[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75M9TH050T581P38T18MP53":3,"skill-same:01M75M9TH050T581P38T18MP53":56},{"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":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":13,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M75M9TH050T581P38T18MP53","reference-pack",null,"Reference skill demonstrating the 10\u002F10 skillpack contract. Adds a \"what does this skillpack do\" answer to the user's agent.","Sigmacodeat\u002FSigmabrain","Sigmacodeat","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F220578687?v=4","01M75M8ZBH9439AFP2NTF8K98S","01M75M8ZC680S4377SFWSKP0D1",0,"MIT","https:\u002F\u002Fgithub.com\u002FSigmacodeat\u002FSigmabrain\u002Fblob\u002Fmain\u002Fexamples\u002Fskillpack-reference\u002Fskills\u002Freference-pack\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: reference-pack\ndescription: Reference skill demonstrating the 10\u002F10 skillpack contract. Adds a \"what does this skillpack do\" answer to the user's agent.\nmutating: false\ntriggers:\n  - what is the reference skillpack\n  - show me the reference skill\n  - explain the skillpack contract\n  - what's a 10\u002F10 skillpack\n  - how do third-party skillpacks work\n---\n\n# reference-pack\n\nThis is the canonical reference for a third-party gbrain skillpack. Read\nits tree once and you know how to author one.\n\n## What this skill does\n\nWhen the user asks how third-party gbrain skillpacks work, this skill\npoints them at the four artifacts every pack ships:\n\n- `skillpack.json` — declares pack metadata + which artifacts the\n  doctor scores (skills, unit_tests, e2e_tests, llm_evals, routing_evals,\n  runbooks, changelog).\n- `skills\u002F\u003Cname>\u002FSKILL.md` — frontmatter (name, description, mutating,\n  triggers) plus markdown body. Agents route on `triggers:`; the body\n  is the in-context instruction set.\n- `runbooks\u002Fbootstrap.md` — agent-readable post-scaffold steps. gbrain\n  DISPLAYS this after `scaffold` lands; the agent walks per-step at\n  its own discretion. No auto-executor (codex T1 supply-chain hardening).\n- `CHANGELOG.md` — Keep-a-Changelog shape. The doctor's `changelog_\n  present_and_current` dimension fails if there's no `## [\u003Cversion>]`\n  entry matching the manifest's `version`.\n\n## What the doctor scores\n\nTen binary dimensions, split into:\n\n**Core (5; must all pass to publish at any tier):**\n\n1. `manifest_valid` — schema-validates skillpack.json\n2. `skills_have_skill_md` — every listed skill has SKILL.md with\n   name \u002F description \u002F triggers\n3. `routing_evals_present` — each skill has routing-eval.jsonl with\n   >= 5 intents\n4. `skills_have_unique_triggers` — MECE at the pack level\n5. `changelog_present_and_current` — CHANGELOG entry for current version\n\n**Quality badges (5; earn for tier eligibility):**\n\n6. `unit_tests_present` — manifest.unit_tests matches >= 1 file\n7. `e2e_tests_present` — manifest.e2e_tests matches >= 1 file\n8. `llm_eval_present` — `*.judge.json` with >= 3 cases\n9. `bootstrap_runbook_present` — non-empty runbooks\u002Fbootstrap.md\n10. `license_present` — LICENSE \u002F LICENSE.md \u002F LICENSE.txt non-empty\n\nTier eligibility:\n\n- `endorsed` — all 10 (gates: Garry's `endorsements.json` overlay\n  in the registry)\n- `community` — all 5 core + >= 3 of 5 badges (default tier on PR\n  merge)\n- `experimental` — all 5 core + \u003C 3 badges\n- `blocked` — any core fails\n\nRun `gbrain skillpack doctor \u003Cpack-dir>` to see exactly which\ndimensions a candidate pack passes and the paste-ready fix for each\nfailure. `--fix --yes` auto-scaffolds the dimensions flagged\n`auto_fixable: true` (routing-eval stubs, CHANGELOG entries,\nlicense stub, bootstrap stub, test stubs).\n\n## How agents use this skill\n\nThe triggers above route any \"what is a skillpack\" \u002F \"how do third-\nparty packs work\" user phrasing to THIS skill. The agent reads the\nmarkdown body, then either answers the user's question directly or\ncalls `gbrain skillpack info \u003Cname>` \u002F `search \u003Cquery>` for live\nregistry data.\n\n## Test + eval coverage\n\n- `test\u002Fexample.test.ts` — unit test that imports the skill helper\n  (stub; replace with real assertions).\n- `e2e\u002Fexample.e2e.test.ts` — integration test gated on DATABASE_URL.\n- `evals\u002Freference-pack.judge.json` — LLM-judge eval scoring this\n  skill's output against the \"does it actually teach the contract\"\n  bar across happy-path \u002F edge \u002F failure-mode cases.\n- `skills\u002Freference-pack\u002Frouting-eval.jsonl` — five phrasings users\n  ask, all mapped to `expected_skill: reference-pack`.\n\n## Author's checklist\n\nBefore pushing, the publisher runs:\n\n```\ngbrain skillpack doctor . --quick --json\ngbrain skillpack pack\n```\n\nThe first hits the rubric and prints paste-ready fixes for any failed\ndimension. The second emits `reference-pack-\u003Cversion>.tgz` with a\ndeterministic SHA-256 the publisher submits to the registry PR.\n","# reference-pack\n\nThis is the canonical reference for a third-party gbrain skillpack. Read\nits tree once and you know how to author one.\n\n## What this skill does\n\nWhen the user asks how third-party gbrain skillpacks work, this skill\npoints them at the four artifacts every pack ships:\n\n- `skillpack.json` — declares pack metadata + which artifacts the\n  doctor scores (skills, unit_tests, e2e_tests, llm_evals, routing_evals,\n  runbooks, changelog).\n- `skills\u002F\u003Cname>\u002FSKILL.md` — frontmatter (name, description, mutating,\n  triggers) plus markdown body. Agents route on `triggers:`; the body\n  is the in-context instruction set.\n- `runbooks\u002Fbootstrap.md` — agent-readable post-scaffold steps. gbrain\n  DISPLAYS this after `scaffold` lands; the agent walks per-step at\n  its own discretion. No auto-executor (codex T1 supply-chain hardening).\n- `CHANGELOG.md` — Keep-a-Changelog shape. The doctor's `changelog_\n  present_and_current` dimension fails if there's no `## [\u003Cversion>]`\n  entry matching the manifest's `version`.\n\n## What the doctor scores\n\nTen binary dimensions, split into:\n\n**Core (5; must all pass to publish at any tier):**\n\n1. `manifest_valid` — schema-validates skillpack.json\n2. `skills_have_skill_md` — every listed skill has SKILL.md with\n   name \u002F description \u002F triggers\n3. `routing_evals_present` — each skill has routing-eval.jsonl with\n   >= 5 intents\n4. `skills_have_unique_triggers` — MECE at the pack level\n5. `changelog_present_and_current` — CHANGELOG entry for current version\n\n**Quality badges (5; earn for tier eligibility):**\n\n6. `unit_tests_present` — manifest.unit_tests matches >= 1 file\n7. `e2e_tests_present` — manifest.e2e_tests matches >= 1 file\n8. `llm_eval_present` — `*.judge.json` with >= 3 cases\n9. `bootstrap_runbook_present` — non-empty runbooks\u002Fbootstrap.md\n10. `license_present` — LICENSE \u002F LICENSE.md \u002F LICENSE.txt non-empty\n\nTier eligibility:\n\n- `endorsed` — all 10 (gates: Garry's `endorsements.json` overlay\n  in the registry)\n- `community` — all 5 core + >= 3 of 5 badges (default tier on PR\n  merge)\n- `experimental` — all 5 core + \u003C 3 badges\n- `blocked` — any core fails\n\nRun `gbrain skillpack doctor \u003Cpack-dir>` to see exactly which\ndimensions a candidate pack passes and the paste-ready fix for each\nfailure. `--fix --yes` auto-scaffolds the dimensions flagged\n`auto_fixable: true` (routing-eval stubs, CHANGELOG entries,\nlicense stub, bootstrap stub, test stubs).\n\n## How agents use this skill\n\nThe triggers above route any \"what is a skillpack\" \u002F \"how do third-\nparty packs work\" user phrasing to THIS skill. The agent reads the\nmarkdown body, then either answers the user's question directly or\ncalls `gbrain skillpack info \u003Cname>` \u002F `search \u003Cquery>` for live\nregistry data.\n\n## Test + eval coverage\n\n- `test\u002Fexample.test.ts` — unit test that imports the skill helper\n  (stub; replace with real assertions).\n- `e2e\u002Fexample.e2e.test.ts` — integration test gated on DATABASE_URL.\n- `evals\u002Freference-pack.judge.json` — LLM-judge eval scoring this\n  skill's output against the \"does it actually teach the contract\"\n  bar across happy-path \u002F edge \u002F failure-mode cases.\n- `skills\u002Freference-pack\u002Frouting-eval.jsonl` — five phrasings users\n  ask, all mapped to `expected_skill: reference-pack`.\n\n## Author's checklist\n\nBefore pushing, the publisher runs:\n\n```\ngbrain skillpack doctor . --quick --json\ngbrain skillpack pack\n```\n\nThe first hits the rubric and prints paste-ready fixes for any failed\ndimension. The second emits `reference-pack-\u003Cversion>.tgz` with a\ndeterministic SHA-256 the publisher submits to the registry PR.\n",{"name":5,"mutating":19,"triggers":23,"description":7},[24,25,26,27,28],"what is the reference skillpack","show me the reference skill","explain the skillpack contract","what's a 10\u002F10 skillpack","how do third-party skillpacks work","main","b8e699fc7cff8641b94a51ac9d4aa599fcc03ae5","examples\u002Fskillpack-reference\u002Fskills\u002Freference-pack","https:\u002F\u002Fgithub.com\u002FSigmacodeat\u002FSigmabrain","https:\u002F\u002Fsigmabrain.vercel.app","https:\u002F\u002Fgithub.com\u002FSigmacodeat","2026-07-09 09:21:55",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Sigmacodeat\u002FSigmabrain --skill reference-pack",{"tool":42,"command":43},"bunx","bunx skills add Sigmacodeat\u002FSigmabrain --skill reference-pack",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Sigmacodeat\u002FSigmabrain --skill reference-pack","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSigmacodeat\u002FSigmabrain\u002Fblob\u002Fmain\u002Fexamples\u002Fskillpack-reference\u002Fskills\u002Freference-pack\u002FSKILL.md",true,[50],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"routing-eval.jsonl","OTHER","其他",415,"https:\u002F\u002Fgithub.com\u002FSigmacodeat\u002FSigmabrain\u002Fblob\u002Fmain\u002Fexamples\u002Fskillpack-reference\u002Fskills\u002Freference-pack\u002Frouting-eval.jsonl",[57,63,69,76,83,90],{"skillNo":58,"name":59,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M75MW3405DES0348DPKVF20G","query-helper","https:\u002F\u002Fgithub.com\u002FSigmacodeat\u002FSigmabrain\u002Fblob\u002Fmain\u002Fserver\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fquery-helper\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M75MW29T3N856QPT2SK467A3","broken","https:\u002F\u002Fgithub.com\u002FSigmacodeat\u002FSigmabrain\u002Fblob\u002Fmain\u002Fserver\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbroken\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M75MVZV51CX9W3Y602M0GJR9","brain-ops","Read, enrich, and write brain pages with source attribution.","https:\u002F\u002Fgithub.com\u002FSigmacodeat\u002FSigmabrain\u002Fblob\u002Fmain\u002Fserver\u002Ftest\u002Ffixtures\u002Fskill-catalog\u002Fskills\u002Fbrain-ops\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M75MVXQAQBVNQBZPKPEBPRHV","signal-detector","Always-on ambient signal capture for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002FSigmacodeat\u002FSigmabrain\u002Fblob\u002Fmain\u002Fserver\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fsignal-detector\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M75MVWJN0EV5EFW6JMMC73XC","query","Look up brain pages in the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002FSigmacodeat\u002FSigmabrain\u002Fblob\u002Fmain\u002Fserver\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fquery\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M75MVVA7Q6PMDBTPQGT49M6M","context-now","ALWAYS-ON time-sensitivity discipline for the OpenClaw reference fixture.","https:\u002F\u002Fgithub.com\u002FSigmacodeat\u002FSigmabrain\u002Fblob\u002Fmain\u002Fserver\u002Ftest\u002Ffixtures\u002Fopenclaw-reference-minimal\u002Fskills\u002Fcontext-now\u002FSKILL.md",[],[]]