[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CWDNEM6Y4AD3CZW04RFCDK":3,"skill-same:01M7CWDNEM6Y4AD3CZW04RFCDK":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},"01M7CWDNEM6Y4AD3CZW04RFCDK","speckit-bug-fix",null,"Apply the remediation from a bug assessment and record what was changed","arrrrny\u002Fzuraffa_minio","arrrrny","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F48218623?v=4","01M7AT2E1VCEKRXW66PKN6VF10","Ahmet TOK","01M7CW66ZCFMV5D5C7RBDVZR41",0,"MIT","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_minio\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Fbug\u002F.specify-dev\u002Fagent-commands\u002Fkimi\u002Fspeckit-bug-fix\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: speckit-bug-fix\ndescription: Apply the remediation from a bug assessment and record what was changed\ncompatibility: Requires spec-kit project structure with .specify\u002F directory\nmetadata:\n  author: github-spec-kit\n  source: bug:commands\u002Fspeckit.bug.fix.md\n---\n\n# Fix Bug\n\nApply the remediation that was proposed by `\u002Fspeckit-bug-assess` and record the changes in a fix report at `.specify\u002Fbugs\u002F\u003Cslug>\u002Ffix.md`. This command is **only** valid after an assessment exists for the given slug. Pass `--branch` (or `--worktree`) to isolate the fix on its own git branch before editing, mirroring how `\u002Fspeckit-specify` isolates feature work.\n\n## User Input\n\n```text\n$ARGUMENTS\n```\n\nThe user input should identify the bug to fix. Accept any of:\n\n- `slug=\u003Cbug-slug>` or `--slug \u003Cbug-slug>` or just a bare slug-like token.\n- A path that contains the slug (e.g. `.specify\u002Fbugs\u002Flogin-timeout\u002F`).\n- **Branch isolation** (optional): `branch` \u002F `--branch` creates a fix branch (`\u003Cprefix>\u002F\u003Cslug>`) first; `worktree` \u002F `--worktree` creates a git worktree instead. See **Optional — isolate the fix on a branch** below.\n- **Nothing** — fall back to context (see below).\n\n## Slug Resolution\n\nResolve `BUG_SLUG` in this order, stopping at the first match:\n\n1. **Explicit user input** — a slug passed in `$ARGUMENTS` (any of the forms above).\n2. **Conversation context** — if the current session has just run `\u002Fspeckit-bug-assess`, the slug it reported is the working slug. Reuse it without re-prompting. Confirm it by checking that `.specify\u002Fbugs\u002F\u003Cslug>\u002Fassessment.md` exists; if it does not, fall through.\n3. **Single candidate on disk** — list `.specify\u002Fbugs\u002F*\u002Fassessment.md`. If exactly one matching `assessment.md` is found, use the slug from its parent directory.\n4. **Disambiguate**:\n   - **Interactive mode**: ask the user which bug to fix and list the candidates.\n   - **Automated mode**: stop with an error listing the candidates. Do not guess.\n\nOnce resolved, set `BUG_SLUG` and `BUG_DIR = .specify\u002Fbugs\u002F\u003CBUG_SLUG>`, and briefly state in your reply which resolution path was used (explicit \u002F from context \u002F single candidate \u002F asked).\n\n## Prerequisites\n\n- `BUG_DIR\u002Fassessment.md` MUST exist. If it does not, stop and instruct the user to run `\u002Fspeckit-bug-assess` first.\n- If `BUG_DIR\u002Ffix.md` already exists, ask the user whether to overwrite it before continuing (interactive mode) or refuse (automated mode).\n- Read `BUG_DIR\u002Fassessment.md` in full. Treat its **Proposed Remediation**, **Files likely to change**, **Tests to add or update**, and **Risks & Considerations** sections as the contract for this command.\n\n## TDD mode (when `tdd_enabled: true` in bug-config.yml)\n\nWhen the bug extension's `tdd_enabled` config is `true` (the default), fix the bug\nthrough the TDD extension's red-green-refactor loop instead of editing code directly.\nThis mirrors how `spec-whole` drives a feature — the \"feature\" here is the bug:\n\n1. **Ensure the TDD stack profile exists** — if `.specify\u002Fmemory\u002Ftdd-profile.md` is\n   missing, run `\u002Fspeckit.tdd.setup` first (every other TDD command requires it).\n2. **Synthesize the bug spec** — write `BUG_DIR\u002Fspec.md` from `assessment.md`: the\n   required (fixed) behavior becomes the acceptance criteria, and the assessment's\n   reproduction steps become the failing-test scenario. This is the TDD spec source.\n3. **Pin the bug as the TDD feature** — set `.specify\u002Ffeature.json` so\n   `feature_directory` points at `BUG_DIR` (e.g. `.specify\u002Fbugs\u002F\u003Cslug>`). Everything\n   downstream (`tdd.plan`, `tdd.run`, `tdd.verify`) then operates on this directory.\n4. **Plan the tests** — run `\u002Fspeckit.tdd.plan` to derive `BUG_DIR\u002Ftdd\u002Ftest-list.md`.\n   If no `plan.md` exists in `BUG_DIR`, use `tdd.plan outer-only`.\n5. **Drive the loop** — run `\u002Fspeckit.tdd.run all`. It writes the failing\n   reproduction test, proves it RED, applies the minimal fix, proves it GREEN,\n   refactors while green, and logs evidence in `BUG_DIR\u002Ftdd\u002Fcycle-log.md`.\n6. **Implement non-behavior work** — run `\u002Fspeckit.implement` for any scaffolding,\n   config, or wiring tasks the loop left for it.\n7. **Write the fix report** (Execution step 4), referencing the `tdd\u002F` artifacts.\n\nIn TDD mode the \"Apply the remediation\" step below is performed *by* `tdd.run`, not by\nhand — do not pre-write the implementation before the test is red.\n\n## Execution\n\n1. **Confirm the plan**\n   - Restate, in 3–6 bullets, what you are about to change and where, based on the assessment.\n   - If the assessment's verdict is `invalid`, stop — there is nothing to fix. Tell the user and exit.\n   - If the verdict is `likely valid, needs reproduction` and there are unresolved `[NEEDS CLARIFICATION]` items, flag them and ask the user whether to proceed in interactive mode, or stop in automated mode.\n\n### Optional — isolate the fix on a branch\n\nBy default the fix is applied to the current branch. To match how `\u002Fspeckit-specify` isolates feature work, you may ask `bug.fix` to create a dedicated branch (or git worktree) first:\n\n- Parse the user input for `branch` \u002F `--branch` \u002F `worktree` \u002F `--worktree` (or `branch=true` \u002F `worktree=true`). These are mutually exclusive; prefer `--branch` unless the user explicitly asks for a worktree.\n- Determine the branch name `\u003Cprefix>\u002F\u003CBUG_SLUG>`, where `\u003Cprefix>` comes from `.specify\u002Fextensions\u002Fbug\u002Fbug-config.yml` (`branch_prefix`, default `fix`). Example: `fix\u002Flogin-timeout`. If a branch with that name already exists, stop and ask the user how to proceed (reuse it, choose another name, or skip isolation).\n- **Branch mode** (`--branch`): run `git checkout -b \u003Cprefix>\u002F\u003CBUG_SLUG>` from the current branch (assumed clean or committed).\n- **Worktree mode** (`--worktree`): run `git worktree add ..\u002F\u003Crepo>-\u003CBUG_SLUG> -b \u003Cprefix>\u002F\u003CBUG_SLUG>` so the fix lives in a separate working directory; then continue operations there.\n- If Git is unavailable or the directory is not a Git repository, skip isolation with a warning and apply the fix on the current branch.\n- State which mode was used in your reply; all subsequent edits happen on that branch\u002Fworktree.\n\n2. **Apply the remediation**\n   - **TDD mode:** if `tdd_enabled` is `true`, you already drove the fix via `tdd.run`\n     in the TDD-mode section above. Skip to step 3 and step 4, and reference the\n     `tdd\u002F` artifacts (test-list, cycle-log, verification) in the report.\n   - Make the code changes described by the preferred remediation. Stay within the files listed by the assessment unless newly discovered evidence requires expanding scope (in which case, log the expansion explicitly in the report).\n   - Add or update the tests called out in the assessment so the bug cannot regress silently.\n   - Keep the change minimal — do not refactor unrelated code, do not introduce dependencies that the assessment did not call for.\n   - If you discover the assessment was wrong (the proposed fix does not work, the root cause is elsewhere), STOP modifying code, document the new finding in the fix report under **Deviations from Assessment**, and recommend re-running `\u002Fspeckit-bug-assess`.\n\n3. **Run local checks**\n   - If the project has obvious test commands (e.g., `pytest`, `npm test`, `cargo test`), run the tests that exercise the changed paths. Capture pass\u002Ffail and key output.\n   - Do not run destructive or network-dependent suites without the user's consent.\n\n4. **Write the fix report**\n\n   Write to `BUG_DIR\u002Ffix.md` using this structure:\n\n   ```markdown\n   # Bug Fix: \u003Cshort title>\n\n   - **Slug**: \u003CBUG_SLUG>\n   - **Fixed**: \u003CISO 8601 date>\n   - **Assessment**: .\u002Fassessment.md\n   - **Status**: applied | partial | not-applied\n   - **TDD artifacts**: .\u002Ftdd\u002Ftest-list.md, .\u002Ftdd\u002Fcycle-log.md, .\u002Ftdd\u002Fverification.md (present only when the fix ran in TDD mode)\n\n   ## Summary\n\n   \u003COne or two sentences describing what was changed and why.>\n\n   ## Changes\n\n   | File | Change | Notes |\n   |------|--------|-------|\n   | `path\u002Fto\u002Ffile.py` | \u003Cadded \u002F modified \u002F removed> | \u003Cshort note> |\n   | `path\u002Fto\u002Ftest_file.py` | added test | \u003Cshort note> |\n\n   ## Diff Highlights (optional)\n\n   \u003CShort, illustrative snippets of the most important hunks — not a full diff dump.>\n\n   ## Tests Added or Updated\n\n   - `path\u002Fto\u002Ftest_file.py::test_name` — \u003Cwhat it pins down>\n\n   ## Local Verification\n\n   - Commands run: `\u003Ccommand>` → \u003Cresult, brief>\n   - Manual checks: \u003Cwhat was verified by hand, if anything>\n\n   ## Deviations from Assessment\n\n   \u003CEmpty if none. Otherwise, list any places where the actual fix departed from the proposed remediation and why.>\n\n   ## Follow-ups\n\n   - \u003Csuggested cleanup, monitoring, doc update, etc.>\n   ```\n\n5. **Report back** with:\n   - The slug and `BUG_DIR\u002Ffix.md` path.\n   - The status (`applied`, `partial`, `not-applied`).\n   - Which branch\u002Fworktree the fix was applied to (or \"current branch\" if isolation was not used).\n   - The next suggested step(s), in order:\n     - `\u002Fspeckit-bug-pr slug=\u003CBUG_SLUG>` (open a PR from the fix branch, linking the issue).\n     - Then: `\u002Fspeckit-bug-test slug=\u003CBUG_SLUG>` (validate the fix). In TDD mode this runs\n       `tdd.verify` against the bug directory and reports its verdict.\n\n## Guardrails\n\n- Never modify files outside the project workspace.\n- Never edit `assessment.md` — it is the contract you are working against. Record disagreements in `fix.md` under **Deviations from Assessment**.\n- Never delete files unless the assessment explicitly required it.\n- Never overwrite an existing `fix.md` without confirmation.","# Fix Bug\n\nApply the remediation that was proposed by `\u002Fspeckit-bug-assess` and record the changes in a fix report at `.specify\u002Fbugs\u002F\u003Cslug>\u002Ffix.md`. This command is **only** valid after an assessment exists for the given slug. Pass `--branch` (or `--worktree`) to isolate the fix on its own git branch before editing, mirroring how `\u002Fspeckit-specify` isolates feature work.\n\n## User Input\n\n```text\n$ARGUMENTS\n```\n\nThe user input should identify the bug to fix. Accept any of:\n\n- `slug=\u003Cbug-slug>` or `--slug \u003Cbug-slug>` or just a bare slug-like token.\n- A path that contains the slug (e.g. `.specify\u002Fbugs\u002Flogin-timeout\u002F`).\n- **Branch isolation** (optional): `branch` \u002F `--branch` creates a fix branch (`\u003Cprefix>\u002F\u003Cslug>`) first; `worktree` \u002F `--worktree` creates a git worktree instead. See **Optional — isolate the fix on a branch** below.\n- **Nothing** — fall back to context (see below).\n\n## Slug Resolution\n\nResolve `BUG_SLUG` in this order, stopping at the first match:\n\n1. **Explicit user input** — a slug passed in `$ARGUMENTS` (any of the forms above).\n2. **Conversation context** — if the current session has just run `\u002Fspeckit-bug-assess`, the slug it reported is the working slug. Reuse it without re-prompting. Confirm it by checking that `.specify\u002Fbugs\u002F\u003Cslug>\u002Fassessment.md` exists; if it does not, fall through.\n3. **Single candidate on disk** — list `.specify\u002Fbugs\u002F*\u002Fassessment.md`. If exactly one matching `assessment.md` is found, use the slug from its parent directory.\n4. **Disambiguate**:\n   - **Interactive mode**: ask the user which bug to fix and list the candidates.\n   - **Automated mode**: stop with an error listing the candidates. Do not guess.\n\nOnce resolved, set `BUG_SLUG` and `BUG_DIR = .specify\u002Fbugs\u002F\u003CBUG_SLUG>`, and briefly state in your reply which resolution path was used (explicit \u002F from context \u002F single candidate \u002F asked).\n\n## Prerequisites\n\n- `BUG_DIR\u002Fassessment.md` MUST exist. If it does not, stop and instruct the user to run `\u002Fspeckit-bug-assess` first.\n- If `BUG_DIR\u002Ffix.md` already exists, ask the user whether to overwrite it before continuing (interactive mode) or refuse (automated mode).\n- Read `BUG_DIR\u002Fassessment.md` in full. Treat its **Proposed Remediation**, **Files likely to change**, **Tests to add or update**, and **Risks & Considerations** sections as the contract for this command.\n\n## TDD mode (when `tdd_enabled: true` in bug-config.yml)\n\nWhen the bug extension's `tdd_enabled` config is `true` (the default), fix the bug\nthrough the TDD extension's red-green-refactor loop instead of editing code directly.\nThis mirrors how `spec-whole` drives a feature — the \"feature\" here is the bug:\n\n1. **Ensure the TDD stack profile exists** — if `.specify\u002Fmemory\u002Ftdd-profile.md` is\n   missing, run `\u002Fspeckit.tdd.setup` first (every other TDD command requires it).\n2. **Synthesize the bug spec** — write `BUG_DIR\u002Fspec.md` from `assessment.md`: the\n   required (fixed) behavior becomes the acceptance criteria, and the assessment's\n   reproduction steps become the failing-test scenario. This is the TDD spec source.\n3. **Pin the bug as the TDD feature** — set `.specify\u002Ffeature.json` so\n   `feature_directory` points at `BUG_DIR` (e.g. `.specify\u002Fbugs\u002F\u003Cslug>`). Everything\n   downstream (`tdd.plan`, `tdd.run`, `tdd.verify`) then operates on this directory.\n4. **Plan the tests** — run `\u002Fspeckit.tdd.plan` to derive `BUG_DIR\u002Ftdd\u002Ftest-list.md`.\n   If no `plan.md` exists in `BUG_DIR`, use `tdd.plan outer-only`.\n5. **Drive the loop** — run `\u002Fspeckit.tdd.run all`. It writes the failing\n   reproduction test, proves it RED, applies the minimal fix, proves it GREEN,\n   refactors while green, and logs evidence in `BUG_DIR\u002Ftdd\u002Fcycle-log.md`.\n6. **Implement non-behavior work** — run `\u002Fspeckit.implement` for any scaffolding,\n   config, or wiring tasks the loop left for it.\n7. **Write the fix report** (Execution step 4), referencing the `tdd\u002F` artifacts.\n\nIn TDD mode the \"Apply the remediation\" step below is performed *by* `tdd.run`, not by\nhand — do not pre-write the implementation before the test is red.\n\n## Execution\n\n1. **Confirm the plan**\n   - Restate, in 3–6 bullets, what you are about to change and where, based on the assessment.\n   - If the assessment's verdict is `invalid`, stop — there is nothing to fix. Tell the user and exit.\n   - If the verdict is `likely valid, needs reproduction` and there are unresolved `[NEEDS CLARIFICATION]` items, flag them and ask the user whether to proceed in interactive mode, or stop in automated mode.\n\n### Optional — isolate the fix on a branch\n\nBy default the fix is applied to the current branch. To match how `\u002Fspeckit-specify` isolates feature work, you may ask `bug.fix` to create a dedicated branch (or git worktree) first:\n\n- Parse the user input for `branch` \u002F `--branch` \u002F `worktree` \u002F `--worktree` (or `branch=true` \u002F `worktree=true`). These are mutually exclusive; prefer `--branch` unless the user explicitly asks for a worktree.\n- Determine the branch name `\u003Cprefix>\u002F\u003CBUG_SLUG>`, where `\u003Cprefix>` comes from `.specify\u002Fextensions\u002Fbug\u002Fbug-config.yml` (`branch_prefix`, default `fix`). Example: `fix\u002Flogin-timeout`. If a branch with that name already exists, stop and ask the user how to proceed (reuse it, choose another name, or skip isolation).\n- **Branch mode** (`--branch`): run `git checkout -b \u003Cprefix>\u002F\u003CBUG_SLUG>` from the current branch (assumed clean or committed).\n- **Worktree mode** (`--worktree`): run `git worktree add ..\u002F\u003Crepo>-\u003CBUG_SLUG> -b \u003Cprefix>\u002F\u003CBUG_SLUG>` so the fix lives in a separate working directory; then continue operations there.\n- If Git is unavailable or the directory is not a Git repository, skip isolation with a warning and apply the fix on the current branch.\n- State which mode was used in your reply; all subsequent edits happen on that branch\u002Fworktree.\n\n2. **Apply the remediation**\n   - **TDD mode:** if `tdd_enabled` is `true`, you already drove the fix via `tdd.run`\n     in the TDD-mode section above. Skip to step 3 and step 4, and reference the\n     `tdd\u002F` artifacts (test-list, cycle-log, verification) in the report.\n   - Make the code changes described by the preferred remediation. Stay within the files listed by the assessment unless newly discovered evidence requires expanding scope (in which case, log the expansion explicitly in the report).\n   - Add or update the tests called out in the assessment so the bug cannot regress silently.\n   - Keep the change minimal — do not refactor unrelated code, do not introduce dependencies that the assessment did not call for.\n   - If you discover the assessment was wrong (the proposed fix does not work, the root cause is elsewhere), STOP modifying code, document the new finding in the fix report under **Deviations from Assessment**, and recommend re-running `\u002Fspeckit-bug-assess`.\n\n3. **Run local checks**\n   - If the project has obvious test commands (e.g., `pytest`, `npm test`, `cargo test`), run the tests that exercise the changed paths. Capture pass\u002Ffail and key output.\n   - Do not run destructive or network-dependent suites without the user's consent.\n\n4. **Write the fix report**\n\n   Write to `BUG_DIR\u002Ffix.md` using this structure:\n\n   ```markdown\n   # Bug Fix: \u003Cshort title>\n\n   - **Slug**: \u003CBUG_SLUG>\n   - **Fixed**: \u003CISO 8601 date>\n   - **Assessment**: .\u002Fassessment.md\n   - **Status**: applied | partial | not-applied\n   - **TDD artifacts**: .\u002Ftdd\u002Ftest-list.md, .\u002Ftdd\u002Fcycle-log.md, .\u002Ftdd\u002Fverification.md (present only when the fix ran in TDD mode)\n\n   ## Summary\n\n   \u003COne or two sentences describing what was changed and why.>\n\n   ## Changes\n\n   | File | Change | Notes |\n   |------|--------|-------|\n   | `path\u002Fto\u002Ffile.py` | \u003Cadded \u002F modified \u002F removed> | \u003Cshort note> |\n   | `path\u002Fto\u002Ftest_file.py` | added test | \u003Cshort note> |\n\n   ## Diff Highlights (optional)\n\n   \u003CShort, illustrative snippets of the most important hunks — not a full diff dump.>\n\n   ## Tests Added or Updated\n\n   - `path\u002Fto\u002Ftest_file.py::test_name` — \u003Cwhat it pins down>\n\n   ## Local Verification\n\n   - Commands run: `\u003Ccommand>` → \u003Cresult, brief>\n   - Manual checks: \u003Cwhat was verified by hand, if anything>\n\n   ## Deviations from Assessment\n\n   \u003CEmpty if none. Otherwise, list any places where the actual fix departed from the proposed remediation and why.>\n\n   ## Follow-ups\n\n   - \u003Csuggested cleanup, monitoring, doc update, etc.>\n   ```\n\n5. **Report back** with:\n   - The slug and `BUG_DIR\u002Ffix.md` path.\n   - The status (`applied`, `partial`, `not-applied`).\n   - Which branch\u002Fworktree the fix was applied to (or \"current branch\" if isolation was not used).\n   - The next suggested step(s), in order:\n     - `\u002Fspeckit-bug-pr slug=\u003CBUG_SLUG>` (open a PR from the fix branch, linking the issue).\n     - Then: `\u002Fspeckit-bug-test slug=\u003CBUG_SLUG>` (validate the fix). In TDD mode this runs\n       `tdd.verify` against the bug directory and reports its verdict.\n\n## Guardrails\n\n- Never modify files outside the project workspace.\n- Never edit `assessment.md` — it is the contract you are working against. Record disagreements in `fix.md` under **Deviations from Assessment**.\n- Never delete files unless the assessment explicitly required it.\n- Never overwrite an existing `fix.md` without confirmation.",{"name":5,"metadata":24,"description":7,"compatibility":27},{"author":25,"source":26},"github-spec-kit","bug:commands\u002Fspeckit.bug.fix.md","Requires spec-kit project structure with .specify\u002F directory","master","0cfd28166bb8fb13e3d82aaa2d423497978e0caa",".specify\u002Fextensions\u002Fbug\u002F.specify-dev\u002Fagent-commands\u002Fkimi\u002Fspeckit-bug-fix","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_minio","https:\u002F\u002Fgithub.com\u002Farrrrny","https:\u002F\u002Farrrrny.com","AI Engineer @ ZikZak AI Moscow, Russia","2026-11-14 00:13:36",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add arrrrny\u002Fzuraffa_minio --skill speckit-bug-fix",{"tool":42,"command":43},"bunx","bunx skills add arrrrny\u002Fzuraffa_minio --skill speckit-bug-fix",{"tool":45,"command":46},"pnpm","pnpm dlx skills add arrrrny\u002Fzuraffa_minio --skill speckit-bug-fix","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_minio\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Fbug\u002F.specify-dev\u002Fagent-commands\u002Fkimi\u002Fspeckit-bug-fix\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"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},"01M7CWG6KFF0BZV47VX9FE5HZ4","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_minio\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fkimi\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},"01M7CWG3F7PKHN0B4BYK4SAB9Z","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_minio\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fkimi\u002Fspeckit-tdd-setup\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7CWFZRW205F1GJ0TBZ9ZS4R","speckit-tdd-run","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","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_minio\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fkimi\u002Fspeckit-tdd-run\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7CWFWRQP914YNHXD1KA68J1","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_minio\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Ftdd\u002F.specify-dev\u002Fagent-commands\u002Fkimi\u002Fspeckit-tdd-plan\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7CWFSCRDJ0K3KRQBVE24GV2","speckit-spec-stats-runs","On-demand execution — reads verified suite command from .specify\u002Fmemory\u002Ftdd-profile.md, runs it for selected specs (--all, spec id\u002Fslug, or default active feature), captures pass\u002Ffail + duration + tail, appends run record to .specify\u002Fstats\u002Fruns.json, refreshes dashboard health column","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_minio\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Fspec-stats\u002F.specify-dev\u002Fagent-commands\u002Fkimi\u002Fspeckit-spec-stats-runs\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7CWFNMBFCW157QGZBXPQ64Y","speckit-spec-stats-report","Main generator — scans all specs\u002F*\u002F, derives per-feature stage, task progress, health, last updated; when the TDD extension is installed, adds a deep TDD table (acceptance\u002Funit\u002Fcharacterization counts, DONE, loop mode, tasks.md state); renders dashboard to configurable output path and writes .specify\u002Fstats\u002Fstats.json snapshot","https:\u002F\u002Fgithub.com\u002Farrrrny\u002Fzuraffa_minio\u002Fblob\u002Fmaster\u002F.specify\u002Fextensions\u002Fspec-stats\u002F.specify-dev\u002Fagent-commands\u002Fkimi\u002Fspeckit-spec-stats-report\u002FSKILL.md",[],[]]