[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6P62J8XKJHPCA4FDZ8VD8CS":3,"skill-same:01M6P62J8XKJHPCA4FDZ8VD8CS":101},{"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":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":80,"commitSha":81,"skillDirectory":82,"forksCount":83,"repositoryHtmlUrl":84,"repositoryHomepageUrl":6,"ownerHtmlUrl":85,"ownerBlogUrl":86,"ownerDescription":6,"updatedAt":87,"install":88,"resources":100},"01M6P62J8XKJHPCA4FDZ8VD8CS","build-sweep",null,"Produces a verified build\u002Ftest status report and auto-fixed modules by sweeping all Go modules in a workspace. Use when: \"run a sweep\", \"check all builds\", \"nightly sweep\", \"fix all failing modules\", \"workspace health check\".","DojoGenesis\u002Fgateway","DojoGenesis","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F273886418?v=4","01M6P54RXMD3TZ2082Z3Z4JMQP","Cruz Morales (TresPies)","01M6P54S269YR0ZZZ96WGQM439",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fsystem-health\u002Fskills\u002Fbuild-sweep\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"build sweep","build","sweep","auto","verified","path","sonnet","STRING","status report","modules","verified build","directory","fix","table","text","markdown","run","status","commit","go","2026-11-10 10:12:30",false,"---\nname: build-sweep\nmodel: sonnet\ndescription: \"Produces a verified build\u002Ftest status report and auto-fixed modules by sweeping all Go modules in a workspace. Use when: \\\"run a sweep\\\", \\\"check all builds\\\", \\\"nightly sweep\\\", \\\"fix all failing modules\\\", \\\"workspace health check\\\".\"\ncategory: system-health\ntriggers:\n  - \"run a sweep\"\n  - \"check all builds\"\n  - \"nightly sweep\"\n  - \"fix all failing modules\"\n  - \"workspace health check\"\ntier: 1\nagents:\n  - \"primary\"\ntool_dependencies:\n  - \"file_system\"\n\ninputs:\n  - name: workspace_path\n    type: string\n    description: Root directory containing Go modules to sweep\n    required: true\noutputs:\n  - name: sweep_report\n    type: text\n    format: markdown-table\n    description: Verified status table of all modules with build\u002Ftest results, fixes applied, and commit hashes\n---\n# Build Sweep Skill\n\n## Philosophy\n\nA healthy workspace is one where every module compiles and every test passes. The build sweep is not a debugging session — it is a systematic sweep that treats each module as an independent unit, diagnoses failures mechanically, and applies minimal fixes. The sweep must never trust self-reports: every fix is verified by re-running the exact build and test commands that originally failed.\n\n## When to Use\n\n- As a scheduled nightly task to catch drift across a multi-module workspace\n- Before a release to verify all modules are green\n- After a large refactor or dependency update that may have broken multiple modules\n- When onboarding to a workspace to establish a health baseline\n\n## Workflow\n\n### Phase 1: Detect\n1. Find all directories containing `go.mod` under the workspace path (skip `vendor\u002F`, `.git\u002F`, `node_modules\u002F`, `.claude\u002Fworktrees\u002F`)\n2. For each module, run `go build .\u002F...` and `go test .\u002F...`\n3. Collect results into a table: module | build status | test status | error summary\n\n### Phase 2: Diagnose and Fix\nFor each failing module, dispatch a parallel agent (max 5 concurrent) to:\n1. Read the failing build\u002Ftest output\n2. Read the relevant source files to diagnose the root cause\n3. Implement the minimal fix — do not refactor, do not add features\n4. Re-run that module's build and tests to confirm green\n\n### Phase 3: Verify\nAfter ALL agents complete, independently verify each fix:\n1. Run the tests yourself — do NOT trust agent self-reports of completion\n2. Check actual file diffs with `git diff`\n3. Confirm no duplicate imports, wrong formats, or regressions\n4. Run the full suite one final time to catch cross-module integration issues\n\n### Phase 4: Commit\nIf all fixes pass verification:\n1. Stage only the fixed files (not unrelated changes)\n2. Commit each module separately: `fix(sweep): [module] — [one-line description]`\n\n### Phase 5: Report\nOutput a verified summary table: module | failure type | fix applied | verification status | commit hash\n\n## Output\n\nThe skill produces:\n1. A markdown table summarizing all module statuses\n2. Git commits for each fix applied (one per module)\n3. A final pass\u002Ffail verdict for the entire workspace\n\n## Examples\n\n**Clean workspace:**\n```\n\u002Fsweep\n> All 29 modules pass build and test. No action needed.\n```\n\n**Two failures detected and fixed:**\n```\n\u002Fsweep\n> Phase 1: 27 pass, 2 fail (DIP: missing interface method, MCP: stale test count)\n> Phase 2: Dispatched 2 agents\n> Phase 3: Both fixes verified independently\n> Phase 4: 2 commits created\n> RESULT: 29\u002F29 modules green\n```\n\n## Edge Cases\n\n- **Module with no test files**: Report as SKIP, not FAIL — `[no test files]` is not an error\n- **Flaky tests**: If a test fails then passes on rerun, report as FLAKY with the original error\n- **Circular dependency between modules**: Run builds in topological order if dependency info is available\n- **Module requires external service**: Skip with a note if `go test` fails due to missing database\u002Fservice connection\n- **Agent fix breaks another module**: Resolve the cross-module conflict before committing either fix\n\n## Anti-Patterns\n\n- **Trusting agent self-reports**: Agents may report \"all tests pass\" without actually running them. Always verify.\n- **Committing untested fixes**: Never commit a fix without running the full build and test suite for that module.\n- **Fixing unrelated issues**: The sweep fixes build\u002Ftest failures only. Do not refactor, add features, or clean up code.\n- **Running the full workspace test suite after each individual fix**: Too slow. Verify each module independently, then run one final integration pass.\n- **Force-pushing sweep commits**: Sweep commits are always local. Never push without explicit user confirmation.\n","# Build Sweep Skill\n\n## Philosophy\n\nA healthy workspace is one where every module compiles and every test passes. The build sweep is not a debugging session — it is a systematic sweep that treats each module as an independent unit, diagnoses failures mechanically, and applies minimal fixes. The sweep must never trust self-reports: every fix is verified by re-running the exact build and test commands that originally failed.\n\n## When to Use\n\n- As a scheduled nightly task to catch drift across a multi-module workspace\n- Before a release to verify all modules are green\n- After a large refactor or dependency update that may have broken multiple modules\n- When onboarding to a workspace to establish a health baseline\n\n## Workflow\n\n### Phase 1: Detect\n1. Find all directories containing `go.mod` under the workspace path (skip `vendor\u002F`, `.git\u002F`, `node_modules\u002F`, `.claude\u002Fworktrees\u002F`)\n2. For each module, run `go build .\u002F...` and `go test .\u002F...`\n3. Collect results into a table: module | build status | test status | error summary\n\n### Phase 2: Diagnose and Fix\nFor each failing module, dispatch a parallel agent (max 5 concurrent) to:\n1. Read the failing build\u002Ftest output\n2. Read the relevant source files to diagnose the root cause\n3. Implement the minimal fix — do not refactor, do not add features\n4. Re-run that module's build and tests to confirm green\n\n### Phase 3: Verify\nAfter ALL agents complete, independently verify each fix:\n1. Run the tests yourself — do NOT trust agent self-reports of completion\n2. Check actual file diffs with `git diff`\n3. Confirm no duplicate imports, wrong formats, or regressions\n4. Run the full suite one final time to catch cross-module integration issues\n\n### Phase 4: Commit\nIf all fixes pass verification:\n1. Stage only the fixed files (not unrelated changes)\n2. Commit each module separately: `fix(sweep): [module] — [one-line description]`\n\n### Phase 5: Report\nOutput a verified summary table: module | failure type | fix applied | verification status | commit hash\n\n## Output\n\nThe skill produces:\n1. A markdown table summarizing all module statuses\n2. Git commits for each fix applied (one per module)\n3. A final pass\u002Ffail verdict for the entire workspace\n\n## Examples\n\n**Clean workspace:**\n```\n\u002Fsweep\n> All 29 modules pass build and test. No action needed.\n```\n\n**Two failures detected and fixed:**\n```\n\u002Fsweep\n> Phase 1: 27 pass, 2 fail (DIP: missing interface method, MCP: stale test count)\n> Phase 2: Dispatched 2 agents\n> Phase 3: Both fixes verified independently\n> Phase 4: 2 commits created\n> RESULT: 29\u002F29 modules green\n```\n\n## Edge Cases\n\n- **Module with no test files**: Report as SKIP, not FAIL — `[no test files]` is not an error\n- **Flaky tests**: If a test fails then passes on rerun, report as FLAKY with the original error\n- **Circular dependency between modules**: Run builds in topological order if dependency info is available\n- **Module requires external service**: Skip with a note if `go test` fails due to missing database\u002Fservice connection\n- **Agent fix breaks another module**: Resolve the cross-module conflict before committing either fix\n\n## Anti-Patterns\n\n- **Trusting agent self-reports**: Agents may report \"all tests pass\" without actually running them. Always verify.\n- **Committing untested fixes**: Never commit a fix without running the full build and test suite for that module.\n- **Fixing unrelated issues**: The sweep fixes build\u002Ftest failures only. Do not refactor, add features, or clean up code.\n- **Running the full workspace test suite after each individual fix**: Too slow. Verify each module independently, then run one final integration pass.\n- **Force-pushing sweep commits**: Sweep commits are always local. Never push without explicit user confirmation.\n",{"name":5,"tier":57,"model":38,"agents":58,"inputs":60,"outputs":66,"category":71,"triggers":72,"description":7,"tool_dependencies":78},1,[59],"primary",[61],{"name":62,"type":63,"required":64,"description":65},"workspace_path","string",true,"Root directory containing Go modules to sweep",[67],{"name":68,"type":46,"format":69,"description":70},"sweep_report","markdown-table","Verified status table of all modules with build\u002Ftest results, fixes applied, and commit hashes","system-health",[73,74,75,76,77],"run a sweep","check all builds","nightly sweep","fix all failing modules","workspace health check",[79],"file_system","main","ff07df5fd8f75762c2a131e6e26d297e8ae403ee","plugins\u002Fsystem-health\u002Fskills\u002Fbuild-sweep",0,"https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway","https:\u002F\u002Fgithub.com\u002FDojoGenesis","dojogenesis.com","2026-10-25 22:59:58",{"source":8,"skillName":5,"commands":89,"prompt":99,"zipAvailable":64},[90,93,96],{"tool":91,"command":92},"npx","npx skills add DojoGenesis\u002Fgateway --skill build-sweep",{"tool":94,"command":95},"bunx","bunx skills add DojoGenesis\u002Fgateway --skill build-sweep",{"tool":97,"command":98},"pnpm","pnpm dlx skills add DojoGenesis\u002Fgateway --skill build-sweep","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fsystem-health\u002Fskills\u002Fbuild-sweep\u002FSKILL.md",[],[102,119,130,138,177,202],{"skillNo":103,"name":104,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":108,"publishedAt":52},"01M6P6J0WYSD1MTGA3ZX6MGGZ5","kata-test-echo","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fserver\u002Ftestdata\u002Fkata\u002Fskills\u002Fkata-test-echo\u002FSKILL.md",[107],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[109,110,111,112,113,114,115,116,117,118],"kata test echo","Echo","test","json","v1","output","input","structured","contracts","schema",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":126,"publishedAt":52},"01M6P6HQJNGG4WPZW0DEWMAY2N","kata-plain","An ordinary prose skill; not dispatchable.","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fserver\u002Ftestdata\u002Fkata\u002Fskills\u002Fkata-plain\u002FSKILL.md",[125],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[127,128,129],"kata plain","prose skill","prose",{"skillNo":131,"name":132,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":52},"01M6P6HH6Y7K8K6606MF7VZ1HB","kata-broken","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fserver\u002Ftestdata\u002Fkata\u002Fskills\u002Fkata-broken\u002FSKILL.md",[],[136,137,116,117,110,118,112,111,115,113,114],"kata broken","broken",{"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":156,"publishedAt":52},"01M6P6GW520QJ03A6K7Y5PWJ52","voice-before-structure","Read the project's design language and philosophy before writing structural artifacts. Ground manifests, READMEs, and descriptions in the project's voice, not boilerplate. Use when creating manifests or READMEs for established projects, writing ecosystem-level documentation, building plugin descriptions or marketplace metadata, or authoring metadata that carries a project's identity. Trigger phrases: 'write the manifest', 'create a README', 'describe this plugin', 'ground yourself in the philosophy', 'ecosystem-level work'.","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fvoice-before-structure\u002FSKILL.md",[144,147,150,153],{"categoryNo":145,"categoryName":146,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":148,"categoryName":149,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":151,"categoryName":152,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000032","设计师",{"categoryNo":154,"categoryName":155,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000036","内容创作者",[157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176],"voice before structure","structure","voice","manifests","ecosystem","false","authoring","structural","project","artifact","philosophy","design","writing","identity","documentation","create","projects","work","read","write",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":184,"publishedAt":52},"01M6P6GMNA4HJ4D5RRM3BQZ73M","system-prompt-archaeology","Produces a named ADA disposition preset (YAML) and a layered behavioral analysis (structural decomposition + evidence-cited classifications) from a system prompt. Use when: \"analyze this system prompt\", \"extract disposition from prompt\", \"reverse-engineer agent behavior\", \"what patterns does this prompt use\", \"build a preset from this prompt\".","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fsystem-prompt-archaeology\u002FSKILL.md",[183],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[185,186,187,188,189,190,164,191,192,193,194,195,196,197,198,199,39,38,200,201],"system prompt archaeology","system prompt","prompt","system","behavioral","classify","decomposition","wisdom","patterns","engineer","decompose","evidence","ada","analyze","analysis","true","reverse",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":209,"publishedAt":52},"01M6P6G2D70T9R00HX6K154X5Y","session-lifecycle-automation","Designs and configures all three loops of solo-operator session automation — session bookends, background maintenance agents, and a delegation flywheel. Use when setting up a new workspace, recovering from the 44% zero-artifact session leak, or preparing to scale delegation across multiple concurrent agents.","https:\u002F\u002Fgithub.com\u002FDojoGenesis\u002Fgateway\u002Fblob\u002Fmain\u002Fplugins\u002Fwisdom-garden\u002Fskills\u002Fsession-lifecycle-automation\u002FSKILL.md",[208],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[210,211,212,213,214,47,215,43,216,217,218,219,220,166,221,222,223,224,225,226],"automation","session lifecycle automation","session lifecycle","lifecycle","session","configure","config","delegation","audit","SET","files","solo","across","scheduled","loops","up","template"]