[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M734YQQTS4GRCD0DXTJQ290M":3,"skill-same:01M734YQQTS4GRCD0DXTJQ290M":57},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":35,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":37,"install":38,"resources":50},"01M734YQQTS4GRCD0DXTJQ290M","assess-model-fit",null,"Assess model fit for task.","Morrison-Lab\u002Fai-config","Morrison-Lab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F104235520?v=4","01M734G0451S2G35MN4HFQK7XP","Morrison Lab","01M734G059BYFDFQA8YTPDGPMH",4,"MIT","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fassess-model-fit\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: assess-model-fit\ndescription: \"Assess model fit for task.\"\nuser-invocable: true\nallowed-tools:\n  - Bash\n  - Read\n  - Edit\n  - Write\n---\n\n# assess-model-fit — Evaluate current model capability\n\nDetermine whether the current Claude model is sufficient for your task, or recommend\nescalation to a higher-level model.\nRuns in **procedural mode** (checklist guidance)\nor **executable mode** (analyze a task and auto-recommend).\n\n## Procedure\n\n### Assess model fit (manual, procedural mode)\n\n1. **Identify the current model.**\n   Do not guess it: run `python3 scripts\u002Fcheck-session-runtime.py`, which reads the session's own transcript\n   (see [`verify-running-model`](..\u002F..\u002Fshared\u002Fworkflow\u002Fverify-running-model.md)).\n   Common tiers:\n   - Tier 1: Fable 5 (`claude-fable-5`), Opus 4.8 (`claude-opus-4-8`)\n   - Tier 2: Sonnet 4.6 \u002F 5 (`claude-sonnet-4-6`)\n   - Tier 3: Haiku 4.5 (`claude-haiku-4-5-20251001`)\n\n2. **Score your task against these criteria.**\n   A task needs escalation or orchestrator-worker delegation if it hits any of these:\n   - **Deep multi-step reasoning:** more than 5 logical steps, complex dependencies, or\n     architectural design decisions\n   - **Code review rigor:** assessing code for subtle bugs, security gaps, performance,\n     or architectural issues (not just syntax)\n   - **Large context window needed:** task involves many files, long documents, or\n     substantial history to reason over\n   - **Complex decomposition:** breaking down an ambiguous problem into sub-tasks and\n     choosing the right approach (not following a clear spec)\n   - **Uncertain scope:** task requirements are vague and need clarification by reasoning\n   - **Novel problem:** no standard solution applies; requires creative or exploratory thinking\n\n3. **Determine Orchestration Strategy:**\n   - **Solo Executor (Tier 2\u002F3):** The task is straightforward, bounded, well-specified, and single-purpose.\n   - **Orchestrator + Worker Delegation (Tier 1 Conductor + Tier 2 Workers):** The task is large, multi-stage, or complex.\n     Use Tier 1 to plan and decompose into tasks with strict stop conditions, spawn Tier 2 workers to implement, and audit before merging.\n   - **Escalate Model:** If the current model struggles with reasoning or loops on a bug, escalate immediately to Tier 1.\n\n4. **If escalation needed,** invoke `\u002Fselect-model` to determine the target.\n   Describe your task, and `select-model` will recommend the optimal tier and suggest a config update if desired.\n\n### Executable mode (auto-analysis and auto-chaining)\n\nInstead of running the checklist manually, invoke the skill with a task description.\nThe script will analyze the task, output an assessment, and if escalation is needed,\nautomatically call `select-model`:\n\n```\n\u002Fassess-model-fit --task \"I need to refactor a large REST API module and add comprehensive unit tests\"\n```\n\nThe script reads your current model, evaluates the task complexity, and either gives\nyou a go-ahead or chains into `select-model` with your task details.\n\n## How to use\n\n- **Procedural mode (manual checklist):** Read this procedure, run through the\n  scoring criteria, decide if escalation is needed.\n- **Executable mode (auto-analysis):** Invoke `\u002Fassess-model-fit --task \"\u003Cyour task description>\"`\n  and let the script recommend a verdict and model.\n- **When in doubt:** Use executable mode — it's faster and catches nuance the\n  manual checklist might miss.\n- **Broader stack recommendation ([recm](..\u002Frecm\u002FSKILL.md)):** Use `recm` when\n  deciding across harnesses, billing tiers, or multi-engine review rather than\n  within-session Claude escalation.\n","# assess-model-fit — Evaluate current model capability\n\nDetermine whether the current Claude model is sufficient for your task, or recommend\nescalation to a higher-level model.\nRuns in **procedural mode** (checklist guidance)\nor **executable mode** (analyze a task and auto-recommend).\n\n## Procedure\n\n### Assess model fit (manual, procedural mode)\n\n1. **Identify the current model.**\n   Do not guess it: run `python3 scripts\u002Fcheck-session-runtime.py`, which reads the session's own transcript\n   (see [`verify-running-model`](..\u002F..\u002Fshared\u002Fworkflow\u002Fverify-running-model.md)).\n   Common tiers:\n   - Tier 1: Fable 5 (`claude-fable-5`), Opus 4.8 (`claude-opus-4-8`)\n   - Tier 2: Sonnet 4.6 \u002F 5 (`claude-sonnet-4-6`)\n   - Tier 3: Haiku 4.5 (`claude-haiku-4-5-20251001`)\n\n2. **Score your task against these criteria.**\n   A task needs escalation or orchestrator-worker delegation if it hits any of these:\n   - **Deep multi-step reasoning:** more than 5 logical steps, complex dependencies, or\n     architectural design decisions\n   - **Code review rigor:** assessing code for subtle bugs, security gaps, performance,\n     or architectural issues (not just syntax)\n   - **Large context window needed:** task involves many files, long documents, or\n     substantial history to reason over\n   - **Complex decomposition:** breaking down an ambiguous problem into sub-tasks and\n     choosing the right approach (not following a clear spec)\n   - **Uncertain scope:** task requirements are vague and need clarification by reasoning\n   - **Novel problem:** no standard solution applies; requires creative or exploratory thinking\n\n3. **Determine Orchestration Strategy:**\n   - **Solo Executor (Tier 2\u002F3):** The task is straightforward, bounded, well-specified, and single-purpose.\n   - **Orchestrator + Worker Delegation (Tier 1 Conductor + Tier 2 Workers):** The task is large, multi-stage, or complex.\n     Use Tier 1 to plan and decompose into tasks with strict stop conditions, spawn Tier 2 workers to implement, and audit before merging.\n   - **Escalate Model:** If the current model struggles with reasoning or loops on a bug, escalate immediately to Tier 1.\n\n4. **If escalation needed,** invoke `\u002Fselect-model` to determine the target.\n   Describe your task, and `select-model` will recommend the optimal tier and suggest a config update if desired.\n\n### Executable mode (auto-analysis and auto-chaining)\n\nInstead of running the checklist manually, invoke the skill with a task description.\nThe script will analyze the task, output an assessment, and if escalation is needed,\nautomatically call `select-model`:\n\n```\n\u002Fassess-model-fit --task \"I need to refactor a large REST API module and add comprehensive unit tests\"\n```\n\nThe script reads your current model, evaluates the task complexity, and either gives\nyou a go-ahead or chains into `select-model` with your task details.\n\n## How to use\n\n- **Procedural mode (manual checklist):** Read this procedure, run through the\n  scoring criteria, decide if escalation is needed.\n- **Executable mode (auto-analysis):** Invoke `\u002Fassess-model-fit --task \"\u003Cyour task description>\"`\n  and let the script recommend a verdict and model.\n- **When in doubt:** Use executable mode — it's faster and catches nuance the\n  manual checklist might miss.\n- **Broader stack recommendation ([recm](..\u002Frecm\u002FSKILL.md)):** Use `recm` when\n  deciding across harnesses, billing tiers, or multi-engine review rather than\n  within-session Claude escalation.\n",{"name":5,"description":7,"allowed-tools":24,"user-invocable":29},[25,26,27,28],"Bash","Read","Edit","Write",true,"main","0f720481f8ce3b3d9fef485f6e230d8b3035748e","skills\u002Fassess-model-fit",1,"https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config","https:\u002F\u002Fmorrison-lab.github.io\u002Fai-config\u002F","https:\u002F\u002Fgithub.com\u002FMorrison-Lab","2026-11-15 04:39:15",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":29},[40,43,46],{"tool":41,"command":42},"npx","npx skills add Morrison-Lab\u002Fai-config --skill assess-model-fit",{"tool":44,"command":45},"bunx","bunx skills add Morrison-Lab\u002Fai-config --skill assess-model-fit",{"tool":47,"command":48},"pnpm","pnpm dlx skills add Morrison-Lab\u002Fai-config --skill assess-model-fit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fassess-model-fit\u002FSKILL.md",[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"scripts\u002Fassess-model-fit.sh","SCRIPT","脚本",8697,"https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fassess-model-fit\u002Fscripts\u002Fassess-model-fit.sh",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M735BVYCGR5VEC65AFDVSNKW","wrap-up","End-of-session verification and UMS.","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[],{"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":71,"publishedAt":19},"01M735BTH469T1CQ8G2Q9GENCR","workaround-watcher","Watch upstream issue for fix.","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fworkaround-watcher\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M735BRKZWFANSQ0GM380B4TD","wn","→ whats-next.","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fwn\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M735BPE9V830B3B6NGXQ56J6","whats-next","Recommend concrete next step or action.","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fwhats-next\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M735BMHQ60EAD5B7QAWXC5A0","wait-for-results","Wait for pipeline\u002FCI results.","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fwait-for-results\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M735BKGZHPN1PEMJ7YBD5VJ8","wai","→ send-notes.","https:\u002F\u002Fgithub.com\u002FMorrison-Lab\u002Fai-config\u002Fblob\u002Fmain\u002Fskills\u002Fwai\u002FSKILL.md",[],[]]