[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71R71AD51RKCJ5B8CW12TX7":3,"skill-same:01M71R71AD51RKCJ5B8CW12TX7":75},{"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":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":13,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":60,"install":61,"resources":74},"01M71R71AD51RKCJ5B8CW12TX7","workflow-optimizer",null,"Optimize workflow patterns — faster info access, reduced token waste, smarter caching, auto-learning triggers.","LuisAlbertoMK\u002Fgentleman-agent-gh","LuisAlbertoMK","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F96153499?v=4","01M71QZX0CF9KKGQZ8ZN9BME63","01M71QZX11P5X6Z27HE1GQDF71",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK\u002Fgentleman-agent-gh\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-optimizer\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"workflow","workflow optimizer","optimizer","learning","access","auto","workflow patterns","patterns","optimize","info","auto-learning","pattern","caching","Optimization","token","triggers","information","token-optimization","docs","2026-11-10 13:02:02",false,"---\nname: workflow-optimizer\ndescription: \"Optimize workflow patterns — faster info access, reduced token waste, smarter caching, auto-learning triggers.\"\ntriggers: [optimize-workflow, faster-access, token-optimization, workflow-pattern, information-access, fluidez]\nchangelog: docs\u002Fciclos\u002Fcycle28-20260815.md\ntoken_budget: 3000\n---\n## When to Use\nOptimize workflow — info access, token economy, caching, auto-learning triggers.\n## Core Principles\n1. Info Access: right info, right time. 2. Token Economy: every token earns its place. 3. Auto-Learning: patterns→rules→habits→instinct. 4. Cache Aggressively: compute once, reuse everywhere.\n## Speed Patterns\n1. **Pre-flight**: `mem_search(\"\u003Ckeywords>\", limit=3)` → top 3; check skill-graph; no recent error (immune-system). Savings: 2-5K\u002Ftask.\n2. **Lazy loading**: Q&A → karpathy-loop + lean-context (skip sdd-*, judgment-day) | Bug fix → recovery-protocol + immune-system (skip sdd-propose) | Review → code-review-agent + judgment-day (skip sdd-*). Savings: 5-15K\u002Fsession.\n3. **Compression**: L1 (8 msgs\u002F15 calls) -60-70% | L2 (20 msgs\u002F3 L1) decisions+ID -40-50% | L3 (ORANGE>60%) 1-liner+ref -80-90%.\n4. **Parallel gather**: >3 files → delegate explore; independent research → parallel; batch reads → single call.\n## Auto-Learning Triggers\nIF same_fix_2x → ANTI-PATTERN-CATALOG · IF same_error_3x → immune-system · IF user_correction_2x → AGENTS.md rules · IF repeat_workflow_3x → create skill.\nPipeline: Capture (mem_save every decision\u002Fbugfix\u002Fdiscovery) → Extract (dreaming on 5th error) → Evaluate (score delta) → Apply (inject next session).\n## Information Access\nFast recall: `mem_context` → `mem_search` → `mem_get_observation`. Proactive: project → `mem_search(project=...)`; feature → query; error → `mem_search(type=bugfix)`.\n## Reference\nExtended details, examples, patterns → docs\u002Fskills\u002Fworkflow-optimizer\u002Freference.md\n## Anti-Rationalization\n\n| Rationalization | Red Flag | Verification |\n|-----------------|----------|--------------|\n| \"Caching no aplica aquí\" | Recomputing instead of reusing mem_search | Check pre-flight `mem_search` cache — saves 2-5K\u002Ftask if skipped |\n| \"Paralelizar es overkill\" | Serial gather for >3 files | >3 files → delegate explore parallel — verify batch vs sequential cost |\n| \"Auto-learning después\" | Deferring mem_save after decision\u002Fbugfix | Capture→Extract→Evaluate — `mem_save` every decision\u002Fbugfix now |\n\n## Red Flags\n- Doing work without checking output format → STOP, re-read skill\n- Second occurrence of same rationalization → force RED zone\n\n## Verification\n- Output matches skill ## Output contract + file:line citaton\n- cross-ref-check.ps1 → SKILL.md OK\n## Refs\nCross-Refs: skill-graph | performance | context-watchdog | lean-context | karpathy-loop\n\n","## When to Use\nOptimize workflow — info access, token economy, caching, auto-learning triggers.\n## Core Principles\n1. Info Access: right info, right time. 2. Token Economy: every token earns its place. 3. Auto-Learning: patterns→rules→habits→instinct. 4. Cache Aggressively: compute once, reuse everywhere.\n## Speed Patterns\n1. **Pre-flight**: `mem_search(\"\u003Ckeywords>\", limit=3)` → top 3; check skill-graph; no recent error (immune-system). Savings: 2-5K\u002Ftask.\n2. **Lazy loading**: Q&A → karpathy-loop + lean-context (skip sdd-*, judgment-day) | Bug fix → recovery-protocol + immune-system (skip sdd-propose) | Review → code-review-agent + judgment-day (skip sdd-*). Savings: 5-15K\u002Fsession.\n3. **Compression**: L1 (8 msgs\u002F15 calls) -60-70% | L2 (20 msgs\u002F3 L1) decisions+ID -40-50% | L3 (ORANGE>60%) 1-liner+ref -80-90%.\n4. **Parallel gather**: >3 files → delegate explore; independent research → parallel; batch reads → single call.\n## Auto-Learning Triggers\nIF same_fix_2x → ANTI-PATTERN-CATALOG · IF same_error_3x → immune-system · IF user_correction_2x → AGENTS.md rules · IF repeat_workflow_3x → create skill.\nPipeline: Capture (mem_save every decision\u002Fbugfix\u002Fdiscovery) → Extract (dreaming on 5th error) → Evaluate (score delta) → Apply (inject next session).\n## Information Access\nFast recall: `mem_context` → `mem_search` → `mem_get_observation`. Proactive: project → `mem_search(project=...)`; feature → query; error → `mem_search(type=bugfix)`.\n## Reference\nExtended details, examples, patterns → docs\u002Fskills\u002Fworkflow-optimizer\u002Freference.md\n## Anti-Rationalization\n\n| Rationalization | Red Flag | Verification |\n|-----------------|----------|--------------|\n| \"Caching no aplica aquí\" | Recomputing instead of reusing mem_search | Check pre-flight `mem_search` cache — saves 2-5K\u002Ftask if skipped |\n| \"Paralelizar es overkill\" | Serial gather for >3 files | >3 files → delegate explore parallel — verify batch vs sequential cost |\n| \"Auto-learning después\" | Deferring mem_save after decision\u002Fbugfix | Capture→Extract→Evaluate — `mem_save` every decision\u002Fbugfix now |\n\n## Red Flags\n- Doing work without checking output format → STOP, re-read skill\n- Second occurrence of same rationalization → force RED zone\n\n## Verification\n- Output matches skill ## Output contract + file:line citaton\n- cross-ref-check.ps1 → SKILL.md OK\n## Refs\nCross-Refs: skill-graph | performance | context-watchdog | lean-context | karpathy-loop\n\n",{"name":5,"triggers":47,"changelog":53,"description":7,"token_budget":54},[48,49,40,50,51,52],"optimize-workflow","faster-access","workflow-pattern","information-access","fluidez","docs\u002Fciclos\u002Fcycle28-20260815.md",3000,"main","4af6946b30783e2c8f9182082324d530fc28f838",".agents\u002Fskills\u002Fworkflow-optimizer","https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK\u002Fgentleman-agent-gh","https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK","2026-11-10 18:34:27",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add LuisAlbertoMK\u002Fgentleman-agent-gh --skill workflow-optimizer",{"tool":67,"command":68},"bunx","bunx skills add LuisAlbertoMK\u002Fgentleman-agent-gh --skill workflow-optimizer",{"tool":70,"command":71},"pnpm","pnpm dlx skills add LuisAlbertoMK\u002Fgentleman-agent-gh --skill workflow-optimizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK\u002Fgentleman-agent-gh\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-optimizer\u002FSKILL.md",true,[],[76,116,139,159,181,207],{"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":96,"publishedAt":42},"01M71R7K35P668DYEPYGDQP2QA","web-quality-audit","Comprehensive web audit: performance, a11y, SEO, responsive, animation, design tokens.","https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK\u002Fgentleman-agent-gh\u002Fblob\u002Fmain\u002Fdocs\u002Fciclos\u002Fc28-w1-backup\u002Fweb-quality-audit\u002FSKILL.md",[82,85,88,93],{"categoryNo":83,"categoryName":84,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":86,"categoryName":87,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":94,"categoryName":95,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000035","市场营销",[97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,31,114,115],"quality","quality audit","web quality audit","audit","web","Animation","design audit","design","website","ui","responsive","seo","tokens","ui audit","Lighthouse","performance","review","a11y","page",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":123,"publishedAt":42},"01M71R7H1RA7CQ568DHRK37PE2","ui-engine","UI system — Grid\u002FFlexbox\u002F@layer\u002F:has(), container queries, compositor-only animation, OKLCH tokens, component patterns","https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK\u002Fgentleman-agent-gh\u002Fblob\u002Fmain\u002Fdocs\u002Fciclos\u002Fc28-w1-backup\u002Fui-engine\u002FSKILL.md",[122],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[124,125,106,102,126,127,128,115,129,109,130,131,132,104,133,134,135,136,137,138],"ui engine","engine","compositor","css","dark","system","mode","hooks","container","only","query","components","dark mode","grid","queries",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":147,"publishedAt":42},"01M71R7EPMZFKB833WE4B3GTHC","baseline-ui","Anti-slop UI — layout, typography, responsive, animation, tokens. Use for cleanup or polish.","https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK\u002Fgentleman-agent-gh\u002Fblob\u002Fmain\u002Fdocs\u002Fciclos\u002Fc28-w1-backup\u002Fbaseline-ui\u002FSKILL.md",[145,146],{"categoryNo":83,"categoryName":84,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[148,149,106,102,150,151,152,153,109,154,132,104,155,156,157,110,158,134,137,113],"baseline ui","baseline","generic","slop","for","anti-slop","fix","interface","cleanup","design review","use",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"publishedAt":42},"01M71R7CWK3FBW77Z8WD9GXQFE","skill-creator","Create new AI agent skills following Agent Skills spec -- auto-bootstrap unknown tasks, define structure, register in AGENTS.md","https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK\u002Fgentleman-agent-gh\u002Fblob\u002Fmain\u002F.archive\u002Fskills\u002Fskill-creator\u002FSKILL.md",[165],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[167,168,169,170,171,172,173,174,175,28,176,177,178,179,180],"skill creator","creator","create","structure","register","2026","spec","new","ai skill","define","ai agent","unknown","tasks","bootstrap",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":189,"publishedAt":42},"01M71R78DZM1GA16F1KN8ND926","senior-engineer","Apply senior engineering competencies — system design, trade-off analysis, delegation, mentoring, and tech debt strategy","https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK\u002Fgentleman-agent-gh\u002Fblob\u002Fmain\u002F.archive\u002Fskills\u002Fsenior-engineer\u002FSKILL.md",[187,188],{"categoryNo":83,"categoryName":84,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[190,191,192,193,194,195,196,104,197,198,172,199,200,201,129,202,203,204,205,206],"engineer","senior","senior engineer","system design","trade-offs","senior engineering","delegation","senior architect","analysis","debt","architect","tech","strategy","apply","trade","tech debt","engineering",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":217,"publishedAt":42},"01M71R74WQTXZMG3219RND96CE","prompt-engineering","Design effective prompts using SPEARS framework — scope, principles, examples, assertions, refinements, with ReAct and multi-agent patterns","https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK\u002Fgentleman-agent-gh\u002Fblob\u002Fmain\u002F.archive\u002Fskills\u002Fprompt-engineering\u002FSKILL.md",[213,216],{"categoryNo":214,"categoryName":215,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[218,219,206,220,221,104,222,172,223,30,224,225,226,227,228,229,230,231,232,233],"prompt","prompt engineering","scope","improve","react","security","multi-agent","framework","agent patterns","assertions","examples","with","multi","principles","improve prompt","prompts"]