[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MJ7DPTMW985TAVZMDPMVG":3,"skill-same:01M77MJ7DPTMW985TAVZMDPMVG":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M77MJ7DPTMW985TAVZMDPMVG","model-router",null,"Recommend a model tier (Haiku \u002F Sonnet \u002F Opus) for a coding task by scoring it on scope, novelty, risk, and expected iteration. Use when the user describes a task they are about to start, or explicitly asks \"which model should I use for this\".","Temrel\u002Ftemrel-agentic-toolkit","Temrel","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F127121325?v=4","01M77MHGP6FMVMJ0PHF7VZR8ZG","01M77MHGPX5FCVTH7164SCA571",2,"MIT","https:\u002F\u002Fgithub.com\u002FTemrel\u002Ftemrel-agentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fmodel-invoked\u002Fmodel-router\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: model-router\ndescription: Recommend a model tier (Haiku \u002F Sonnet \u002F Opus) for a coding task by scoring it on scope, novelty, risk, and expected iteration. Use when the user describes a task they are about to start, or explicitly asks \"which model should I use for this\".\n---\n\n# Model router\n\nRecommend which model tier a task warrants, so routine work doesn't burn Opus-tier tokens and hard work doesn't get under-powered.\n\n## When to use this\n\n- The user describes a task they are about to start (a feature, fix, refactor, script, migration) and hasn't yet picked a model.\n- The user explicitly asks \"which model should I use for this\" or similar.\n\nNever refuse to answer. If the task description is ambiguous, score conservatively (round the uncertain axis up, not down) and say which axis is uncertain.\n\n## Scoring rubric\n\nScore the task on four axes, each 1–3:\n\n| Axis | 1 | 2 | 3 |\n| --- | --- | --- | --- |\n| **Scope** | Single-file edit | Multi-file feature | Cross-cutting refactor or greenfield system |\n| **Novelty** | Pattern exists in repo | Familiar domain, new pattern | Unfamiliar domain or algorithmically hard |\n| **Risk** | Throwaway or easily reverted | User-facing but tested | Data-touching, security-sensitive, or hard to roll back |\n| **Iteration** | Likely one-shot | A few review cycles | Long-horizon agentic session with many tool calls |\n\n## Routing rule\n\n| Total score | Recommendation |\n| --- | --- |\n| 4–6 | Haiku-tier (mechanical edits, renames, boilerplate) |\n| 7–9 | Sonnet 5 (the default; medium-effort agentic work) |\n| 10–12 | Opus-tier (high ambiguity, high risk, long horizon) |\n\n**Override:** if Risk scores 3, bump the recommendation up one tier (Haiku → Sonnet, Sonnet → Opus; Opus stays Opus).\n\n## Output format\n\nKeep the whole answer under 15 lines:\n\n1. The recommendation, first line, bolded.\n2. The four scores, one line each, with one-line reasoning per axis.\n3. The estimated relative cost multiplier vs the recommended tier if the user insists on the tier above (per-Mtok list price ratio: Haiku→Sonnet ≈ 3x, Sonnet→Opus ≈ 1.7x on input \u002F 1.7x on output; Opus→Fable ≈ 2x). If Opus is already recommended, note Fable 5 as the tier above.\n\n## Example\n\n> Task: \"Rename a config key across the repo and update the docs.\"\n\n**Recommendation: Haiku-tier** (total 5, no override)\n- Scope 2 — touches many files, but mechanically.\n- Novelty 1 — pure find-and-replace, pattern exists.\n- Risk 1 — trivially reverted in one commit.\n- Iteration 1 — one-shot with a grep to verify.\nInsisting on Sonnet 5 instead ≈ 3x the per-token cost for no quality gain.\n","# Model router\n\nRecommend which model tier a task warrants, so routine work doesn't burn Opus-tier tokens and hard work doesn't get under-powered.\n\n## When to use this\n\n- The user describes a task they are about to start (a feature, fix, refactor, script, migration) and hasn't yet picked a model.\n- The user explicitly asks \"which model should I use for this\" or similar.\n\nNever refuse to answer. If the task description is ambiguous, score conservatively (round the uncertain axis up, not down) and say which axis is uncertain.\n\n## Scoring rubric\n\nScore the task on four axes, each 1–3:\n\n| Axis | 1 | 2 | 3 |\n| --- | --- | --- | --- |\n| **Scope** | Single-file edit | Multi-file feature | Cross-cutting refactor or greenfield system |\n| **Novelty** | Pattern exists in repo | Familiar domain, new pattern | Unfamiliar domain or algorithmically hard |\n| **Risk** | Throwaway or easily reverted | User-facing but tested | Data-touching, security-sensitive, or hard to roll back |\n| **Iteration** | Likely one-shot | A few review cycles | Long-horizon agentic session with many tool calls |\n\n## Routing rule\n\n| Total score | Recommendation |\n| --- | --- |\n| 4–6 | Haiku-tier (mechanical edits, renames, boilerplate) |\n| 7–9 | Sonnet 5 (the default; medium-effort agentic work) |\n| 10–12 | Opus-tier (high ambiguity, high risk, long horizon) |\n\n**Override:** if Risk scores 3, bump the recommendation up one tier (Haiku → Sonnet, Sonnet → Opus; Opus stays Opus).\n\n## Output format\n\nKeep the whole answer under 15 lines:\n\n1. The recommendation, first line, bolded.\n2. The four scores, one line each, with one-line reasoning per axis.\n3. The estimated relative cost multiplier vs the recommended tier if the user insists on the tier above (per-Mtok list price ratio: Haiku→Sonnet ≈ 3x, Sonnet→Opus ≈ 1.7x on input \u002F 1.7x on output; Opus→Fable ≈ 2x). If Opus is already recommended, note Fable 5 as the tier above.\n\n## Example\n\n> Task: \"Rename a config key across the repo and update the docs.\"\n\n**Recommendation: Haiku-tier** (total 5, no override)\n- Scope 2 — touches many files, but mechanically.\n- Novelty 1 — pure find-and-replace, pattern exists.\n- Risk 1 — trivially reverted in one commit.\n- Iteration 1 — one-shot with a grep to verify.\nInsisting on Sonnet 5 instead ≈ 3x the per-token cost for no quality gain.\n",{"name":5,"description":7},"main","14c5d40ee0aec4abb935e26c246de93c4efdbee2","skills\u002Fmodel-invoked\u002Fmodel-router",0,"https:\u002F\u002Fgithub.com\u002FTemrel\u002Ftemrel-agentic-toolkit","https:\u002F\u002Fgithub.com\u002FTemrel","2026-07-31 19:43:16",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add Temrel\u002Ftemrel-agentic-toolkit --skill model-router",{"tool":36,"command":37},"bunx","bunx skills add Temrel\u002Ftemrel-agentic-toolkit --skill model-router",{"tool":39,"command":40},"pnpm","pnpm dlx skills add Temrel\u002Ftemrel-agentic-toolkit --skill model-router","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTemrel\u002Ftemrel-agentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fmodel-invoked\u002Fmodel-router\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"README.md","REFERENCE","参考文档",2159,"https:\u002F\u002Fgithub.com\u002FTemrel\u002Ftemrel-agentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fmodel-invoked\u002Fmodel-router\u002FREADME.md",[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M77MJ2YGAF234B7YYDRJZ56X","mcp-spec-audit","Audit an MCP server codebase for the MCP 2026-07-28 stateless spec revision by running the mcp-spec-audit CLI and summarizing its findings. Use when the user asks to audit, check, or migrate an MCP server for the new spec, asks whether their server is ready for MCP 2026-07-28 or \"the stateless revision\", or mentions migrating off Roots, Sampling, protocol Logging, or the experimental Tasks API.","https:\u002F\u002Fgithub.com\u002FTemrel\u002Ftemrel-agentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fmodel-invoked\u002Fmcp-spec-audit\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M77MJ0DKA1TBRTCDC71RK2H7","example-skill","A copy-me template skill. Replace this description with a precise, one-line summary of what the skill does and when an agent should reach for it, because this line is what the agent reads to decide relevance.","https:\u002F\u002Fgithub.com\u002FTemrel\u002Ftemrel-agentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fmodel-invoked\u002Fexample-skill\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M77MHX1SY3MDQSET9MA7CY4Z","example-command","A copy-me template for a human-invoked skill. Replace this with a one-line summary of what running \u002Fyour-command does.","https:\u002F\u002Fgithub.com\u002FTemrel\u002Ftemrel-agentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fhuman-invoked\u002Fexample-command\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M77MHTHG1G10DV762AQA32YY","gated","Use only when the user explicitly asks to run the release checklist.","https:\u002F\u002Fgithub.com\u002FTemrel\u002Ftemrel-agentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fhuman-invoked\u002Fautonomy-audit\u002Fscripts\u002Ffixtures\u002Fproject\u002F.claude\u002Fskills\u002Fgated\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M77MHQ5XD63TP0XX1V0H71X0","auto-leak","Use whenever the user mentions databases, migrations, or schema changes. Runs the full migration linter and applies fixes automatically.","https:\u002F\u002Fgithub.com\u002FTemrel\u002Ftemrel-agentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fhuman-invoked\u002Fautonomy-audit\u002Fscripts\u002Ffixtures\u002Fproject\u002F.claude\u002Fskills\u002Fauto-leak\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M77MHJHKNBJ7XQ0PT6KQ480Q","autonomy-audit","Inventory every behaviour this Claude Code setup can trigger (hooks, skills, MCP servers, permission rules, CLAUDE.md directives), classify each as auto-firing or manual, tag its cost-of-wrong, and write a recommended trigger policy to autonomy-audit.md. Takes an optional path to audit a different project.","https:\u002F\u002Fgithub.com\u002FTemrel\u002Ftemrel-agentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fhuman-invoked\u002Fautonomy-audit\u002FSKILL.md",[],[]]