[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71SVDBEWN6H1RJCPV06900X":3,"skill-same:01M71SVDBEWN6H1RJCPV06900X":64},{"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":23,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":63},"01M71SVDBEWN6H1RJCPV06900X","using-orc",null,"orc's iron rules, instruction priority, and skill-routing discipline. Injected at every SessionStart; required reading before your first action.","HigorAlves\u002Forc","HigorAlves","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F11262976?v=4","01M71S79EZEMHZ8PQSV0XQJHYY","Higor Alves","01M71S79FKKTCHCN1EDR8DSTWQ",7,"MIT","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fusing-orc\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34],"using orc","true","false","Rules","routing","iron","first","discipline","at","reading","action","2026-11-10 13:02:02",false,"---\nname: using-orc\ndescription: orc's iron rules, instruction priority, and skill-routing discipline. Injected at every SessionStart; required reading before your first action.\ndisable-model-invocation: true\nuser-invocable: false\n---\n\n\u003CSUBAGENT-STOP>\nIf you were dispatched as a subagent to execute a specific task, skip this skill.\n\u003C\u002FSUBAGENT-STOP>\n\n\u003CEXTREMELY-IMPORTANT>\nIf there is even a 1% chance an orc skill applies, you MUST invoke it with the `Skill` tool — not optional, and you cannot rationalize past it. Check for a relevant skill BEFORE responding, before clarifying questions, and before exploring the codebase: \"it's just a quick question\" and \"let me explore first\" are rationalizations — questions are tasks. Announce \"Using [skill] to [purpose]\", then follow it. If an invoked skill turns out wrong for the situation, you don't have to use it.\n\u003C\u002FEXTREMELY-IMPORTANT>\n\n## Instruction priority\n\n1. **User instructions** (CLAUDE.md, direct requests) — always win.\n2. **orc skills** — override default system behavior where they conflict.\n3. **Default system prompt** — lowest.\n\nInstructions say WHAT, not HOW: \"Add X\" \u002F \"Fix Y\" never means skip the workflow.\n\n## Accessing skills\n\nUse the `Skill` tool — never `Read` a skill file. Every skill's description is already loaded; invoke the one that fits.\n\n## Iron rules\n\n1. **No commits to main\u002Fmaster\u002Fdevelop** — branch first; check the branch before any commit. The PreToolUse hook downgrades protected-branch commits\u002Fpushes to a confirm prompt — approve it only with explicit user consent.\n2. **No code without a failing test** — write it, watch it fail, then implement. → `orc:tdd`\n3. **No claim without verification** — run it, read the output, then claim the result. → `orc:verification-before-completion`\n4. **No fix without root cause** — find why it's broken before changing code. → `orc:systematic-debugging`\n5. **No AI attribution** — never reference Claude\u002FAI\u002Fautomation, and never add `Co-Authored-By` trailers, in code, commits, or PRs. The PreToolUse hook blocks it.\n6. **No multi-phase work without `.orc\u002F` state** — register and checkpoint via `orc-state` after every phase (schema + rules: `orc:state-protocol`), so `\u002Forc:resume` survives interruption.\n7. **No silent broadcast in workspace mode** — when the SessionStart banner says `workspace[…]`, repo-touching commands need an explicit `--repos` \u002F `--repo` \u002F `--all-repos` \u002F `--this-repo` or a confirming `AskUserQuestion`. → `orc:workspace-mode`\n8. **No PR over the size budget without a recorded choice** — default **300 LOC** (additions+deletions, post-exclusion); over budget → stack \u002F open-big with a `Size-budget-override:` trailer \u002F abort. → `orc:pr-size-budget`. A web change → browser QA with `.orc\u002F\u003Cbranch>\u002Ffiles\u002Fqa\u002F` artifacts, no exceptions. → `orc:qa` (drives `orc:agent-browser`)\n\n## Gate taxonomy (interaction policy)\n\nGates come in three classes. **Hard-outward** — anything writing to a tracker, posting a PR review, or publishing evidence: always asks; no flag or policy skips it. **Soft-inward** — decisions about the user's own working tree (plan approval, driver choice, PR compose): convertible to pre-approved defaults by the `interaction_policy` autopilot ladder (`manual` | `guided` | `auto`, via userConfig or `--auto`; banner shows the resolved level). **Escalation-only** — never asked proactively; always stop the run when triggered (implementer escalations, env failures, criteria misses), at every policy level. How every gate is rendered (header chips, Recommended-first, `preview`, multiSelect chunking): → `orc:gates`\n\n## Skill routing\n\n- **Process skills first** — `orc:systematic-debugging`, `orc:tdd`, `orc:verification-before-completion` decide HOW to approach a task; implementation skills come second.\n- **Rigid** skills (tdd, systematic-debugging, verification) — follow exactly. **Flexible** skills — adapt the principles. The skill itself tells you which.\n- Stack packs (skills auto-surface via their own descriptions; these just group them by stack, load on demand): **web-react** · **backend** · **ios** · **workflow-extras**.\n\n## Insights & callouts\n\nWhen writing substantive code, surface 2–3 brief, codebase-specific notes as emoji-header blockquotes — `> **💡 Insight**` \u002F `> **⚠️ Caution**`. → `orc:callouts`\nSame palette for must-not-miss command output: 🛑 danger, ⛔ gate, 📋 preview, ➡️ next. **Terminal output carries no `[!TYPE]` tag** (it prints as junk in the TUI); add the GitHub tag (`[!IMPORTANT]`\u002F`[!WARNING]`\u002F`[!CAUTION]`\u002F`[!NOTE]`\u002F`[!TIP]`) only in GitHub-bound output — PR bodies, review comments, committed docs.\n","\u003CSUBAGENT-STOP>\nIf you were dispatched as a subagent to execute a specific task, skip this skill.\n\u003C\u002FSUBAGENT-STOP>\n\n\u003CEXTREMELY-IMPORTANT>\nIf there is even a 1% chance an orc skill applies, you MUST invoke it with the `Skill` tool — not optional, and you cannot rationalize past it. Check for a relevant skill BEFORE responding, before clarifying questions, and before exploring the codebase: \"it's just a quick question\" and \"let me explore first\" are rationalizations — questions are tasks. Announce \"Using [skill] to [purpose]\", then follow it. If an invoked skill turns out wrong for the situation, you don't have to use it.\n\u003C\u002FEXTREMELY-IMPORTANT>\n\n## Instruction priority\n\n1. **User instructions** (CLAUDE.md, direct requests) — always win.\n2. **orc skills** — override default system behavior where they conflict.\n3. **Default system prompt** — lowest.\n\nInstructions say WHAT, not HOW: \"Add X\" \u002F \"Fix Y\" never means skip the workflow.\n\n## Accessing skills\n\nUse the `Skill` tool — never `Read` a skill file. Every skill's description is already loaded; invoke the one that fits.\n\n## Iron rules\n\n1. **No commits to main\u002Fmaster\u002Fdevelop** — branch first; check the branch before any commit. The PreToolUse hook downgrades protected-branch commits\u002Fpushes to a confirm prompt — approve it only with explicit user consent.\n2. **No code without a failing test** — write it, watch it fail, then implement. → `orc:tdd`\n3. **No claim without verification** — run it, read the output, then claim the result. → `orc:verification-before-completion`\n4. **No fix without root cause** — find why it's broken before changing code. → `orc:systematic-debugging`\n5. **No AI attribution** — never reference Claude\u002FAI\u002Fautomation, and never add `Co-Authored-By` trailers, in code, commits, or PRs. The PreToolUse hook blocks it.\n6. **No multi-phase work without `.orc\u002F` state** — register and checkpoint via `orc-state` after every phase (schema + rules: `orc:state-protocol`), so `\u002Forc:resume` survives interruption.\n7. **No silent broadcast in workspace mode** — when the SessionStart banner says `workspace[…]`, repo-touching commands need an explicit `--repos` \u002F `--repo` \u002F `--all-repos` \u002F `--this-repo` or a confirming `AskUserQuestion`. → `orc:workspace-mode`\n8. **No PR over the size budget without a recorded choice** — default **300 LOC** (additions+deletions, post-exclusion); over budget → stack \u002F open-big with a `Size-budget-override:` trailer \u002F abort. → `orc:pr-size-budget`. A web change → browser QA with `.orc\u002F\u003Cbranch>\u002Ffiles\u002Fqa\u002F` artifacts, no exceptions. → `orc:qa` (drives `orc:agent-browser`)\n\n## Gate taxonomy (interaction policy)\n\nGates come in three classes. **Hard-outward** — anything writing to a tracker, posting a PR review, or publishing evidence: always asks; no flag or policy skips it. **Soft-inward** — decisions about the user's own working tree (plan approval, driver choice, PR compose): convertible to pre-approved defaults by the `interaction_policy` autopilot ladder (`manual` | `guided` | `auto`, via userConfig or `--auto`; banner shows the resolved level). **Escalation-only** — never asked proactively; always stop the run when triggered (implementer escalations, env failures, criteria misses), at every policy level. How every gate is rendered (header chips, Recommended-first, `preview`, multiSelect chunking): → `orc:gates`\n\n## Skill routing\n\n- **Process skills first** — `orc:systematic-debugging`, `orc:tdd`, `orc:verification-before-completion` decide HOW to approach a task; implementation skills come second.\n- **Rigid** skills (tdd, systematic-debugging, verification) — follow exactly. **Flexible** skills — adapt the principles. The skill itself tells you which.\n- Stack packs (skills auto-surface via their own descriptions; these just group them by stack, load on demand): **web-react** · **backend** · **ios** · **workflow-extras**.\n\n## Insights & callouts\n\nWhen writing substantive code, surface 2–3 brief, codebase-specific notes as emoji-header blockquotes — `> **💡 Insight**` \u002F `> **⚠️ Caution**`. → `orc:callouts`\nSame palette for must-not-miss command output: 🛑 danger, ⛔ gate, 📋 preview, ➡️ next. **Terminal output carries no `[!TYPE]` tag** (it prints as junk in the TUI); add the GitHub tag (`[!IMPORTANT]`\u002F`[!WARNING]`\u002F`[!CAUTION]`\u002F`[!NOTE]`\u002F`[!TIP]`) only in GitHub-bound output — PR bodies, review comments, committed docs.\n",{"name":5,"description":7,"user-invocable":36,"disable-model-invocation":40},true,"main","7522fd7266944e30052204c2f6df287d8b5516be","orc\u002Fskills\u002Fusing-orc",0,"https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc","https:\u002F\u002Forc.novacstack.com\u002F","https:\u002F\u002Fgithub.com\u002FHigorAlves","higoralves.dev","Software Engineering","2026-11-07 07:26:38",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":40},[53,56,59],{"tool":54,"command":55},"npx","npx skills add HigorAlves\u002Forc --skill using-orc",{"tool":57,"command":58},"bunx","bunx skills add HigorAlves\u002Forc --skill using-orc",{"tool":60,"command":61},"pnpm","pnpm dlx skills add HigorAlves\u002Forc --skill using-orc","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fusing-orc\u002FSKILL.md",[],[65,103,127,148,170,189],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":82,"publishedAt":35},"01M71SW40F9TAAEDKBYYBCM814","writing-plans","Write a comprehensive implementation plan of bite-sized TDD tasks that an engineer with zero codebase context could execute — exact files, code, tests, and verification steps","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[71,74,79],{"categoryNo":72,"categoryName":73,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":80,"categoryName":81,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000036","内容创作者",[83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102],"writing","writing plans","plans","engineer","superpowers","implementation plan","files","when","you","code","tasks","verification","plan","write","steps","context","ZeRO","for","tests","use",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":112,"publishedAt":35},"01M71SW15KHE4MHJW9NEXV65X2","writing-for-agents","orc's doctrine layer for writing any document an agent consumes — skills, AGENTS.md\u002FCLAUDE.md, reference docs","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[109,110,111],{"categoryNo":72,"categoryName":73,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":80,"categoryName":81,"taxonomyType":77,"taxonomyTypeDesc":78},[113,83,100,114,90,115,116,117,118,119,120,121,102,122,123,124,125,126],"writing for agents","matt pocock","inline","tuning","a skill","layer","doctrine","push","editing","document","github","https","reference","docs",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":134,"publishedAt":35},"01M71SVYQKXT743HHHWGHT3G13","workspace-mode","Use when cwd is a parent dir holding multiple sibling git repos — defines repo auto-detection, --repos\u002F--repo\u002F--all-repos\u002F--this-repo precedence, per-repo dispatch, and linked-PR mechanics.","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fworkspace-mode\u002FSKILL.md",[133],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[135,136,137,138,139,90,140,141,142,143,102,144,145,146,147],"workspace mode","mode","workspace","mechanics","auto","repos","git","pr","repo","dispatch","auto-detection","detection","parent",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":155,"publishedAt":35},"01M71SVVP3BXS06G9395P2K0RH","wizard","Generate an interactive bash wizard walking a human through work only they can perform — credentials, secrets, one-off migrations","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fwizard\u002FSKILL.md",[154],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[150,156,157,158,159,114,90,160,161,162,163,164,165,97,166,167,100,102,168,169],"condition","never","provisioning infrastructure","only","Bash","work","credentials","generate","human","secrets","infrastructure","do","one","interactive",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":35},"01M71SVT4AR6NKAM5B077E7QSJ","wait-what","Stop and re-pitch — the last message did not land; say it again simply, in the project's own vocabulary.","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[177,178,179,180,25,114,181,182,183,184,123,124,185,186,187,188],"wait what","wait","project","re","pitch","last","say","message","land","it","stop","vocabulary",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":199,"publishedAt":35},"01M71SVQVYRA9QBQ6G8MWR8G6F","vitest","Vitest fast unit testing framework powered by Vite with Jest-compatible API","https:\u002F\u002Fgithub.com\u002FHigorAlves\u002Forc\u002Fblob\u002Fmain\u002Forc\u002Fskills\u002Fvitest\u002FSKILL.md",[195,198],{"categoryNo":196,"categoryName":197,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},[191,200,201,202,203,204,83,90,205,206,207,32,208,209,210,211,212,213,101,214],"coverage","unit","testing","testing framework","generated","api","jest","2026","scripts","unit testing","antfu","framework","vite","mocking","dev"]