[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6K5QDP64XNBZS6KA335XRQM":3,"skill-same:01M6K5QDP64XNBZS6KA335XRQM":108},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":73},"01M6K5QDP64XNBZS6KA335XRQM","sme-test",null,"TDD coach: guides users through Given\u002FWhen\u002FThen test design using a Subject Matter Expert approach. Use when writing new tests, adding test coverage, or learning TDD patterns.","laurac8r\u002Fclaude-damn","laurac8r","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F23003243?v=4","01M6K5HCAJJR4Q5BCBRRZF8E5D","Laura Kaminskiy","01M6K5HCEQRFFJFK32A0VR7AS3",3,"MIT","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fsme-test\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"sme test","test","sme","test design","true","-expert","users","guides","tests","coach","expert","design","test coverage","auto","use","coverage","learning","file","tdd","writing","2026-11-10 10:12:30",false,"---\nname: sme-test\ndescription:\n   \"TDD coach: guides users through Given\u002FWhen\u002FThen test design using a Subject\n   Matter Expert approach. Use when writing new tests, adding test coverage, or\n   learning TDD patterns.\"\nuser-invocable: true\nargument-hint: \"[file|function] [--expert|-x] [--auto|-xa]\"\n---\n\n# sme-test: Subject Matter Expert TDD Coach\n\nA coaching-driven TDD workflow that teaches you to think in Given\u002FWhen\u002FThen\ntriples before writing test code.\n\n**Arguments:** \"$ARGUMENTS\"\n\n---\n\n## Mode Dispatch\n\nParse arguments to determine mode:\n\n| Input                      | Mode            | Flow                                                          |\n| -------------------------- | --------------- | ------------------------------------------------------------- |\n| (default)                  | **Coach**       | Full 6-stage coaching flow with 3-Whys dialogue               |\n| `--expert` or `-x`         | **Expert**      | Single-turn: paste G\u002FW\u002FT triples directly, skip coaching      |\n| `--expert --auto` or `-xa` | **Expert-Auto** | Auto-infer triples from code scan with mandatory preview gate |\n\n`--auto --yes` is **not a valid flag combination** — the preview gate cannot be\nbypassed.\n\n**Escape hatches (available at any prompt in expert\u002Fexpert-auto modes):**\n\n- Type `coach` → bail up to full coach mode (3-Whys flow)\n- Type `paste` → bail sideways to manual triple entry (expert mode)\n\n---\n\n## Coach Mode (Default) — 6-Stage Flow\n\n### Stage 1: Dispatch\n\nRead the prompt from `prompts\u002Fcoach-dispatch.md` and execute it.\n\nDetect the target code file\u002Ffunction from arguments. Identify the project\nlanguage using the adapter DETECT capability. Select the appropriate adapter\nfrom `adapters\u002F`. Load any existing `shared\u002F` memory state from prior sessions.\n\n**Subagent:** test-coach (Opus) — judgment-heavy, needs deep reasoning for\nintent extraction.\n\n### Stage 2: 3-Whys\n\nRead the prompt from `prompts\u002Fthree-whys.md` and execute it.\n\nAsk three progressive \"why\" questions to surface the real behavioral intent\nbehind the user's test request. Do not accept \"test this function\" as sufficient\n— probe until a concrete behavioral contract emerges.\n\n**Subagent:** test-coach (Opus) — conversational coaching requires judgment.\n\n### Stage 3: G\u002FW\u002FT Formulation\n\nRead the prompt from `prompts\u002Fgwt-formulation.md` and execute it.\n\nGuide the user to translate 3-Whys answers into Given\u002FWhen\u002FThen triples. Each\ntriple must be concrete, testable, and non-redundant. Validate each triple\nbefore accepting.\n\n**Subagent:** test-coach (Opus) — triple validation requires judgment.\n\n### Stage 4: Test-Writer Delegation\n\nRead the prompt from `prompts\u002Ftest-writer.md` and execute it.\n\nDispatch a Sonnet subagent (test-writer) with the approved triples and the\nselected language adapter. The subagent generates executable test code. Stage\noutput for user review before proceeding.\n\n**Subagent:** test-writer (Sonnet) — structured code generation from approved\ntriples, no deep judgment needed.\n\nWrite subagent state to `shared\u002Ftest-writer-output.md`. Read all files in\n`shared\u002F` before dispatching.\n\n### Stage 5: RED Gate\n\nRead the prompt from `prompts\u002Fred-gate.md` and execute it.\n\nDispatch a Sonnet subagent (test-runner) to execute the generated tests. The\ntests **MUST fail** (red state). This gate is **mandatory** — there is **no\noverride**. If tests pass, this is an error (see error class 4 in\n`errors\u002Ferror-handlers.md`).\n\n**Subagent:** test-runner (Sonnet) — test execution is deterministic, no\nreasoning needed.\n\nWrite subagent state to `shared\u002Fred-gate-result.md`. Read all files in `shared\u002F`\nbefore dispatching.\n\n### Stage 6: Handoff\n\nPresent the failing tests to the user. Offer handoff options:\n\n- Continue manually — user writes implementation code\n- Handoff to `\u002Ftdd` — use the TDD skill for RED→GREEN→REFACTOR\n- Handoff to `\u002Fduper-tdd` — TDD in an isolated worktree\n\n---\n\n## Expert Mode (`--expert` \u002F `-x`)\n\nSkip Stages 2-3 (no 3-Whys, no coached G\u002FW\u002FT formulation).\n\n1. Prompt user to paste Given\u002FWhen\u002FThen triples in structured format\n2. Parse triples (no per-triple critique — trust the expert user)\n3. Proceed directly to Stage 4 (test-writer delegation)\n4. RED gate (Stage 5) remains **mandatory**\n5. Handoff (Stage 6)\n\n**Model routing:** Sonnet-only — no Opus subagent required. Parsing structured\ninput does not require deep reasoning.\n\n---\n\n## Expert-Auto Mode (`--expert --auto` \u002F `-xa`)\n\nReplace Stages 2-3 with automated triple inference.\n\n1. **Code scan:** test-coach (Opus) scans target file, infers triples from\n   function signatures and docstrings\n2. **Provenance tags:** Each inferred triple carries a tag identifying which\n   function\u002Fsignature it was inferred from\n3. **Cap:** Maximum **8 triples** per invocation (hard cap)\n4. **Mandatory preview gate:** User sees all inferred triples and must\n   explicitly:\n   - **(k)eep all** — accept all triples\n   - **(d)rop N** — remove specific triples\n   - **(a)dd** — add custom triples\n   - **(abort)** — cancel entirely\n\n5. Proceed to Stage 4 → Stage 5 (RED gate mandatory) → Stage 6 (handoff)\n\n**Model routing:** test-coach on Opus for inference quality (code\nunderstanding + triple generation).\n\n---\n\n## Subagent Coordination\n\nAll subagents coordinate via the `shared\u002F` memory directory pattern (per\nCLAUDE.md):\n\n| Subagent    | Model                         | Stages | Writes to `shared\u002F`            |\n| ----------- | ----------------------------- | ------ | ------------------------------ |\n| test-coach  | Opus (coach), Sonnet (expert) | 1-3    | `shared\u002Fcoach-state.md`        |\n| test-writer | Sonnet                        | 4      | `shared\u002Ftest-writer-output.md` |\n| test-runner | Sonnet                        | 5      | `shared\u002Fred-gate-result.md`    |\n\n**Rules:**\n\n- Each subagent writes only its own file in `shared\u002F`\n- Each subagent reads all files in `shared\u002F` on startup\n- Main skill agent manages cleanup and compacts to `COMBINED.md` after subagent\n  completion\n- No subagent modifies `COMBINED.md` directly\n\n---\n\n## Error Handling\n\nSee `errors\u002Ferror-handlers.md` for the 5 error classes and recovery paths:\n\n1. **Input errors** — malformed triples, unsupported language, missing target\n2. **Environment errors** — test runner not installed, wrong version, missing\n   deps\n3. **Subagent errors** — timeout, unexpected output, coordination failure\n4. **RED-gate errors** — tests pass when they should fail (false green)\n5. **Safety-refusal errors** — subagent refuses to generate test\n\n---\n\n## Adapter Contract\n\nAll language adapters implement 4 capabilities: **DETECT**, **GENERATE**,\n**RUN**, **EXPLAIN**.\n\nv1 adapters:\n\n- `adapters\u002Fpython\u002Fadapter.md` — pytest\n- `adapters\u002Fbats\u002Fadapter.md` — bats (N-block parametrize limitation documented)\n","# sme-test: Subject Matter Expert TDD Coach\n\nA coaching-driven TDD workflow that teaches you to think in Given\u002FWhen\u002FThen\ntriples before writing test code.\n\n**Arguments:** \"$ARGUMENTS\"\n\n---\n\n## Mode Dispatch\n\nParse arguments to determine mode:\n\n| Input                      | Mode            | Flow                                                          |\n| -------------------------- | --------------- | ------------------------------------------------------------- |\n| (default)                  | **Coach**       | Full 6-stage coaching flow with 3-Whys dialogue               |\n| `--expert` or `-x`         | **Expert**      | Single-turn: paste G\u002FW\u002FT triples directly, skip coaching      |\n| `--expert --auto` or `-xa` | **Expert-Auto** | Auto-infer triples from code scan with mandatory preview gate |\n\n`--auto --yes` is **not a valid flag combination** — the preview gate cannot be\nbypassed.\n\n**Escape hatches (available at any prompt in expert\u002Fexpert-auto modes):**\n\n- Type `coach` → bail up to full coach mode (3-Whys flow)\n- Type `paste` → bail sideways to manual triple entry (expert mode)\n\n---\n\n## Coach Mode (Default) — 6-Stage Flow\n\n### Stage 1: Dispatch\n\nRead the prompt from `prompts\u002Fcoach-dispatch.md` and execute it.\n\nDetect the target code file\u002Ffunction from arguments. Identify the project\nlanguage using the adapter DETECT capability. Select the appropriate adapter\nfrom `adapters\u002F`. Load any existing `shared\u002F` memory state from prior sessions.\n\n**Subagent:** test-coach (Opus) — judgment-heavy, needs deep reasoning for\nintent extraction.\n\n### Stage 2: 3-Whys\n\nRead the prompt from `prompts\u002Fthree-whys.md` and execute it.\n\nAsk three progressive \"why\" questions to surface the real behavioral intent\nbehind the user's test request. Do not accept \"test this function\" as sufficient\n— probe until a concrete behavioral contract emerges.\n\n**Subagent:** test-coach (Opus) — conversational coaching requires judgment.\n\n### Stage 3: G\u002FW\u002FT Formulation\n\nRead the prompt from `prompts\u002Fgwt-formulation.md` and execute it.\n\nGuide the user to translate 3-Whys answers into Given\u002FWhen\u002FThen triples. Each\ntriple must be concrete, testable, and non-redundant. Validate each triple\nbefore accepting.\n\n**Subagent:** test-coach (Opus) — triple validation requires judgment.\n\n### Stage 4: Test-Writer Delegation\n\nRead the prompt from `prompts\u002Ftest-writer.md` and execute it.\n\nDispatch a Sonnet subagent (test-writer) with the approved triples and the\nselected language adapter. The subagent generates executable test code. Stage\noutput for user review before proceeding.\n\n**Subagent:** test-writer (Sonnet) — structured code generation from approved\ntriples, no deep judgment needed.\n\nWrite subagent state to `shared\u002Ftest-writer-output.md`. Read all files in\n`shared\u002F` before dispatching.\n\n### Stage 5: RED Gate\n\nRead the prompt from `prompts\u002Fred-gate.md` and execute it.\n\nDispatch a Sonnet subagent (test-runner) to execute the generated tests. The\ntests **MUST fail** (red state). This gate is **mandatory** — there is **no\noverride**. If tests pass, this is an error (see error class 4 in\n`errors\u002Ferror-handlers.md`).\n\n**Subagent:** test-runner (Sonnet) — test execution is deterministic, no\nreasoning needed.\n\nWrite subagent state to `shared\u002Fred-gate-result.md`. Read all files in `shared\u002F`\nbefore dispatching.\n\n### Stage 6: Handoff\n\nPresent the failing tests to the user. Offer handoff options:\n\n- Continue manually — user writes implementation code\n- Handoff to `\u002Ftdd` — use the TDD skill for RED→GREEN→REFACTOR\n- Handoff to `\u002Fduper-tdd` — TDD in an isolated worktree\n\n---\n\n## Expert Mode (`--expert` \u002F `-x`)\n\nSkip Stages 2-3 (no 3-Whys, no coached G\u002FW\u002FT formulation).\n\n1. Prompt user to paste Given\u002FWhen\u002FThen triples in structured format\n2. Parse triples (no per-triple critique — trust the expert user)\n3. Proceed directly to Stage 4 (test-writer delegation)\n4. RED gate (Stage 5) remains **mandatory**\n5. Handoff (Stage 6)\n\n**Model routing:** Sonnet-only — no Opus subagent required. Parsing structured\ninput does not require deep reasoning.\n\n---\n\n## Expert-Auto Mode (`--expert --auto` \u002F `-xa`)\n\nReplace Stages 2-3 with automated triple inference.\n\n1. **Code scan:** test-coach (Opus) scans target file, infers triples from\n   function signatures and docstrings\n2. **Provenance tags:** Each inferred triple carries a tag identifying which\n   function\u002Fsignature it was inferred from\n3. **Cap:** Maximum **8 triples** per invocation (hard cap)\n4. **Mandatory preview gate:** User sees all inferred triples and must\n   explicitly:\n   - **(k)eep all** — accept all triples\n   - **(d)rop N** — remove specific triples\n   - **(a)dd** — add custom triples\n   - **(abort)** — cancel entirely\n\n5. Proceed to Stage 4 → Stage 5 (RED gate mandatory) → Stage 6 (handoff)\n\n**Model routing:** test-coach on Opus for inference quality (code\nunderstanding + triple generation).\n\n---\n\n## Subagent Coordination\n\nAll subagents coordinate via the `shared\u002F` memory directory pattern (per\nCLAUDE.md):\n\n| Subagent    | Model                         | Stages | Writes to `shared\u002F`            |\n| ----------- | ----------------------------- | ------ | ------------------------------ |\n| test-coach  | Opus (coach), Sonnet (expert) | 1-3    | `shared\u002Fcoach-state.md`        |\n| test-writer | Sonnet                        | 4      | `shared\u002Ftest-writer-output.md` |\n| test-runner | Sonnet                        | 5      | `shared\u002Fred-gate-result.md`    |\n\n**Rules:**\n\n- Each subagent writes only its own file in `shared\u002F`\n- Each subagent reads all files in `shared\u002F` on startup\n- Main skill agent manages cleanup and compacts to `COMBINED.md` after subagent\n  completion\n- No subagent modifies `COMBINED.md` directly\n\n---\n\n## Error Handling\n\nSee `errors\u002Ferror-handlers.md` for the 5 error classes and recovery paths:\n\n1. **Input errors** — malformed triples, unsupported language, missing target\n2. **Environment errors** — test runner not installed, wrong version, missing\n   deps\n3. **Subagent errors** — timeout, unexpected output, coordination failure\n4. **RED-gate errors** — tests pass when they should fail (false green)\n5. **Safety-refusal errors** — subagent refuses to generate test\n\n---\n\n## Adapter Contract\n\nAll language adapters implement 4 capabilities: **DETECT**, **GENERATE**,\n**RUN**, **EXPLAIN**.\n\nv1 adapters:\n\n- `adapters\u002Fpython\u002Fadapter.md` — pytest\n- `adapters\u002Fbats\u002Fadapter.md` — bats (N-block parametrize limitation documented)\n",{"name":5,"description":7,"argument-hint":49,"user-invocable":50},"[file|function] [--expert|-x] [--auto|-xa]",true,"main","9635fb649979617cf684ea860dcaeb4eb272aa7d","skills\u002Fsme-test",1,"https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn","https:\u002F\u002Flaurac8r.github.io\u002Fclaude-damn\u002F","https:\u002F\u002Fgithub.com\u002Flaurac8r","https:\u002F\u002Fwww.webcatgirl.com\u002F","SWE | Python, Java, Typescript, Cloud, AI, ML | Open-source, large-language model, and decision model enthusiast","2026-09-10 01:18:30",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":50},[63,66,69],{"tool":64,"command":65},"npx","npx skills add laurac8r\u002Fclaude-damn --skill sme-test",{"tool":67,"command":68},"bunx","bunx skills add laurac8r\u002Fclaude-damn --skill sme-test",{"tool":70,"command":71},"pnpm","pnpm dlx skills add laurac8r\u002Fclaude-damn --skill sme-test","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fsme-test\u002FSKILL.md",[74,80,84,88,92,96,100,104],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"adapters\u002Fbats\u002Fadapter.md","REFERENCE","参考文档",4422,"https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fsme-test\u002Fadapters\u002Fbats\u002Fadapter.md",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"adapters\u002Fpython\u002Fadapter.md",3822,"https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fsme-test\u002Fadapters\u002Fpython\u002Fadapter.md",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"errors\u002Ferror-handlers.md",3956,"https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fsme-test\u002Ferrors\u002Ferror-handlers.md",{"path":89,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":90,"sourceHtmlUrl":91},"prompts\u002Fcoach-dispatch.md",1721,"https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fsme-test\u002Fprompts\u002Fcoach-dispatch.md",{"path":93,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":94,"sourceHtmlUrl":95},"prompts\u002Fgwt-formulation.md",2435,"https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fsme-test\u002Fprompts\u002Fgwt-formulation.md",{"path":97,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":98,"sourceHtmlUrl":99},"prompts\u002Fred-gate.md",2946,"https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fsme-test\u002Fprompts\u002Fred-gate.md",{"path":101,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":102,"sourceHtmlUrl":103},"prompts\u002Ftest-writer.md",1753,"https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fsme-test\u002Fprompts\u002Ftest-writer.md",{"path":105,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":106,"sourceHtmlUrl":107},"prompts\u002Fthree-whys.md",2511,"https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fsme-test\u002Fprompts\u002Fthree-whys.md",[109,144,166,181,200,216],{"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":124,"publishedAt":44},"01M6K5V5PPEYZGPW80S9QAF7WZ","visual-aid","Use when the user asks for a quick visual aid, visual explainer, concept card, one-pager, poster, cheat sheet, infographic, visual summary, summary card, or mini explainer page — especially from input like a block of text, attached images, an attached song (lyrics\u002Faudio), a web link, a CSV\u002Fdataset, a math formula, a code snippet to walk through, a tutorial's steps, a timeline, or an A-vs-B comparison. Triggers include \"make me a quick visual aid\", \"turn this into a one-pager \u002F cheat sheet \u002F explainer\", \"summarize this visually\", \"give me a visual of\", \"explain this on a single page\", \"make a concept card for\", \"whip up a page about\", \"build a mini page that shows\", \"something I can paste into a doc explaining X\", or any request to render a topic\u002Ftext\u002Flink\u002Fimage-set\u002Fsong\u002Fdata into a standalone page. Prefer this skill over frontend-design when the ask is an explanatory single-file page (not a production UI), over playground when the output is static information display (not an interactive configurator), and over a Markdown\u002Fcode answer when the user explicitly wants a *page* (HTML). Produces a single self-contained HTML file that opens on double-click without a server.","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-aid\u002FSKILL.md",[115,118,121],{"categoryNo":116,"categoryName":117,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[125,126,127,35,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143],"visual","visual aid","frontend","SET","Audio","visual explainer","up","images","formula","infographic","click","card","render","information","quick","song","standalone","frontend-design","static",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":44},"01M6K5TZZ34SBMQMN2EX11XMYS","tesseract","Use when you've been poking at the same file, concept, or problem across many sessions and want to step outside time to see its whole arc — or when you want to leave a note for next-session-you. Triggers: 'I've been going in circles on X', 'what have I learned about X', 'what did past-me say about X', 'I keep rediscovering this'.","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Ftesseract\u002FSKILL.md",[],[146,151,41,152,38,153,154,155,125,156,157,158,159,160,161,162,163,28,164,165],"sessions","session","say","me","time","across","anchor","triggers","learned","problem","keep","you","morse","concept","for",{"skillNo":167,"name":42,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":171,"publishedAt":44},"01M6K5TSVWXGRFMQTSM8VFSRDS","Invoke test-driven development as an explicit one-at-a-time micro-cycle — one test, one piece of functionality, refactor, then repeat for the next behavior","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Ftdd\u002FSKILL.md",[],[42,25,172,173,174,175,176,177,155,178,179,28,180,165],"development","micro","refactor","behavior","cycle","next","as","driven","at",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":187,"publishedAt":44},"01M6K5TP1KX237V9FDZ8PMNXH5","tdd-cat","TDD workflow with subagent-driven-development — \u002Ftdd composed with \u002Fcat, plus the A\u002FB TDD execution-mode axis (split-phase vs micro-cycle) asked as a third question in \u002Fcat's combined pre-dispatch question","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Ftdd-cat\u002FSKILL.md",[],[42,188,189,190,172,173,191,192,193,194,195,196,176,178,179,197,198,28,199],"cat","tdd cat","workflow","execution","tdd workflow","subagent","question","dispatch","task","with","split","mode",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":206,"publishedAt":44},"01M6K5TGDERXT82MS7SB3ZGA3V","task-list","TaskCreate \u002F TaskUpdate \u002F render the current TaskList in response to `\u002Ftask-list` (with or without flags). The skill body executes immediately on the syntax — no permission-seeking, no echoing the list back as plain text.","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Ftask-list\u002FSKILL.md",[],[207,196,208,209,210,211,212,213,214,178,137,197,28,215],"list","task list","update","text","syntax","flags","back","permission","display",{"skillNo":217,"name":218,"nameZh":6,"description":219,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":220,"categories":221,"keywords":222,"publishedAt":44},"01M6K5T8CER0BAPJVJDG5F5GD0","sync","Sync files between two local directories, repos, or git worktrees. Five modes (plan\u002Finteractive\u002Fpush\u002Fpull\u002Fmirror), .gitignore-aware, Claude-workflow allowlist via --claude, dropbox-restore-style per-directory prompts.","https:\u002F\u002Fgithub.com\u002Flaurac8r\u002Fclaude-damn\u002Fblob\u002Fmain\u002Fskills\u002Fsync\u002FSKILL.md",[],[218,190,223,224,225,226,227,228,229,230,231,232,233,234,235,236,28,199,237,238],"delete","pull","push","plan","interactive","git worktrees","files","restore","gitignore","local","dry","directories","yes","limit","mirror","modes"]