[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71R6M25S13RCJGAYHTY193Q":3,"skill-same:01M71R6M25S13RCJGAYHTY193Q":54},{"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":17,"publishedAt":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":13,"repositoryHtmlUrl":37,"repositoryHomepageUrl":6,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":39,"install":40,"resources":53},"01M71R6M25S13RCJGAYHTY193Q","triple-verify",null,"Triple verification — 3 enfoques, thresholds por zona, modos !ship\u002F!fast\u002F!draft","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\u002Ftriple-verify\u002FSKILL.md",[],[18,19,20,21,22,23,24,25],"verify","triple verify","docs","verification","fast","ship","draft","thresholds","2026-11-10 13:02:02",false,"---\nname: triple-verify\ndescription: \"Triple verification — 3 enfoques, thresholds por zona, modos !ship\u002F!fast\u002F!draft\"\ntriggers: \"Triple verify, triangulate, 3 enfoques, !ship, !listo, !fast, !draft\"\nchangelog: docs\u002Fciclos\u002Fcycle28-20260815.md\ntoken_budget: 3150\n---\n## 3 Approaches\n| E1 — Testing | E2 — Static | E3 — Build\u002FRuntime |\n|---|---|---|\n| Unit\u002Fintegration\u002Fe2e | Lint, 4R, secrets | Build, dry-run, schema |\n| Tests pass, bug repro | No regressions | Build OK, runtime checks |\n| Schema validate, PSSA | Lint, 4R review | Dry-run, `-WhatIf` |\n## Workflow\n**Mode routing** (keyword overrides):\n- `!ship\u002F!listo` → quality-gate → triple-verify (por zona) → commit-crafter → commit+push\n- `!fast` → quality-gate → commit+push (skip verify)\n- `!check` → quality-gate only (no commit)\n- `!draft` → no gates\n- (no keyword) → zona determina verify depth\n**quality-gate ALWAYS mandatory** in `!ship`\u002F`!fast`\u002F`!check` regardless of zone. Zone only affects triple-verify, NOT quality-gate.\n**Zone routing** (verify depth, when keyword didn't route):\n- Verde → SKIP verify → quality-gate if commit\n- Amarilla ≤10L → quality-gate\n- Rojo\u002FAmarilla >10L → TRIPLE VERIFY (E1+E2+E3 parallel)\n- Fail → STOP + evidence · Pass → continue\n## Rules\n1. **3 DISTINCT approaches**: behavior + quality + compilation\n2. **Default-FAIL**: no evidence of 3 steps → not verified\n3. **Build mandatory** for compilable code\n4. **!ship = responsibility**: quality-gate NEVER optional\n5. **capture-learnings** (inline): run `scripts\u002Fsession-miner.ps1 -Mode scan -Json` post-task or pre-commit. Parse JSON for new patterns → `.learnings\u002F`. `mem_save` decisions\u002Fbugfixes to Engram. Skip if unavailable. Stage `.learnings\u002F`.\n6. **Override**: `!ship --no-verify` emergency only\n7. **Self-improvement override**: difficulty levels from CYCLE.md override verify depth\n## Reference\n> docs\u002Fskills\u002Ftriple-verify\u002Freference.md\n## Anti-Rationalization\n\n| Rationalization | Red Flag | Verification |\n|-----------------|----------|--------------|\n| \"2 de 3 enfoques bastan si coinciden\" | Omitir un enfoque porque otros dos pasaron | Exigir SIEMPRE E1+E2+E3 distintos (behavior+quality+compilation), Default-FAIL si falta uno |\n| \"E2 static es suficiente para refactors\" | Solo lint\u002F4R sin tests ni build | Rojo\u002FAmarilla >10L → E1+E2+E3 en paralelo; build mandatory si compilable, tests de repro obligatorios |\n| \"thresholds iguales para todas las zonas\" | Misma profundidad verify para Verde y Rojo | Zone routing: Verde→SKIP, Amarilla ≤10L→quality-gate, Rojo\u002FAmarilla >10L→TRIPLE VERIFY; quality-gate siempre en !ship |\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: trial-verify | testing-strategy\n\n","## 3 Approaches\n| E1 — Testing | E2 — Static | E3 — Build\u002FRuntime |\n|---|---|---|\n| Unit\u002Fintegration\u002Fe2e | Lint, 4R, secrets | Build, dry-run, schema |\n| Tests pass, bug repro | No regressions | Build OK, runtime checks |\n| Schema validate, PSSA | Lint, 4R review | Dry-run, `-WhatIf` |\n## Workflow\n**Mode routing** (keyword overrides):\n- `!ship\u002F!listo` → quality-gate → triple-verify (por zona) → commit-crafter → commit+push\n- `!fast` → quality-gate → commit+push (skip verify)\n- `!check` → quality-gate only (no commit)\n- `!draft` → no gates\n- (no keyword) → zona determina verify depth\n**quality-gate ALWAYS mandatory** in `!ship`\u002F`!fast`\u002F`!check` regardless of zone. Zone only affects triple-verify, NOT quality-gate.\n**Zone routing** (verify depth, when keyword didn't route):\n- Verde → SKIP verify → quality-gate if commit\n- Amarilla ≤10L → quality-gate\n- Rojo\u002FAmarilla >10L → TRIPLE VERIFY (E1+E2+E3 parallel)\n- Fail → STOP + evidence · Pass → continue\n## Rules\n1. **3 DISTINCT approaches**: behavior + quality + compilation\n2. **Default-FAIL**: no evidence of 3 steps → not verified\n3. **Build mandatory** for compilable code\n4. **!ship = responsibility**: quality-gate NEVER optional\n5. **capture-learnings** (inline): run `scripts\u002Fsession-miner.ps1 -Mode scan -Json` post-task or pre-commit. Parse JSON for new patterns → `.learnings\u002F`. `mem_save` decisions\u002Fbugfixes to Engram. Skip if unavailable. Stage `.learnings\u002F`.\n6. **Override**: `!ship --no-verify` emergency only\n7. **Self-improvement override**: difficulty levels from CYCLE.md override verify depth\n## Reference\n> docs\u002Fskills\u002Ftriple-verify\u002Freference.md\n## Anti-Rationalization\n\n| Rationalization | Red Flag | Verification |\n|-----------------|----------|--------------|\n| \"2 de 3 enfoques bastan si coinciden\" | Omitir un enfoque porque otros dos pasaron | Exigir SIEMPRE E1+E2+E3 distintos (behavior+quality+compilation), Default-FAIL si falta uno |\n| \"E2 static es suficiente para refactors\" | Solo lint\u002F4R sin tests ni build | Rojo\u002FAmarilla >10L → E1+E2+E3 en paralelo; build mandatory si compilable, tests de repro obligatorios |\n| \"thresholds iguales para todas las zonas\" | Misma profundidad verify para Verde y Rojo | Zone routing: Verde→SKIP, Amarilla ≤10L→quality-gate, Rojo\u002FAmarilla >10L→TRIPLE VERIFY; quality-gate siempre en !ship |\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: trial-verify | testing-strategy\n\n",{"name":5,"triggers":31,"changelog":32,"description":7,"token_budget":33},"Triple verify, triangulate, 3 enfoques, !ship, !listo, !fast, !draft","docs\u002Fciclos\u002Fcycle28-20260815.md",3150,"main","4af6946b30783e2c8f9182082324d530fc28f838",".agents\u002Fskills\u002Ftriple-verify","https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK\u002Fgentleman-agent-gh","https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK","2026-11-10 18:34:27",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add LuisAlbertoMK\u002Fgentleman-agent-gh --skill triple-verify",{"tool":46,"command":47},"bunx","bunx skills add LuisAlbertoMK\u002Fgentleman-agent-gh --skill triple-verify",{"tool":49,"command":50},"pnpm","pnpm dlx skills add LuisAlbertoMK\u002Fgentleman-agent-gh --skill triple-verify","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLuisAlbertoMK\u002Fgentleman-agent-gh\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftriple-verify\u002FSKILL.md",true,[],[55,98,121,141,166,192],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":77,"publishedAt":26},"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",[61,66,69,74],{"categoryNo":62,"categoryName":63,"taxonomyType":64,"taxonomyTypeDesc":65},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":67,"categoryName":68,"taxonomyType":64,"taxonomyTypeDesc":65},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":75,"categoryName":76,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000035","市场营销",[78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97],"quality","quality audit","web quality audit","audit","web","Animation","design audit","design","website","ui","responsive","seo","tokens","ui audit","Lighthouse","performance","review","optimize","a11y","page",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":105,"publishedAt":26},"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",[104],{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},[106,107,87,83,108,109,110,97,111,90,112,113,114,85,115,116,117,118,119,120],"ui engine","engine","compositor","css","dark","system","mode","hooks","container","only","query","components","dark mode","grid","queries",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":129,"publishedAt":26},"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",[127,128],{"categoryNo":62,"categoryName":63,"taxonomyType":64,"taxonomyTypeDesc":65},{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},[130,131,87,83,132,133,134,135,90,136,114,85,137,138,139,91,140,116,119,94],"baseline ui","baseline","generic","slop","for","anti-slop","fix","interface","cleanup","design review","use",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":150,"publishedAt":26},"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",[147],{"categoryNo":148,"categoryName":149,"taxonomyType":64,"taxonomyTypeDesc":65},"01JBSEEDCAT000000000000023","Skill与智能体开发",[151,152,153,154,155,156,157,158,159,160,161,162,163,164,165],"skill creator","creator","create","structure","register","2026","spec","new","ai skill","auto","define","ai agent","unknown","tasks","bootstrap",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":174,"publishedAt":26},"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",[172,173],{"categoryNo":62,"categoryName":63,"taxonomyType":64,"taxonomyTypeDesc":65},{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},[175,176,177,178,179,180,181,85,182,183,156,184,185,186,111,187,188,189,190,191],"engineer","senior","senior engineer","system design","trade-offs","senior engineering","delegation","senior architect","analysis","debt","architect","tech","strategy","apply","trade","tech debt","engineering",{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":202,"publishedAt":26},"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",[198,201],{"categoryNo":199,"categoryName":200,"taxonomyType":64,"taxonomyTypeDesc":65},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":148,"categoryName":149,"taxonomyType":64,"taxonomyTypeDesc":65},[203,204,191,205,206,85,207,156,208,209,210,211,212,213,214,215,216,217,218,219],"prompt","prompt engineering","scope","improve","react","security","patterns","multi-agent","framework","agent patterns","assertions","examples","with","multi","principles","improve prompt","prompts"]