect the cycle-log for the reason. If the behavior's\nsubject needs a real implementation the generator can't express, implement\nthe minimal change that makes the certified-red test pass (this is the TDD\n\"smallest change\" step — the LLM writes it, the suite proves it).\n\n**`refactor` with `outcome=not-green` or `runner-error`**:\nThe suite went red during refactor. Inspect, fix, resume.\n\nAfter fixing any stop, **re-dispatch** — never continue by hand past a gate.\n\n### Any exit code 2 or 3\n\nGrammar or contract drift. Report verbatim with the fix line; these are spec\nor template problems, not loop problems.\n\n## Step 4 — Tick tasks and report\n\nFor each behavior zfa drove to done, tick the matching `[behavior: \u003Cid>]`\ntask in `tasks.md`. Report: behaviors completed (one line each with its\nred→green evidence summary), tasks ticked, final suite state.\n\n## Fallback Path (LLM-guided, non-zuraffa projects only)\n\nWhen zfa is unavailable, run the original red-green-refactor loop yourself:\npick the next PENDING behavior from `tdd\u002Ftest-list.md`, write one failing\ntest, prove it fails for the right reason, make it pass with the smallest\nchange, refactor while green, record evidence in `tdd\u002Fcycle-log.md`, tick\nthe tasks.md task, repeat.\n\nNever use the fallback when zfa is available — the deterministic loop is the\ncontract, and its evidence is the only kind verify accepts without penalty.",{"name":5,"metadata":24,"description":7,"compatibility":27},{"author":25,"source":26},"github-spec-kit","tdd:commands\u002Fspeckit.tdd.run.md","Requires spec-kit project structure with .specify\u002F directory","master","52f71eebd1a07a3150e315471d57d04ca0a29137",".specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fagy\u002Fspeckit-tdd-run","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_agent","https:\u002F\u002Fgithub.com\u002Farrrrny","https:\u002F\u002Farrrrny.com","AI Engineer @ ZikZak AI Moscow, Russia","2026-11-14 18:33:12",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add arrrrny\u002Fzuraffa_agent --skill speckit-tdd-run",{"tool":42,"command":43},"bunx","bunx skills add arrrrny\u002Fzuraffa_agent --skill speckit-tdd-run",{"tool":45,"command":46},"pnpm","pnpm dlx skills add arrrrny\u002Fzuraffa_agent --skill speckit-tdd-run","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_agent\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fagy\u002Fspeckit-tdd-run\u002FSKILL.md",true,[],[51,58,65,70,77,82],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7ATG1T9TD0WZ8BFYR3GT18H","speckit-tdd-verify","Audit TDD discipline by delegating to zfa tdd verify (mutation testing, evidence integrity); the LLM interprets the verdict and drives remediation","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_agent\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fzed\u002Fspeckit-tdd-verify\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7ATFYWYKKD8V8K1YJN71RTE","speckit-tdd-setup","Detect the test stack and write .specify\u002Fmemory\u002Ftdd-profile.md; zuraffa-wired projects record zfa commands as the engine","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_agent\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fzed\u002Fspeckit-tdd-setup\u002FSKILL.md",[],[],{"skillNo":66,"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":67,"categories":68,"keywords":69,"publishedAt":19},"01M7ATFV57E5PNAGS3KM01F7PT","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_agent\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fzed\u002Fspeckit-tdd-run\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7ATFPQ5GSJ70A3ZX74ZS12Y","speckit-tdd-plan","Derive the feature's test list by delegating to zfa tdd plan (deterministic engine); falls back to LLM-guided derivation only when zfa is unavailable","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_agent\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fzed\u002Fspeckit-tdd-plan\u002FSKILL.md",[],[],{"skillNo":78,"name":53,"nameZh":6,"description":54,"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},"01M7ATFJ47RXD5059ERWQW4452","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_agent\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fagy\u002Fspeckit-tdd-verify\u002FSKILL.md",[],[],{"skillNo":83,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7ATFE3VDH5B81J5Y5G9BAR2","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_agent\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fagy\u002Fspeckit-tdd-setup\u002FSKILL.md",[],[]]