[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QVBJWV7ZA80CSSN54P92E0":3,"skill-same:01M6QVBJWV7ZA80CSSN54P92E0":53},{"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":28,"linkOnly":29,"markdownContent":30,"markdownBody":31,"frontMatter":32,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M6QVBJWV7ZA80CSSN54P92E0","optimize-repo-skills",null,"Audits a repository's harness skills against the actual codebase, proposes conservative skill updates, and after explicit approval updates, creates, or removes repo-specific skills.","joe-salamy\u002Fharness-loadouts","joe-salamy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F241636360?v=4","01M6QV9XR82S4QFQCPTJXK2KTZ","Joe Salamy","01M6QV9XWN08VFW40FDQAE3CHP",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjoe-salamy\u002Fharness-loadouts\u002Fblob\u002Fmain\u002F.omp\u002Fskills\u002Foptimize-repo-skills\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27],"repo","optimize","optimize repo skills","harness","repository","approval","skill updates","updates","codebase","2026-11-10 10:12:30",false,"---\nname: optimize-repo-skills\ndescription: Audits a repository's harness skills against the actual codebase, proposes conservative skill updates, and after explicit approval updates, creates, or removes repo-specific skills.\n---\n\n# Optimize Repo Skills\n\nUse this skill when a repository's skill set needs periodic curation instead of routine load tracking. The goal is a small, high-signal set of repo-specific skills that reduce future agent mistakes without adding routine cognitive overhead.\n\n## Required Input\n\n- Repository root to analyze.\n- Harness skills directory, usually `.\u003Charness>\u002Fskills` such as `.omp\u002Fskills`.\n- Any user preference about skill count, protected skills, or areas to ignore.\n\nIf the repo root or skills directory is ambiguous, inspect the repository layout first. Ask only when tools cannot resolve the ambiguity.\n\n## Safety Rules\n\n- Do not read, write, or diff `scratchpad.md`.\n- Preserve user changes you did not make.\n- Treat skill deletion and broad rewrites as destructive: propose them first and get explicit approval before applying them.\n- Do not create generic skills. Every skill must map to observed repo conventions, recurring workflows, risk areas, or project-specific tooling.\n- Prefer editing existing skills over replacing them when the skill's purpose is still valid.\n- Keep final active repo skills lean. A typical repo should have 5-10 high-leverage skills unless the codebase clearly needs more.\n\n## Workflow\n\n1. Inventory the repo:\n   - read existing repo instructions and README\u002Fdeveloper docs;\n   - inspect manifests, source layout, tests, migrations, deployment files, and scripts;\n   - identify primary languages, frameworks, data stores, auth\u002Fsecurity boundaries, build\u002Ftest commands, and recurring workflows.\n\n2. Inventory existing skills:\n   - read every `SKILL.md` under the repo skills directory;\n   - note each skill's trigger, concrete repo knowledge, commands, protected invariants, and overlap with other skills;\n   - mark stale skills whose files, commands, frameworks, or workflows no longer exist.\n\n3. Before creating new skills, research skill-authoring guidance:\n   - search existing available skills for names\u002Fdescriptions related to skill creation, skill writing, or skill design, then read the relevant `SKILL.md` files;\n   - consult official harness skill documentation when available;\n   - use web search for current external framework\u002Flibrary facts needed by any new or heavily updated skill, preferring official docs and source repositories.\n\n4. Produce a curation proposal before destructive changes:\n   - skills to keep unchanged, with reason;\n   - skills to update, with exact gaps to fix;\n   - skills to delete, with evidence that they are stale or redundant;\n   - skills to create, with trigger condition, source evidence, and expected future failure avoided.\n\n5. Ask for approval before applying deletes or broad rewrites. Small typo fixes or clearly non-destructive clarifications may be applied directly if they preserve behavior.\n\n6. Apply approved changes:\n   - one directory per skill: `\u003Cskills-root>\u002F\u003Cskill-name>\u002FSKILL.md`;\n   - frontmatter must include exact `name` and a specific `description` explaining when to use it;\n   - guidance must be concise and repo-specific: files, commands, invariants, edge cases, and verification checks that were confirmed during analysis;\n   - remove obsolete skills completely after approval, including empty directories.\n\n7. Verify the resulting skill set:\n   - every skill has valid frontmatter;\n   - descriptions have clear trigger conditions;\n   - no two skills own the same job without a deliberate split;\n   - commands and file paths referenced by skills exist or are explicitly documented as external prerequisites;\n   - the final count and coverage match the repo's actual risk profile.\n\n## Output Standard\n\nReport:\n\n- repo areas inspected;\n- skills kept, changed, created, and deleted;\n- web sources used for new or materially updated skills;\n- approval decisions received before destructive changes;\n- verification performed;\n- residual risks or skills intentionally left unchanged.\n","# Optimize Repo Skills\n\nUse this skill when a repository's skill set needs periodic curation instead of routine load tracking. The goal is a small, high-signal set of repo-specific skills that reduce future agent mistakes without adding routine cognitive overhead.\n\n## Required Input\n\n- Repository root to analyze.\n- Harness skills directory, usually `.\u003Charness>\u002Fskills` such as `.omp\u002Fskills`.\n- Any user preference about skill count, protected skills, or areas to ignore.\n\nIf the repo root or skills directory is ambiguous, inspect the repository layout first. Ask only when tools cannot resolve the ambiguity.\n\n## Safety Rules\n\n- Do not read, write, or diff `scratchpad.md`.\n- Preserve user changes you did not make.\n- Treat skill deletion and broad rewrites as destructive: propose them first and get explicit approval before applying them.\n- Do not create generic skills. Every skill must map to observed repo conventions, recurring workflows, risk areas, or project-specific tooling.\n- Prefer editing existing skills over replacing them when the skill's purpose is still valid.\n- Keep final active repo skills lean. A typical repo should have 5-10 high-leverage skills unless the codebase clearly needs more.\n\n## Workflow\n\n1. Inventory the repo:\n   - read existing repo instructions and README\u002Fdeveloper docs;\n   - inspect manifests, source layout, tests, migrations, deployment files, and scripts;\n   - identify primary languages, frameworks, data stores, auth\u002Fsecurity boundaries, build\u002Ftest commands, and recurring workflows.\n\n2. Inventory existing skills:\n   - read every `SKILL.md` under the repo skills directory;\n   - note each skill's trigger, concrete repo knowledge, commands, protected invariants, and overlap with other skills;\n   - mark stale skills whose files, commands, frameworks, or workflows no longer exist.\n\n3. Before creating new skills, research skill-authoring guidance:\n   - search existing available skills for names\u002Fdescriptions related to skill creation, skill writing, or skill design, then read the relevant `SKILL.md` files;\n   - consult official harness skill documentation when available;\n   - use web search for current external framework\u002Flibrary facts needed by any new or heavily updated skill, preferring official docs and source repositories.\n\n4. Produce a curation proposal before destructive changes:\n   - skills to keep unchanged, with reason;\n   - skills to update, with exact gaps to fix;\n   - skills to delete, with evidence that they are stale or redundant;\n   - skills to create, with trigger condition, source evidence, and expected future failure avoided.\n\n5. Ask for approval before applying deletes or broad rewrites. Small typo fixes or clearly non-destructive clarifications may be applied directly if they preserve behavior.\n\n6. Apply approved changes:\n   - one directory per skill: `\u003Cskills-root>\u002F\u003Cskill-name>\u002FSKILL.md`;\n   - frontmatter must include exact `name` and a specific `description` explaining when to use it;\n   - guidance must be concise and repo-specific: files, commands, invariants, edge cases, and verification checks that were confirmed during analysis;\n   - remove obsolete skills completely after approval, including empty directories.\n\n7. Verify the resulting skill set:\n   - every skill has valid frontmatter;\n   - descriptions have clear trigger conditions;\n   - no two skills own the same job without a deliberate split;\n   - commands and file paths referenced by skills exist or are explicitly documented as external prerequisites;\n   - the final count and coverage match the repo's actual risk profile.\n\n## Output Standard\n\nReport:\n\n- repo areas inspected;\n- skills kept, changed, created, and deleted;\n- web sources used for new or materially updated skills;\n- approval decisions received before destructive changes;\n- verification performed;\n- residual risks or skills intentionally left unchanged.\n",{"name":5,"description":7},"main","c5d81adf56b155b93b6015e0e15e0d8f9ed8d62f",".omp\u002Fskills\u002Foptimize-repo-skills","https:\u002F\u002Fgithub.com\u002Fjoe-salamy\u002Fharness-loadouts","https:\u002F\u002Fgithub.com\u002Fjoe-salamy","2026-09-24 09:29:45",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add joe-salamy\u002Fharness-loadouts --skill optimize-repo-skills",{"tool":45,"command":46},"bunx","bunx skills add joe-salamy\u002Fharness-loadouts --skill optimize-repo-skills",{"tool":48,"command":49},"pnpm","pnpm dlx skills add joe-salamy\u002Fharness-loadouts --skill optimize-repo-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjoe-salamy\u002Fharness-loadouts\u002Fblob\u002Fmain\u002F.omp\u002Fskills\u002Foptimize-repo-skills\u002FSKILL.md",true,[],[54,70,76,108,133,149],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":65,"publishedAt":28},"01M6QVC87213Q24845Q5W8FXRJ","example-skill","Replace this with your skill description","https:\u002F\u002Fgithub.com\u002Fjoe-salamy\u002Fharness-loadouts\u002Fblob\u002Fmain\u002Fexamples\u002Ftypescript\u002F.harness\u002Fskills\u002Fexample-skill\u002FSKILL.md",[60],{"categoryNo":61,"categoryName":62,"taxonomyType":63,"taxonomyTypeDesc":64},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[66,67,68,69],"example","example skill","with","your skill",{"skillNo":71,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":75,"publishedAt":28},"01M6QVC2XCSAFTK7X7QVH094XR","https:\u002F\u002Fgithub.com\u002Fjoe-salamy\u002Fharness-loadouts\u002Fblob\u002Fmain\u002Fexamples\u002Fpython\u002F.harness\u002Fskills\u002Fexample-skill\u002FSKILL.md",[74],{"categoryNo":61,"categoryName":62,"taxonomyType":63,"taxonomyTypeDesc":64},[66,67,68,69],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":88,"publishedAt":28},"01M6QVBP9NC2T2D6JP8V8A8RNY","publish-polish","Final audit and polish workflow for converting a personal Python project into a publication-ready open-source GitHub repository. Checks security and privacy (including git history), code quality, documentation, packaging metadata, and repo hygiene, then produces a structured readiness report with prioritized findings. Invoke before making a private repo public or before a first release.","https:\u002F\u002Fgithub.com\u002Fjoe-salamy\u002Fharness-loadouts\u002Fblob\u002Fmain\u002F.omp\u002Fskills\u002Fpublish-polish\u002FSKILL.md",[82,83],{"categoryNo":61,"categoryName":62,"taxonomyType":63,"taxonomyTypeDesc":64},{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[89,90,91,92,93,94,95,96,97,98,99,23,100,101,102,103,104,105,106,107],"publish polish","polish","publish","packaging","documentation","cleanup","code","release","git","open source","audit","open","reviewer","go","ready","project","python project","invoke","workflow",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":28},"01M6QVBD4V3J6Z7KDGJ8C0M5YF","merge-conflict-resolver","Resolves merge conflicts inside a temporary integration worktree created by the workflow script, preserves approved plan intent and latest base behavior, and writes a conflict-resolution summary without committing.","https:\u002F\u002Fgithub.com\u002Fjoe-salamy\u002Fharness-loadouts\u002Fblob\u002Fmain\u002F.omp\u002Fskills\u002Fmerge-conflict-resolver\u002FSKILL.md",[],[115,116,117,118,119,120,107,121,122,123,124,125,126,127,128,129,130,131,132],"resolver","merge conflict resolver","conflict","conflict resolver","merge","behavior","worktree","integration","plan","merge conflicts","conflicts","intent","summary","base","resolution","script","latest","conflict-resolution",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":28},"01M6QVB7EW7GQEAJGD8NRXFEGF","implement-worktree","Implements an approved Markdown plan inside the current script-created git worktree, verifies the result, commits the implementation, and writes a handoff summary for audit.","https:\u002F\u002Fgithub.com\u002Fjoe-salamy\u002Fharness-loadouts\u002Fblob\u002Fmain\u002F.omp\u002Fskills\u002Fimplement-worktree\u002FSKILL.md",[],[140,141,121,142,123,143,127,130,144,145,146,147,99,97,148],"implement worktree","implement","handoff","implementation","for","result","markdown","commits","git worktree",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":158,"publishedAt":28},"01M6QVB39PTXV6EGH64H4Y826G","cleanup-dead-code","Dead Code Cleanup for Python (using Vulture)","https:\u002F\u002Fgithub.com\u002Fjoe-salamy\u002Fharness-loadouts\u002Fblob\u002Fmain\u002F.omp\u002Fskills\u002Fcleanup-dead-code\u002FSKILL.md",[155],{"categoryNo":156,"categoryName":157,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000030","开发工程师",[94,95,159,160,144,161,162],"dead code","cleanup dead code","code cleanup","python"]