[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6WR8TMGS9G79DFTX0K1ZA8T":3,"skill-same:01M6WR8TMGS9G79DFTX0K1ZA8T":87},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":14,"repositoryHtmlUrl":62,"repositoryHomepageUrl":6,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":80},"01M6WR8TMGS9G79DFTX0K1ZA8T","smart-commands",null,"Decision guide for when to proactively use Claude Code slash commands — \u002Fthink, \u002Fmodel, \u002Fcompact, \u002Fclear. Use when choosing whether to invoke a command before or during a task, or when a complexity-classifier hook has flagged a task as high or critical. Pairs with the complexity-classifier UserPromptSubmit hook. Answers when to compact, should I switch models, and whether to use extended thinking. Use to pick the right \u002Fmodel command and switch model.","LucasSantana-Dev\u002Fforgekit","LucasSantana-Dev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F98131142?v=4","01M6E038X8H7VE9GCEJP9PT5CA","Lucas Santana","01M6E0391WB0JYZTWXEBR9WSXA",1,"MIT","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-smart-commands\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"smart commands","commands","thinking","when","invoke","for","hook","critical","as","compact","code","switch","classifier","complexity","use","guide","command","decision","pick","model","2026-11-10 10:12:30",false,"---\nname: smart-commands\ndescription: Decision guide for when to proactively use Claude Code slash commands — \u002Fthink, \u002Fmodel, \u002Fcompact, \u002Fclear. Use when choosing whether to invoke a command before or during a task, or when a complexity-classifier hook has flagged a task as high or critical. Pairs with the complexity-classifier UserPromptSubmit hook. Answers when to compact, should I switch models, and whether to use extended thinking. Use to pick the right \u002Fmodel command and switch model.\ntriggers:\n  - smart commands\n  - when to use \u002Fthink\n  - when to compact\n  - should I switch models\n  - use extended thinking\n  - \u002Fthink\n  - \u002Fcompact\n  - \u002Fmodel\n  - \u002Fclear\n  - slash commands\n---\n\n# smart-commands\n\nWhen to invoke Claude Code slash commands — and when not to.\n\n## \u002Fthink — Extended reasoning\n\n**Use before:**\n- Designing something you'll have to live with (API contracts, schema, auth flow)\n- Debugging a non-obvious issue where first guess is likely wrong\n- Security-sensitive decisions (anything touching auth, secrets, permissions)\n- When the complexity-classifier fires `[AUTO] CRITICAL`\n\n**Skip when:**\n- The task is mechanical (rename, format, add field)\n- You already know the answer with high confidence\n- It's a lookup or grep task\n\n**How:** Type `\u002Fthink` before your first action on the task.\n\n---\n\n## \u002Fmodel — Switch model\n\n| Switch to | When |\n|-----------|------|\n| `\u002Fmodel claude-opus-4-7` | Sustained security\u002Farchitecture work (>5 turns), incident response, risky migrations |\n| `\u002Fmodel claude-sonnet-4-6` | Normal coding work (default) |\n| `\u002Fmodel claude-haiku-4-5` | Repetitive formatting, bulk triage, quick lookups across many files |\n\n**Rules:**\n- Switch back to Sonnet after finishing a critical section — Opus is expensive\n- For Agent tool calls, always set `model:` explicitly; the session model is independent\n- `CLAUDE_CODE_SUBAGENT_MODEL=claude-haiku-4-5-20251001` is the default for subagents\n\n---\n\n## \u002Fcompact — Context compression\n\n**Use when:**\n- Switching to a different feature or codebase area\n- Context is at 50%+ and the current task is logically complete\n- You're about to start a long phase and want a clean baseline\n\n**Don't use when:**\n- Mid-task — compaction may lose intermediate reasoning you need\n- The previous turns contain decisions you'll need to defend in the next turn\n\n---\n\n## \u002Fclear — Full reset\n\n**Rarely needed.** Use only when:\n- Starting a completely unrelated task after a compact is insufficient\n- The session has persistent tool failures and state is corrupt\n\n**Never use mid-task** — you'll lose all accumulated context.\n\n---\n\n## Decision tree (quick)\n\n```\nIs this security\u002Farch\u002Fmigration\u002Fproduction?\n  YES → \u002Fthink first, consider \u002Fmodel opus\n  NO  → Is this >3 phases or complex debugging?\n         YES → \u002Fthink at key decision points\n         NO  → Is context >50% and task is done?\n                YES → \u002Fcompact before next task\n                NO  → proceed normally\n```\n\n---\n\n## Installation\n\nThis skill is paired with a zero-cost `complexity-classifier.sh` hook that auto-injects guidance.\n\n1. Copy `complexity-classifier.sh` to `~\u002F.claude\u002Fhooks\u002F`\n2. Make it executable: `chmod +x ~\u002F.claude\u002Fhooks\u002Fcomplexity-classifier.sh`\n3. Add to `settings.json`:\n\n```json\n\"UserPromptSubmit\": [{\n  \"matcher\": \"*\",\n  \"hooks\": [{\n    \"type\": \"command\",\n    \"command\": \"~\u002F.claude\u002Fhooks\u002Fcomplexity-classifier.sh\",\n    \"timeout\": 5\n  }]\n}]\n```\n\nThe hook fires on every prompt, classifies low\u002Fmedium\u002Fhigh\u002Fcritical, and injects `[AUTO]` guidance into systemMessage. No API calls, zero cost.\n","# smart-commands\n\nWhen to invoke Claude Code slash commands — and when not to.\n\n## \u002Fthink — Extended reasoning\n\n**Use before:**\n- Designing something you'll have to live with (API contracts, schema, auth flow)\n- Debugging a non-obvious issue where first guess is likely wrong\n- Security-sensitive decisions (anything touching auth, secrets, permissions)\n- When the complexity-classifier fires `[AUTO] CRITICAL`\n\n**Skip when:**\n- The task is mechanical (rename, format, add field)\n- You already know the answer with high confidence\n- It's a lookup or grep task\n\n**How:** Type `\u002Fthink` before your first action on the task.\n\n---\n\n## \u002Fmodel — Switch model\n\n| Switch to | When |\n|-----------|------|\n| `\u002Fmodel claude-opus-4-7` | Sustained security\u002Farchitecture work (>5 turns), incident response, risky migrations |\n| `\u002Fmodel claude-sonnet-4-6` | Normal coding work (default) |\n| `\u002Fmodel claude-haiku-4-5` | Repetitive formatting, bulk triage, quick lookups across many files |\n\n**Rules:**\n- Switch back to Sonnet after finishing a critical section — Opus is expensive\n- For Agent tool calls, always set `model:` explicitly; the session model is independent\n- `CLAUDE_CODE_SUBAGENT_MODEL=claude-haiku-4-5-20251001` is the default for subagents\n\n---\n\n## \u002Fcompact — Context compression\n\n**Use when:**\n- Switching to a different feature or codebase area\n- Context is at 50%+ and the current task is logically complete\n- You're about to start a long phase and want a clean baseline\n\n**Don't use when:**\n- Mid-task — compaction may lose intermediate reasoning you need\n- The previous turns contain decisions you'll need to defend in the next turn\n\n---\n\n## \u002Fclear — Full reset\n\n**Rarely needed.** Use only when:\n- Starting a completely unrelated task after a compact is insufficient\n- The session has persistent tool failures and state is corrupt\n\n**Never use mid-task** — you'll lose all accumulated context.\n\n---\n\n## Decision tree (quick)\n\n```\nIs this security\u002Farch\u002Fmigration\u002Fproduction?\n  YES → \u002Fthink first, consider \u002Fmodel opus\n  NO  → Is this >3 phases or complex debugging?\n         YES → \u002Fthink at key decision points\n         NO  → Is context >50% and task is done?\n                YES → \u002Fcompact before next task\n                NO  → proceed normally\n```\n\n---\n\n## Installation\n\nThis skill is paired with a zero-cost `complexity-classifier.sh` hook that auto-injects guidance.\n\n1. Copy `complexity-classifier.sh` to `~\u002F.claude\u002Fhooks\u002F`\n2. Make it executable: `chmod +x ~\u002F.claude\u002Fhooks\u002Fcomplexity-classifier.sh`\n3. Add to `settings.json`:\n\n```json\n\"UserPromptSubmit\": [{\n  \"matcher\": \"*\",\n  \"hooks\": [{\n    \"type\": \"command\",\n    \"command\": \"~\u002F.claude\u002Fhooks\u002Fcomplexity-classifier.sh\",\n    \"timeout\": 5\n  }]\n}]\n```\n\nThe hook fires on every prompt, classifies low\u002Fmedium\u002Fhigh\u002Fcritical, and injects `[AUTO]` guidance into systemMessage. No API calls, zero cost.\n",{"name":5,"triggers":49,"description":7},[24,50,51,52,53,54,55,56,57,58],"when to use \u002Fthink","when to compact","should I switch models","use extended thinking","\u002Fthink","\u002Fcompact","\u002Fmodel","\u002Fclear","slash commands","main","f2e470f7ead3f9982aee7aadc1aa5bef5d4db833","packages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-smart-commands","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev","https:\u002F\u002Flucassantana.tech","Senior engineer. AI agent tooling and evals on Node\u002FTS backends. Brazil, UTC-3.","2026-11-11 07:05:28",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add LucasSantana-Dev\u002Fforgekit --skill smart-commands",{"tool":73,"command":74},"bunx","bunx skills add LucasSantana-Dev\u002Fforgekit --skill smart-commands",{"tool":76,"command":77},"pnpm","pnpm dlx skills add LucasSantana-Dev\u002Fforgekit --skill smart-commands","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-smart-commands\u002FSKILL.md",true,[81],{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"manifest.json","REFERENCE","参考文档",1208,"https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-smart-commands\u002Fmanifest.json",[88,115,143,152,170,189],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":95,"publishedAt":44},"01M6WR9SQGQ5WDEJY9HH3T93E8","token-audit","Audit historical Claude Code token usage from JSONL session files — shows total spend, cache hit rates, top costly sessions, weekly trends, and where tokens are going. Run after heavy sessions or weekly to measure optimization impact. Answers how many tokens a session used, how expensive was that session, session cost, and token usage report.","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-token-audit\u002FSKILL.md",[94],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,34,113,114],"audit","token","token audit","sessions","cost","weekly","top","usage","jsonl","usage report","impact","tokens","files","session","how","Optimization","cache","run","rate",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":126,"publishedAt":44},"01M6WR919T3NGWMZ5R5XKWX9KN","smart-model-route","Auto-classify prompt complexity via Haiku (with heuristic fallback) and inject model routing hints for Agent tool calls. Wired as a UserPromptSubmit hook — fires on every prompt, routes low tasks to Haiku, standard to Sonnet, complex to Sonnet with thorough reasoning, and critical (security\u002Farch\u002Fmigrations) to Opus. Handles model selection, for example choose model by task complexity.","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcatalog\u002Fcatalog\u002Fskills\u002Fadt-smart-model-route\u002FSKILL.md",[121],{"categoryNo":122,"categoryName":123,"taxonomyType":124,"taxonomyTypeDesc":125},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[127,128,129,43,130,30,31,131,132,133,134,37,135,136,137,138,139,140,141,142],"route","smart model route","model route","sonnet","arch","classify","selection","fallback","auto","haiku","choose","opus","agent tool","model selection","security","tasks",{"skillNo":144,"name":145,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":44},"01M6E0ZGQ78S4SE6X6RCN1PR9A","spec-ship","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcore\u002Fkit\u002Fspecs\u002Fskills\u002Fspec-ship\u002FSKILL.md",[],[149,150,151],"spec","ship","spec ship",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":44},"01M6E0ZD27S87Z954JTHECWG34","spec-new","Create a committed per-feature spec under `docs\u002Fspecs\u002FYYYY-MM-DD-\u003Cslug>\u002F{spec,tasks}.md` with frontmatter (status, created, owner, pr, tags). Promotes an ephemeral `.claude\u002Fplans\u002F\u003Cname>.md` into a persistent, searchable artifact. Use when starting a feature that's larger than a one-shot PR.","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcore\u002Fkit\u002Fspecs\u002Fskills\u002Fspec-new\u002FSKILL.md",[],[159,149,160,161,162,163,164,165,38,166,142,167,168,169],"spec new","dd","tags","name","plans","feature","artifact","create","pr","status","docs",{"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":179,"publishedAt":44},"01M6E0Z9B5YE1G4NM05JPNVWMK","roadmap-refresh","Regenerate `docs\u002Froadmap.md` for a repo from all specs under `docs\u002Fspecs\u002F` + their frontmatter (status, tags, pr). Produces Now\u002FNext\u002FRecently-shipped sections. Run after creating \u002F shipping a spec, or at the start of a new session for orientation.","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcore\u002Fkit\u002Fspecs\u002Fskills\u002Froadmap-refresh\u002FSKILL.md",[176],{"categoryNo":177,"categoryName":178,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000031","产品经理",[180,181,182,149,183,184,185,186,113,167,168,169,109,161,187,188],"refresh","roadmap","roadmap refresh","repo","new session","start","shipping","now","next",{"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":196,"publishedAt":44},"01M6E0Z5SRVZ8G545HJB3XR6HG","aggregate-roadmap","Regenerate the cross-repo roadmap aggregate in your Claude memory directory by walking every curated repo's `docs\u002Fspecs\u002F**` frontmatter. Run at session start for cross-repo orientation or after any `spec-new`\u002F`spec-ship` in any repo.","https:\u002F\u002Fgithub.com\u002FLucasSantana-Dev\u002Fforgekit\u002Fblob\u002Fmain\u002Fpackages\u002Fcore\u002Fkit\u002Fspecs\u002Fskills\u002Faggregate-roadmap\u002FSKILL.md",[195],{"categoryNo":177,"categoryName":178,"taxonomyType":21,"taxonomyTypeDesc":22},[197,181,198,109,183,150,185,113,199,169,149],"aggregate roadmap","directory","memory"]