[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QPPJA6P2HDC19FFR3FZB7A":3,"skill-same:01M6QPPJA6P2HDC19FFR3FZB7A":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":42,"install":43,"resources":56},"01M6QPPJA6P2HDC19FFR3FZB7A","unslop-coder",null,"Apply unslop-reviewer findings as targeted in-scope code edits in pass order; do not run discovery\u002Fscanning in this skill.","theCat69\u002Fla-briguade","theCat69","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F40163881?v=4","01M6QPEW8JP05VD4Q9E4TJDFB3","01M6QPEWCX5VB9ZKJ7E96BXEHQ",1,"MIT","https:\u002F\u002Fgithub.com\u002FtheCat69\u002Fla-briguade\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Funslop-coder\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28,29],"unslop","coder","unslop coder","run","code","discovery","reviewer","scanning","do","as","scope","apply","2026-11-10 10:12:30",false,"---\nname: unslop-coder\ndescription: Apply unslop-reviewer findings as targeted in-scope code edits in pass order; do not run discovery\u002Fscanning in this skill.\nagents:\n  - coder\n---\n\n# Unslop Coder\n\n**Purpose**: apply a pre-computed findings list from an `unslop-reviewer` sidekick review.\n\nThis skill is implementation-only: it **edits files** to apply listed findings.\nIt is not a scanning skill.\n\n## What You'll Be Fixing\n\nApply only the categories and priorities provided by `unslop-reviewer`; treat that\nreview output as the canonical slop taxonomy for each run.\n\n## Input Format\n\nThe calling prompt provides a findings list in the format produced by `unslop-reviewer`:\n\n```\n1. F-1 | src\u002Fauth.ts | pass:1 | dead-code | S | Unused `lodash` import at line 3 | Delete line 3\n2. F-2 | src\u002Fauth.ts | pass:3 | naming | S | Variable named `data` at line 47 | Rename to `userRecord`\n…\n```\n\nEach finding must use: `F-id | relative-file-path | pass:1-4 | category | size | description | fix`.\nValid categories are `dead-code`, `duplication`, `abstraction`, `boundary`, `naming`,\n`error-handling`, and `test`; sizes are `S`, `M`, or `L`.\n\nApply **only** listed findings. Before editing, confirm the referenced code still exists and the\nproposed fix still matches it. Do not scan for additional slop or apply fixes not present in the\nlist. Skip stale, conflicting, or ambiguous findings and report why.\n\n---\n\n## Application Mechanics\n\n- Apply findings strictly in **pass order**: pass 1 → pass 2 → pass 3 → pass 4.\n- Within each pass, process findings by **file path**. For conflicting findings in the same file,\n  apply only the safer, independently valid finding; report the other as skipped.\n- Never touch files outside caller-provided scope.\n- Apply only the requested fix; do not add opportunistic refactors.\n\n## Non-Negotiable Constraints\n\n- **Preserve observable behavior**. Slop cleanup is a scalpel, not a rewrite.\n- Prefer deletion over addition, but never delete speculatively.\n- **Test-before-delete**: if deletion may affect side effects, lock behavior with a test\n  first, then delete. When test writing is not active, skip and report that finding instead.\n- This skill **always edits files**; it is not for read-only review.\n\n---\n\n## Test-Writing Behavior\n\nTest writing is **opt-in**. Only write new tests when the calling prompt explicitly\nstates that **test-writing override is active**.\n\nWhen active: for each pass-4 finding, write targeted tests that lock the described\nbehavior. Every test must assert a meaningful outcome (not only \"no error thrown\").\nCo-locate tests with existing project test files.\n\nWhen not active: skip pass-4 implementation. Report those findings as deferred gaps.\n\n---\n\n## Reduction Override\n\nWhen the caller explicitly states that reduction mode is active, optimize for **net code-size reduction** within the listed findings.\n\n- Favor the smallest safe implementation that removes lines or symbols.\n- Allowed examples: inline pass-through wrappers, consolidate exact duplicates, remove useless comments, and delete redundant locals\u002Fimports\u002Fguards.\n- Skip rename-only or stylistic cleanup that does not materially shrink the code.\n- Never add a broader abstraction if it increases code size.\n\n---\n\n## Orchestrator Validation Contract\n\nWhen called from `\u002Funslop-loop` Orchestrator mode with a validation rule, this skill must:\n\n1. Detect test runner using the caller-provided order and set `test_cmd`.\n2. If a runner is available, execute `test_cmd` after edits.\n3. Report `tests: pass` or `tests: fail`.\n4. When `tests: fail`, include failing test names in output.\n\nIf no runner is available, report `test_cmd: none`.\n\n---\n\n## Output (≤ 300 tokens)\n\n- **Files touched** — list modified files\n- **Applied findings** — one line per finding: `F-id: \u003Cwhat was done>`\n- **Skipped findings** — each skipped finding with reason (out of scope, ambiguous fix,\n  unsafe change, etc.)\n- **Pass-4 gaps** — when override is not active, list deferred pass-4 findings\n- **Risks** — remaining risk areas that could not be safely cleaned in-scope\n- **Validation status** — `test_cmd: \u003Ccommand|none>` and `tests: pass|fail`; include failing test names when status is fail\n","# Unslop Coder\n\n**Purpose**: apply a pre-computed findings list from an `unslop-reviewer` sidekick review.\n\nThis skill is implementation-only: it **edits files** to apply listed findings.\nIt is not a scanning skill.\n\n## What You'll Be Fixing\n\nApply only the categories and priorities provided by `unslop-reviewer`; treat that\nreview output as the canonical slop taxonomy for each run.\n\n## Input Format\n\nThe calling prompt provides a findings list in the format produced by `unslop-reviewer`:\n\n```\n1. F-1 | src\u002Fauth.ts | pass:1 | dead-code | S | Unused `lodash` import at line 3 | Delete line 3\n2. F-2 | src\u002Fauth.ts | pass:3 | naming | S | Variable named `data` at line 47 | Rename to `userRecord`\n…\n```\n\nEach finding must use: `F-id | relative-file-path | pass:1-4 | category | size | description | fix`.\nValid categories are `dead-code`, `duplication`, `abstraction`, `boundary`, `naming`,\n`error-handling`, and `test`; sizes are `S`, `M`, or `L`.\n\nApply **only** listed findings. Before editing, confirm the referenced code still exists and the\nproposed fix still matches it. Do not scan for additional slop or apply fixes not present in the\nlist. Skip stale, conflicting, or ambiguous findings and report why.\n\n---\n\n## Application Mechanics\n\n- Apply findings strictly in **pass order**: pass 1 → pass 2 → pass 3 → pass 4.\n- Within each pass, process findings by **file path**. For conflicting findings in the same file,\n  apply only the safer, independently valid finding; report the other as skipped.\n- Never touch files outside caller-provided scope.\n- Apply only the requested fix; do not add opportunistic refactors.\n\n## Non-Negotiable Constraints\n\n- **Preserve observable behavior**. Slop cleanup is a scalpel, not a rewrite.\n- Prefer deletion over addition, but never delete speculatively.\n- **Test-before-delete**: if deletion may affect side effects, lock behavior with a test\n  first, then delete. When test writing is not active, skip and report that finding instead.\n- This skill **always edits files**; it is not for read-only review.\n\n---\n\n## Test-Writing Behavior\n\nTest writing is **opt-in**. Only write new tests when the calling prompt explicitly\nstates that **test-writing override is active**.\n\nWhen active: for each pass-4 finding, write targeted tests that lock the described\nbehavior. Every test must assert a meaningful outcome (not only \"no error thrown\").\nCo-locate tests with existing project test files.\n\nWhen not active: skip pass-4 implementation. Report those findings as deferred gaps.\n\n---\n\n## Reduction Override\n\nWhen the caller explicitly states that reduction mode is active, optimize for **net code-size reduction** within the listed findings.\n\n- Favor the smallest safe implementation that removes lines or symbols.\n- Allowed examples: inline pass-through wrappers, consolidate exact duplicates, remove useless comments, and delete redundant locals\u002Fimports\u002Fguards.\n- Skip rename-only or stylistic cleanup that does not materially shrink the code.\n- Never add a broader abstraction if it increases code size.\n\n---\n\n## Orchestrator Validation Contract\n\nWhen called from `\u002Funslop-loop` Orchestrator mode with a validation rule, this skill must:\n\n1. Detect test runner using the caller-provided order and set `test_cmd`.\n2. If a runner is available, execute `test_cmd` after edits.\n3. Report `tests: pass` or `tests: fail`.\n4. When `tests: fail`, include failing test names in output.\n\nIf no runner is available, report `test_cmd: none`.\n\n---\n\n## Output (≤ 300 tokens)\n\n- **Files touched** — list modified files\n- **Applied findings** — one line per finding: `F-id: \u003Cwhat was done>`\n- **Skipped findings** — each skipped finding with reason (out of scope, ambiguous fix,\n  unsafe change, etc.)\n- **Pass-4 gaps** — when override is not active, list deferred pass-4 findings\n- **Risks** — remaining risk areas that could not be safely cleaned in-scope\n- **Validation status** — `test_cmd: \u003Ccommand|none>` and `tests: pass|fail`; include failing test names when status is fail\n",{"name":5,"agents":35,"description":7},[19],"main","f4f3a02e82412dd181a98c114c6650ec02475d0f","content\u002Fskills\u002Funslop-coder",0,"https:\u002F\u002Fgithub.com\u002FtheCat69\u002Fla-briguade","https:\u002F\u002Fgithub.com\u002FtheCat69","2026-09-14 16:38:37",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add theCat69\u002Fla-briguade --skill unslop-coder",{"tool":49,"command":50},"bunx","bunx skills add theCat69\u002Fla-briguade --skill unslop-coder",{"tool":52,"command":53},"pnpm","pnpm dlx skills add theCat69\u002Fla-briguade --skill unslop-coder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FtheCat69\u002Fla-briguade\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Funslop-coder\u002FSKILL.md",true,[],[58,78,92,121,139,161],{"skillNo":59,"name":18,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":30},"01M6QPPWK5A3WJ1SAYDNR5YD6S","Perform sequential slop-cleanup edits in bounded changed-file scope with behavior-preserving rules; do not use for read-only scanning.","https:\u002F\u002Fgithub.com\u002FtheCat69\u002Fla-briguade\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Funslop\u002FSKILL.md",[],[18,64,65,66,67,68,69,70,28,26,71,25,72,73,74,75,76,77],"only","behavior-preserving","bounded","slop","for","read-only","with","builder","use","behavior","read","Rules","file","cleanup",{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":30},"01M6QPPPQ49KBWSWH3X9D9R17B","unslop-reviewer","Run a read-only, pass-ordered slop scan covering abstraction and locally fixable boundary findings; never edit files.","https:\u002F\u002Fgithub.com\u002FtheCat69\u002Fla-briguade\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Funslop-reviewer\u002FSKILL.md",[],[24,18,85,86,74,87,88,67,89,21,64,69,90,91],"unslop reviewer","never","sidekick","edit","boundary","scan","files",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":103,"publishedAt":30},"01M6QPP53KFSKE5KGJBGAKD3WW","serena","Semantic code retrieval, editing, refactoring and debugging tools using LSP servers","https:\u002F\u002Fgithub.com\u002FtheCat69\u002Fla-briguade\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Fserena\u002FSKILL.md",[98],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[94,104,105,106,107,108,109,110,71,111,112,113,114,115,22,116,117,118,119,120],"debugging tools","mcp-server","retrieval","false","project","local","lsp","editing","debugging","open","server","https","web","dashboard","github","MCP","refactoring",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":130,"publishedAt":30},"01M6QPP2M71X18ENVM3R3B6D10","read-image","guidance to read images in a lightweight fashion using cwebp","https:\u002F\u002Fgithub.com\u002FtheCat69\u002Fla-briguade\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Fread-image\u002FSKILL.md",[127],{"categoryNo":128,"categoryName":129,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000016","图像与多媒体",[131,74,132,133,134,135,136,71,137,138,19],"read image","image","cwebp","fashion","guidance","images","orchestrator","ask",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":148,"publishedAt":30},"01M6QPNWCSF2V8AGS8KH9D6A54","playwright-cli","Drive browser UI checks with playwright-cli commands, snapshots, and test\u002Fdebug workflows; do not use for backend-only or non-browser tasks.","https:\u002F\u002Fgithub.com\u002FtheCat69\u002Fla-briguade\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Fplaywright-cli\u002FSKILL.md",[145],{"categoryNo":146,"categoryName":147,"taxonomyType":101,"taxonomyTypeDesc":102},"01JBSEEDCAT000000000000008","测试与质量",[149,150,151,152,26,153,71,64,154,72,19,155,156,157,158,159,160,141,68,70],"playwright cli","playwright","cli","debug","snapshots","backend","ui","browser","tasks","commands","workflows","test",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":168,"publishedAt":30},"01M6QPNEM5D3N37R8E5YEAAV6D","next-devtools","skill to help you use next-devtools","https:\u002F\u002Fgithub.com\u002FtheCat69\u002Fla-briguade\u002Fblob\u002Fmain\u002Fcontent\u002Fskills\u002Fnext-devtools\u002FSKILL.md",[167],{"categoryNo":99,"categoryName":100,"taxonomyType":101,"taxonomyTypeDesc":102},[169,170,171,172,173,109,46,71,72,19,174,119],"next devtools","next","devtools","latest","you","help"]