[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MQV1RT7MWTWVB35RD0B97J":3,"skill-same:01M6MQV1RT7MWTWVB35RD0B97J":66},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":51,"install":52,"resources":65},"01M6MQV1RT7MWTWVB35RD0B97J","delegate-evidence",null,"Use when the delegate-routing skill seems not to work, or before stating how Claude, Codex, Kiro or Kimchi actually behave: delegation, nesting, model or effort reach, system prompts, worktrees, hooks. Answer from the delegate map or the acceptance suite, never from memory.","higherorderfunctor\u002Fnix-agentic-tools","higherorderfunctor","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34926636?v=4","01M6MQT3TQS16N1CBRZJYR2EMB","Christopher Aubut","01M6MQT419AF9ERC87M87NRXQV",2,"Unlicense","https:\u002F\u002Fgithub.com\u002Fhigherorderfunctor\u002Fnix-agentic-tools\u002Fblob\u002Fmain\u002Fdev\u002Fskills\u002Fdelegate-evidence\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"delegate evidence","delegate","evidence","use","when","answer","kiro","map","behave","worktrees","hooks","never","codex","work","model","system","how","acceptance","delegation","routing","memory","2026-11-10 10:12:30",false,"---\nname: delegate-evidence\ndescription: >-\n  Use when the delegate-routing skill seems not to work, or before stating how\n  Claude, Codex, Kiro or Kimchi actually behave: delegation, nesting, model or\n  effort reach, system prompts, worktrees, hooks. Answer from the delegate map\n  or the acceptance suite, never from memory.\n---\n\n# Delegate evidence\n\nTwo sources answer questions about harness behavior. Use them instead of memory.\n\n## The map: how each harness behaves\n\n`packages\u002Fdelegate-routing\u002Fdocs\u002Fdelegates\u002F` holds the map. Start at its\n`README.md`. Every fact cell carries an evidence mark and a case id, such as\n`claude:depth`. `evidence.md` lists the pinned versions and the open unknowns.\n\nTo rerun a row, give its case id to the runner. It reads the case tables in\n`packages\u002Fdelegate-routing\u002Fprobes\u002Fdelegates\u002F\u003Charness>\u002FREADME.md`, runs each\ncommand and greps its output for the expected excerpt:\n\n```bash\nrun=packages\u002Fdelegate-routing\u002Fprobes\u002Fdelegates\u002Frun.py\npython3 \"$run\" --list                              # every id, runnable or why not\npython3 \"$run\" --only=kimchi\u002Fclaude:s1-fg-pins     # one case: \u003Charness>\u002F\u003Ccase id>\npython3 \"$run\" --only='claude:dmu_*,codex\u002Fcodex:R1.*'  # bare id or prefix*\n```\n\nIt prints MATCH, MISMATCH or SKIP per case and exits with the MISMATCH count.\nLIVE cases run only with `--live`. Its docstring holds the case-table format a\nnew row must follow.\n\n## The acceptance suite: does the skill route correctly\n\n`packages\u002Fdelegate-routing\u002Feval\u002F` runs real sessions on Claude, Codex, Kiro and\nKimchi and checks what the explicit suite configuration makes an agent do. Its\nfixtures enable their own runtimes and routing; personal `devenv.local.nix` is\noutside those inputs. Validate every case and print each launch without starting\nanything:\n\n```bash\npython3 packages\u002Fdelegate-routing\u002Feval\u002Fsuite.py --dry-run\n```\n\nA live run spends model turns on the operator's logins, so the operator runs it.\n`--list` prints the case ids; `--only=\u003Cid>[,\u003Cid>|\u003Cprefix>*]`, `--case \u003Cid>` or\n`--harness \u003Cname>` narrows a run; `eval\u002FREADME.md` lists the operator steps.\n\n## Rules\n\n- Make no claim about harness behavior without a map row or a run. If the map\n  lacks it, add a case to that harness's probe directory and run it.\n- Run login-free cases yourself. Cases marked OFFLINE, fake-provider or\n  capture-mock cases need no account.\n- For a case that needs a login, an account or a paid turn, give the operator a\n  numbered list of steps: the setup, the exact command, and what output to send\n  back.\n\n## When the operator reports the skill misbehaving\n\n1. Give the operator the `suite.py --only=\u003Cid>` command for the reported\n   behavior's cases.\n2. Run the map rows behind the failing behavior, to see what the harness really\n   does at the pinned version.\n3. Fix the skill, the configuration, or the map.\n4. Report what the evidence showed, citing the case ids and outputs.\n","# Delegate evidence\n\nTwo sources answer questions about harness behavior. Use them instead of memory.\n\n## The map: how each harness behaves\n\n`packages\u002Fdelegate-routing\u002Fdocs\u002Fdelegates\u002F` holds the map. Start at its\n`README.md`. Every fact cell carries an evidence mark and a case id, such as\n`claude:depth`. `evidence.md` lists the pinned versions and the open unknowns.\n\nTo rerun a row, give its case id to the runner. It reads the case tables in\n`packages\u002Fdelegate-routing\u002Fprobes\u002Fdelegates\u002F\u003Charness>\u002FREADME.md`, runs each\ncommand and greps its output for the expected excerpt:\n\n```bash\nrun=packages\u002Fdelegate-routing\u002Fprobes\u002Fdelegates\u002Frun.py\npython3 \"$run\" --list                              # every id, runnable or why not\npython3 \"$run\" --only=kimchi\u002Fclaude:s1-fg-pins     # one case: \u003Charness>\u002F\u003Ccase id>\npython3 \"$run\" --only='claude:dmu_*,codex\u002Fcodex:R1.*'  # bare id or prefix*\n```\n\nIt prints MATCH, MISMATCH or SKIP per case and exits with the MISMATCH count.\nLIVE cases run only with `--live`. Its docstring holds the case-table format a\nnew row must follow.\n\n## The acceptance suite: does the skill route correctly\n\n`packages\u002Fdelegate-routing\u002Feval\u002F` runs real sessions on Claude, Codex, Kiro and\nKimchi and checks what the explicit suite configuration makes an agent do. Its\nfixtures enable their own runtimes and routing; personal `devenv.local.nix` is\noutside those inputs. Validate every case and print each launch without starting\nanything:\n\n```bash\npython3 packages\u002Fdelegate-routing\u002Feval\u002Fsuite.py --dry-run\n```\n\nA live run spends model turns on the operator's logins, so the operator runs it.\n`--list` prints the case ids; `--only=\u003Cid>[,\u003Cid>|\u003Cprefix>*]`, `--case \u003Cid>` or\n`--harness \u003Cname>` narrows a run; `eval\u002FREADME.md` lists the operator steps.\n\n## Rules\n\n- Make no claim about harness behavior without a map row or a run. If the map\n  lacks it, add a case to that harness's probe directory and run it.\n- Run login-free cases yourself. Cases marked OFFLINE, fake-provider or\n  capture-mock cases need no account.\n- For a case that needs a login, an account or a paid turn, give the operator a\n  numbered list of steps: the setup, the exact command, and what output to send\n  back.\n\n## When the operator reports the skill misbehaving\n\n1. Give the operator the `suite.py --only=\u003Cid>` command for the reported\n   behavior's cases.\n2. Run the map rows behind the failing behavior, to see what the harness really\n   does at the pinned version.\n3. Fix the skill, the configuration, or the map.\n4. Report what the evidence showed, citing the case ids and outputs.\n",{"name":5,"description":7},"main","a33b4e70efef03fe75378fad9c847b73ea142c46","dev\u002Fskills\u002Fdelegate-evidence",0,"https:\u002F\u002Fgithub.com\u002Fhigherorderfunctor\u002Fnix-agentic-tools","https:\u002F\u002Fgithub.com\u002Fhigherorderfunctor","2026-11-13 03:39:17",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add higherorderfunctor\u002Fnix-agentic-tools --skill delegate-evidence",{"tool":58,"command":59},"bunx","bunx skills add higherorderfunctor\u002Fnix-agentic-tools --skill delegate-evidence",{"tool":61,"command":62},"pnpm","pnpm dlx skills add higherorderfunctor\u002Fnix-agentic-tools --skill delegate-evidence","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhigherorderfunctor\u002Fnix-agentic-tools\u002Fblob\u002Fmain\u002Fdev\u002Fskills\u002Fdelegate-evidence\u002FSKILL.md",true,[],[67,97,124,143,162,177],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":78,"publishedAt":40},"01M6MQXHSDNFXSN7TT5FFWPF3X","stack-test","Use when you need to run tests or formatters across commits in a stack. Use INSTEAD of manual git test run or looping git checkout + test. Prevents: testing every commit when only the tip has to pass, unbounded parallel jobs exhausting memory, cache misunderstandings.","https:\u002F\u002Fgithub.com\u002Fhigherorderfunctor\u002Fnix-agentic-tools\u002Fblob\u002Fmain\u002Fpackages\u002Fstacked-workflows\u002Fskills\u002Fstack-test\u002FSKILL.md",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[79,80,81,82,83,84,85,39,86,87,88,89,90,22,91,92,93,94,95,96,23],"test","stack","stack test","parallel","TIP","checkout","commits","manual","testing","fix","tests","only","false","you","cache","commit","across","command",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":40},"01M6MQXAXVWG1RY9H2116G4SVX","stack-summary","Use when you need to audit, analyze, or review stack quality before restructuring. Produces a structured summary with per-commit classification, philosophy audit, and violation flags. Output feeds directly into \u002Fstack-plan restructure mode. Use INSTEAD of manual git log inspection.","https:\u002F\u002Fgithub.com\u002Fhigherorderfunctor\u002Fnix-agentic-tools\u002Fblob\u002Fmain\u002Fpackages\u002Fstacked-workflows\u002Fskills\u002Fstack-summary\u002FSKILL.md",[],[80,104,105,106,107,108,86,109,110,22,91,92,111,94,112,113,114,115,116,117,118,23,119,120,121,122,123],"stack summary","summary","feeds","review stack","for","mode","classification","git log","log","review","output","analyze","with","philosophy","inspection","plan","worktree","audit","flags","git",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":40},"01M6MQX62HMQR5CSN4FSC95ZJC","stack-submit","Use when you need to push, submit, or create pull requests for a commit stack. Rebases only the current stack onto upstream main, validates, and pushes INSTEAD of manual git sync + git submit + PR\u002FMR creation. Handles branch creation, stacked PR\u002FMR creation with correct base branches.","https:\u002F\u002Fgithub.com\u002Fhigherorderfunctor\u002Fnix-agentic-tools\u002Fblob\u002Fmain\u002Fpackages\u002Fstacked-workflows\u002Fskills\u002Fstack-submit\u002FSKILL.md",[],[131,80,132,133,134,135,136,137,108,86,138,139,140,90,45,22,91,141,142,23],"submit","stack submit","pull","branch","push","pr","creation","correct","upstream","branches","git sync","mr",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":40},"01M6MQX2BNQ4MAV9KCV0RZ734G","stack-split","Use when you need to break up, split, or decompose a large commit into smaller atomic commits. Use INSTEAD of manual git rebase -i + edit or git reset HEAD^. Prevents: non-working intermediate commits, wrong split ordering, missed downstream restack.","https:\u002F\u002Fgithub.com\u002Fhigherorderfunctor\u002Fnix-agentic-tools\u002Fblob\u002Fmain\u002Fpackages\u002Fstacked-workflows\u002Fskills\u002Fstack-split\u002FSKILL.md",[],[150,80,151,152,85,86,153,22,91,154,92,94,155,156,157,158,159,160,123,161,23],"split","stack split","decompose","up","atomic commits","reset","head","missed","break","atomic","edit","rebase",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":40},"01M6MQWWM5P7FVQSF7EWHJ70C6","stack-plan","Use when you need to plan commits, restructure a stack, or commit uncommitted work as organized atomic commits. Builds a stack from a description, uncommitted work, or existing commits INSTEAD of dumping everything into one monolithic commit with git add -A && git commit, or manual git rebase -i, git reset --soft, or ad-hoc git move sequences. Prevents: wrong commit ordering, forward references, git move -F panics, untested intermediates.","https:\u002F\u002Fgithub.com\u002Fhigherorderfunctor\u002Fnix-agentic-tools\u002Fblob\u002Fmain\u002Fpackages\u002Fstacked-workflows\u002Fskills\u002Fstack-plan\u002FSKILL.md",[],[80,119,169,170,171,85,108,172,86,173,22,174,91,154,92,94,175,155,116,176,23],"stack plan","tree","as","move","git commit","Existing","git move","references",{"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":183,"publishedAt":40},"01M6MQWP7CKTM5NF72MED1H8NS","stack-fix","Use when you need to fix, correct, or update content in an earlier commit — line-level edits, content moves, or structural changes. Absorbs staged changes into correct stack commits INSTEAD of running git absorb or git commit --fixup via Bash, or hand-running git prev + edit + git amend + git restack --merge. Prevents: missed dry-run preview, leftover staged changes going unnoticed, forgetting to restack. Falls back to guided manual amend when absorb cannot route hunks.","https:\u002F\u002Fgithub.com\u002Fhigherorderfunctor\u002Fnix-agentic-tools\u002Fblob\u002Fmain\u002Fpackages\u002Fstacked-workflows\u002Fskills\u002Fstack-fix\u002FSKILL.md",[],[88,80,184,185,85,86,138,186,173,22,91,92,187,188,94,189,190,191,192,23],"stack fix","back","structural","Bash","preview","hand","dry","route","running"]