[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KWE44A738GDK65QS02XJBG":3,"skill-same:01M6KWE44A738GDK65QS02XJBG":63},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":14,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M6KWE44A738GDK65QS02XJBG","triage",null,"Task classification, decomposition, dependency mapping, and routing skill. Invoked by the triage-agent to break any user request into discrete, independently-routable work items with assigned priorities and agent chains.","rafsanulhasan\u002FHypermediaEngine","rafsanulhasan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F2341142?v=4","01M6KW2HWPTZWK051N7B0HTBVG","Rafsanul Hasan","01M6KW2J0N3613382MF5DRN79H",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ftriage\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,36],"routing","classification","work","user","dependency","task","priorities","decomposition","user request","mapping","with","break","request","2026-11-10 10:12:30",false,"---\nname: triage\ndescription: \"Task classification, decomposition, dependency mapping, and routing skill. Invoked by the triage-agent to break any user request into discrete, independently-routable work items with assigned priorities and agent chains.\"\n---\n\nYou are executing the `triage` skill on behalf of the triage-agent. Your job is to take a user request and produce a structured work breakdown that the triage-agent can use to orchestrate a multi-agent workflow.\n\n## Input\n\nThe calling agent passes the raw user prompt or a task description as `args`.\n\n## Process\n\n### Step 1 — Classify\n\nIdentify all task types present in the request:\n\n| Type | Indicators | Default Priority |\n|---|---|---|\n| Feature | \"Add X\", \"I want X\", \"we need X\", new capability | P1–P2 |\n| Bug Fix | Crash, incorrect behavior, failing test, exception, regression | P0–P1 |\n| Security Fix | Auth bypass, data exposure, input validation gap, vulnerable dependency | P0 |\n| TechDebt | Refactor, convention violation, cleanup, performance | P2–P3 |\n| Release | \"Ship\", \"release\", \"deploy\", \"publish to NuGet\" | — |\n| Question | Exploratory — \"what would...\", \"how should we...\" | — |\n\nA single request may contain multiple types. Identify all present.\n\n### Step 2 — Decompose\n\nFor complex requests (multiple types or >1 agent needed):\n\n1. Identify atomic work items — each deliverable by a single, contiguous agent chain\n2. Map dependencies: which items must complete before others can begin\n3. Identify parallelization: which items share no dependency and can run concurrently\n4. **Flag research dependencies** — for each work item, check whether it requires external knowledge (library\u002FAPI\u002FSDK docs, unfamiliar framework, current best practices, version-migration info) or non-trivial cross-cutting code exploration. If yes, prepend a `research-assistant` step to that item's agent chain. The downstream specialists wait for the research findings before starting. See Step 3 routing rules for the explicit chains.\n5. Keep decomposition minimal — do not split a naturally-sequential flow into artificial fragments\n\nFor simple requests (one type, one agent, no dependencies): return a single-item plan.\n\n### Step 3 — Assign Agent Chains\n\nFor each work item, select the tightest-fitting standard chain:\n\n```\nNew feature (scope unknown)              → requirement-analyst → software-architect → system-engineer → software-engineer → sqa-engineer\nNew feature (design needed)              → software-architect → system-engineer → software-engineer → sqa-engineer\nNew feature (ready to build)             → software-engineer → sqa-engineer\nFeature needs prioritization             → product-manager → (then appropriate build chain above)\nBug fix                                  → software-engineer  (invoke fix-bug skill)\nBug fix with arch concern                → software-engineer → software-architect  (invoke architecture-review skill)\nSecurity fix                             → \u002Fsecurity-review skill directly\nTech debt \u002F refactor                     → software-engineer → code-reviewer\nTech debt needs prioritization           → product-manager → software-engineer → code-reviewer\nTest coverage gap                        → sqa-engineer\nLow-level design question                → system-engineer\nArchitecture question                    → software-architect\nBacklog \u002F prioritization question        → product-manager\nRelease \u002F milestone planning             → product-manager → devops-engineer (NuGet publish + GitHub Release)\nAgent \u002F skill \u002F command lifecycle        → agent-manager\nRules \u002F instructions \u002F hooks change      → agent-manager\nAgent memory prune \u002F audit \u002F refresh     → agent-manager\nExternal knowledge \u002F library docs needed → research-assistant → (then the appropriate chain above)\nUnfamiliar framework \u002F SDK behavior      → research-assistant → (then specialist chain)\nValidate assumption before design        → research-assistant → software-architect\nDeep cross-cutting codebase exploration  → research-assistant (standalone) or research-assistant → specialist\n```\n\n**Research-prepend rule:** Whenever a work item's chain involves design or implementation against external technology the team has not recently verified, prepend `research-assistant` as the first agent in that item's chain. The specialist receiving the work waits for the cited findings report before starting.\n\n### Step 4 — Set Priorities\n\nApply defaults, then check for overrides:\n\n- Security Fix: always P0 — never downgrade\n- Bug (regression or system blocker): P0; other bugs: P1\n- Feature: P1 by default; P2 for cosmetic or low-impact work\n- TechDebt: P2; raise to P1 only if it directly blocks a P0\u002FP1 item\n\n### Step 5 — Flag PM Consultation Requirement\n\nMark whether the PM should be consulted before execution begins:\n\n- **Yes** — if any item is Feature or TechDebt\n- **No** — if all items are Bug Fix (P0), Security Fix, Question, or Routing\n\n## Output\n\nReturn the complete work breakdown to the triage-agent:\n\n```\n### Work Breakdown: \u003Crequest summary>\n\n#### Classification\n\u003CType(s)> — \u003Creason>\n\n#### Work Items\n| ID | Type | Priority | Description | Depends On | Parallel With | Agent Chain |\n|---|---|---|---|---|---|---|\n| WI-001 | Feature | P1 | Add X capability | — | — | req-analyst → sw-arch → sys-eng → sw-eng → sqa |\n| WI-002 | Bug Fix | P0 | Fix Y crash in Z | — | — | software-engineer |\n\n#### Execution Waves\n- Wave 1 (parallel): WI-002 (P0 — immediate), WI-001 (pending PM priority confirmation)\n- Wave 2 (after WI-001 completes): WI-003\n\n#### PM Consultation Required\n\u003CYes — Feature items WI-001 need prioritization before routing>\nOR\n\u003CNo — all items are P0 bug\u002Fsecurity fixes, routing immediately>\n```\n","You are executing the `triage` skill on behalf of the triage-agent. Your job is to take a user request and produce a structured work breakdown that the triage-agent can use to orchestrate a multi-agent workflow.\n\n## Input\n\nThe calling agent passes the raw user prompt or a task description as `args`.\n\n## Process\n\n### Step 1 — Classify\n\nIdentify all task types present in the request:\n\n| Type | Indicators | Default Priority |\n|---|---|---|\n| Feature | \"Add X\", \"I want X\", \"we need X\", new capability | P1–P2 |\n| Bug Fix | Crash, incorrect behavior, failing test, exception, regression | P0–P1 |\n| Security Fix | Auth bypass, data exposure, input validation gap, vulnerable dependency | P0 |\n| TechDebt | Refactor, convention violation, cleanup, performance | P2–P3 |\n| Release | \"Ship\", \"release\", \"deploy\", \"publish to NuGet\" | — |\n| Question | Exploratory — \"what would...\", \"how should we...\" | — |\n\nA single request may contain multiple types. Identify all present.\n\n### Step 2 — Decompose\n\nFor complex requests (multiple types or >1 agent needed):\n\n1. Identify atomic work items — each deliverable by a single, contiguous agent chain\n2. Map dependencies: which items must complete before others can begin\n3. Identify parallelization: which items share no dependency and can run concurrently\n4. **Flag research dependencies** — for each work item, check whether it requires external knowledge (library\u002FAPI\u002FSDK docs, unfamiliar framework, current best practices, version-migration info) or non-trivial cross-cutting code exploration. If yes, prepend a `research-assistant` step to that item's agent chain. The downstream specialists wait for the research findings before starting. See Step 3 routing rules for the explicit chains.\n5. Keep decomposition minimal — do not split a naturally-sequential flow into artificial fragments\n\nFor simple requests (one type, one agent, no dependencies): return a single-item plan.\n\n### Step 3 — Assign Agent Chains\n\nFor each work item, select the tightest-fitting standard chain:\n\n```\nNew feature (scope unknown)              → requirement-analyst → software-architect → system-engineer → software-engineer → sqa-engineer\nNew feature (design needed)              → software-architect → system-engineer → software-engineer → sqa-engineer\nNew feature (ready to build)             → software-engineer → sqa-engineer\nFeature needs prioritization             → product-manager → (then appropriate build chain above)\nBug fix                                  → software-engineer  (invoke fix-bug skill)\nBug fix with arch concern                → software-engineer → software-architect  (invoke architecture-review skill)\nSecurity fix                             → \u002Fsecurity-review skill directly\nTech debt \u002F refactor                     → software-engineer → code-reviewer\nTech debt needs prioritization           → product-manager → software-engineer → code-reviewer\nTest coverage gap                        → sqa-engineer\nLow-level design question                → system-engineer\nArchitecture question                    → software-architect\nBacklog \u002F prioritization question        → product-manager\nRelease \u002F milestone planning             → product-manager → devops-engineer (NuGet publish + GitHub Release)\nAgent \u002F skill \u002F command lifecycle        → agent-manager\nRules \u002F instructions \u002F hooks change      → agent-manager\nAgent memory prune \u002F audit \u002F refresh     → agent-manager\nExternal knowledge \u002F library docs needed → research-assistant → (then the appropriate chain above)\nUnfamiliar framework \u002F SDK behavior      → research-assistant → (then specialist chain)\nValidate assumption before design        → research-assistant → software-architect\nDeep cross-cutting codebase exploration  → research-assistant (standalone) or research-assistant → specialist\n```\n\n**Research-prepend rule:** Whenever a work item's chain involves design or implementation against external technology the team has not recently verified, prepend `research-assistant` as the first agent in that item's chain. The specialist receiving the work waits for the cited findings report before starting.\n\n### Step 4 — Set Priorities\n\nApply defaults, then check for overrides:\n\n- Security Fix: always P0 — never downgrade\n- Bug (regression or system blocker): P0; other bugs: P1\n- Feature: P1 by default; P2 for cosmetic or low-impact work\n- TechDebt: P2; raise to P1 only if it directly blocks a P0\u002FP1 item\n\n### Step 5 — Flag PM Consultation Requirement\n\nMark whether the PM should be consulted before execution begins:\n\n- **Yes** — if any item is Feature or TechDebt\n- **No** — if all items are Bug Fix (P0), Security Fix, Question, or Routing\n\n## Output\n\nReturn the complete work breakdown to the triage-agent:\n\n```\n### Work Breakdown: \u003Crequest summary>\n\n#### Classification\n\u003CType(s)> — \u003Creason>\n\n#### Work Items\n| ID | Type | Priority | Description | Depends On | Parallel With | Agent Chain |\n|---|---|---|---|---|---|---|\n| WI-001 | Feature | P1 | Add X capability | — | — | req-analyst → sw-arch → sys-eng → sw-eng → sqa |\n| WI-002 | Bug Fix | P0 | Fix Y crash in Z | — | — | software-engineer |\n\n#### Execution Waves\n- Wave 1 (parallel): WI-002 (P0 — immediate), WI-001 (pending PM priority confirmation)\n- Wave 2 (after WI-001 completes): WI-003\n\n#### PM Consultation Required\n\u003CYes — Feature items WI-001 need prioritization before routing>\nOR\n\u003CNo — all items are P0 bug\u002Fsecurity fixes, routing immediately>\n```\n",{"name":5,"description":7},"main","00b2c68281930728ee390bb16cec32b88d2caac7",".github\u002Fskills\u002Ftriage","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine","https:\u002F\u002Fgithub.com\u002Frafsanulhasan","\r\n    MCSD || A-CSD || Software Architect\r\n\r\n","2026-06-06 07:47:06",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add rafsanulhasan\u002FHypermediaEngine --skill triage",{"tool":55,"command":56},"bunx","bunx skills add rafsanulhasan\u002FHypermediaEngine --skill triage",{"tool":58,"command":59},"pnpm","pnpm dlx skills add rafsanulhasan\u002FHypermediaEngine --skill triage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ftriage\u002FSKILL.md",true,[],[64,94,114,133,162,188],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":73,"publishedAt":37},"01M6KWEJD606FG3DBBRM0W4DKW","write-tests","Test implementation skill for HypermediaEngine. Takes a confirmed test plan from design-test-cases and produces compilable, runnable xUnit tests following project conventions. Validates coverage quality through mutation testing. Invoked by the sqa-engineer agent after the test plan is approved.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fwrite-tests\u002FSKILL.md",[70],{"categoryNo":71,"categoryName":72,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93],"write tests","write","tests","testing","design","test","project conventions","test plan","Bash","plan","quality","xunit","read","edit","coverage","engineer","mutation testing","project","mutation","for",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":37},"01M6KWEF2XQ00C1Y6QCK7YHZ1H","write-documentation","Structured documentation writing workflow for HypermediaEngine. Writes or updates README.md files at the repo root and in each project directory (src\u002F, tests\u002F, samples\u002F, etc.) based on current implementation, ADRs, and architecture decisions.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fwrite-documentation\u002FSKILL.md",[],[101,75,102,103,104,105,106,82,107,108,109,110,86,87,111,91,76,112,113,93],"documentation","write documentation","writing","directory","workflow","architecture","src","repo","decisions","README","files","updates","at",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":37},"01M6KWEBDXTXAVPQ3BHS3YYYNT","write-adr","Writes a numbered Architecture Decision Record (ADR) for a significant architectural choice in the HypermediaEngine project. Invoked by the software-architect agent whenever a consequential design decision is made or ratified. Saves the ADR to docs\u002Farchitecture\u002Fdecisions\u002F.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fwrite-adr\u002FSKILL.md",[],[121,75,122,78,123,106,124,125,126,127,109,86,128,129,91,130,131,93,132],"adr","write adr","docs","architect","decision","choice","grep","architecture decision record","record","software","opus","architecture decision",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":145,"publishedAt":37},"01M6KWE76TM3QHGQ08PEB3KY6D","tunit-playwright-ui-testing","Comprehensive guidance for writing coded end-to-end UI tests in C# using TUnit.Playwright. Tests inherit from PageTest — the base class manages all browser lifecycle. Covers NuGet setup, PageTest inheritance, Page Object Model, browser configuration, parallelism limiting, and CI integration. Based on the official TUnit docs at https:\u002F\u002Ftunit.dev\u002Fdocs\u002Fexamples\u002Fplaywright.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ftunit-playwright-ui-testing\u002FSKILL.md",[139,140],{"categoryNo":71,"categoryName":72,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":141,"categoryName":142,"taxonomyType":143,"taxonomyTypeDesc":144},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[77,146,147,148,149,150,151,103,152,153,154,155,156,157,158,159,76,160,161,93],"playwright","ui","playwright ui testing","ui testing","tunit","tunit playwright ui testing","official","dev","examples","ci","lifecycle","model","page","inheritance","end","object",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":172,"publishedAt":37},"01M6KWDZ3W9ZKPR7FTTTSX8H2K","system-design","Expert system design skill. Use PROACTIVELY to design systems, review architectures, and assist software engineers in learning design principles and implementing them in the code with design patterns.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fsystem-design\u002FSKILL.md",[168,171],{"categoryNo":169,"categoryName":170,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":141,"categoryName":142,"taxonomyType":143,"taxonomyTypeDesc":144},[78,173,174,175,176,177,178,127,86,179,180,181,182,183,184,130,185,186,34,187],"system","system design","web","design systems","learning","haiku","use","design patterns","design principles","expert","patterns","systems","architectures","principles","implementing",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":194,"publishedAt":37},"01M6KWDVXNF6T2JTMV23RJGAF6","spec-driven-development","Manages the full lifecycle of a feature specification — from collaborative drafting to enforcement during implementation and testing.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fspec-driven-development\u002FSKILL.md",[],[195,196,197,198,199,77,156,82,127,86,75,87,200,201,202,203,204,205,206,207],"spec","spec driven development","development","spec driven","driven","enforcement","implementation","specification","analyst","full","feature","sonnet","feature specification"]