[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KW94GRG74EX4PTK7T52N63":3,"skill-same:01M6KW94GRG74EX4PTK7T52N63":70},{"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":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M6KW94GRG74EX4PTK7T52N63","agent-selection",null,"Expert agent selection and orchestration skill. Use PROACTIVELY to pick the most suitable agent for a task and to decide among four orchestration modes — direct single-agent delegation, parallel independent subagents, sequential SDLC Agent Teams, or a full SDLC traversal — based on task complexity, required expertise, and whether the work needs collaboration.","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\u002Fagent-selection\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"agent selection","selection","use","modes","expertise","for","task","expert","agent teams","complexity","orchestration","sdlc","decide","work","pick","parallel","direct","delegation","teams","collaboration","2026-11-10 10:12:30",false,"---\nname: agent-selection\ndescription: Expert agent selection and orchestration skill. Use PROACTIVELY to pick the most suitable agent for a task and to decide among four orchestration modes — direct single-agent delegation, parallel independent subagents, sequential SDLC Agent Teams, or a full SDLC traversal — based on task complexity, required expertise, and whether the work needs collaboration.\n---\n\n# Agent Selection and Orchestration\n\nThis is the expert agent selection skill. Use PROACTIVELY to select the most suitable agent for a given task, based on the task requirements and agent capabilities. Also use this skill to orchestrate multi-agent workflows when a task requires multiple agents, skills, or expertise.\n\n## Workflow\n\n```\n(research-assistant — optional, when knowledge-dependent) → requirement-analyst → software-architect + system-engineer → software-engineer → (sqa-engineer + documentation-writer) → code-reviewer\n```\n\nUse `triage-agent` to orchestrate multi-agent workflows. When the work depends on external knowledge (library\u002FAPI\u002FSDK docs, unfamiliar framework, current best practices, validating assumptions before design, deep cross-cutting code exploration), prepend `research-assistant` as the first step before any specialist work. After `software-engineer` completes any implementation work (feature, bug fix, or refactor), `sqa-engineer` and `documentation-writer` start in parallel.\n\n## Agent Reference\n\n- **research-assistant** — Read-only research specialist. Invoke when external knowledge is needed: library\u002FAPI\u002FSDK docs, unfamiliar framework behavior, version-migration info, current best practices, validating assumptions before design or implementation, or non-trivial cross-cutting code exploration where a single search is insufficient. Returns a cited, structured findings report. Prefer this over any agent doing ad-hoc web search themselves. Valid as a **first step** in sequential SDLC chains when the work is knowledge-dependent (e.g., before `requirement-analyst` or `software-architect` when external tech is involved).\n\n- **requirement-analyst** — Analyzes requirements. Invoke before any feature work begins.\n\n- **software-architect** — Designs high-level system architecture. Invoke after `requirement-analyst` completes, and after `software-engineer` finishes to validate architectural integrity.\n\n- **system-engineer** — Designs low-level structure: SOLID, design patterns, monads, discriminated unions. Collaborates with `software-architect` to translate requirements into concrete design. Also validates implementation after `software-engineer` finishes.\n\n- **software-engineer** — Implements features, fixes bugs, refactors. Invoke after architecture and design are defined.\n\n- **code-reviewer** — Reviews implementation and test cases after `software-engineer`, `sqa-engineer`, and `documentation-writer` complete their work.\n\n- **sqa-engineer** — Designs and writes test cases, validates tests after `software-engineer` implements features, fixes bugs, and refactors code. Runs in parallel with `documentation-writer`.\n\n- **triage-agent** — Orchestrates and manages multi-agent workflows. Use when a task spans multiple agents or requires coordinated parallel execution.\n\n- **product-manager** — Owns the product backlog, prioritization, and release planning. Consult before starting Feature or TechDebt work. Invoke for release planning and backlog health reviews.\n\n- **documentation-writer** — Writes and maintains documentation, updates README, and updates other documentation such as release notes. Invoked after `software-engineer` completes any implementation work. Runs in parallel with `sqa-engineer`.\n\n- **agent-manager** — **Exclusive owner of all agent artifacts.** Always route here (Mode 1, direct delegation — no SDLC chain) for: agent definitions (`.github\u002Fagents\u002F`, `.claude\u002Fagents\u002F`), skill files (`.github\u002Fskills\u002F`), hooks, rules\u002Finstructions (`.claude\u002Frules\u002F`, `.github\u002Finstructions\u002F`), and commands\u002Fprompts (`.claude\u002Fcommands\u002F`, `.github\u002Fprompts\u002F`). Also handles agent memory prune, audit, and refresh. **Never route these requests to `software-engineer` or any SDLC chain.**\n\n## Decision Framework\n\nUse the following decision tree to pick the right orchestration mode. Always start by analyzing the task: desired outcome, constraints, required expertise, and whether collaboration between roles is required.\n\n### The four orchestration modes\n\n| Mode | When to use | How to execute |\n|------|-------------|----------------|\n| **1. Direct single-agent delegation** | One agent's expertise fully covers the task. No collaboration or SDLC traversal needed. | Select the agent, hand off with the full Handoff Checklist below. Done. |\n| **2. Parallel independent subagents** | Task naturally splits into sub-tasks that do NOT need to talk to each other (e.g., research, parallel reviews, independent analyses). | Spawn multiple subagents in parallel. `triage-agent` synthesizes the combined output. |\n| **3. Agent Teams (sequential SDLC)** | Task requires collaboration between roles — design must inform implementation, implementation must inform testing, etc. | Spawn one or more Agent Teams. Each team follows the sequential SDLC chain with explicit handoffs. |\n| **4. Full SDLC routing** | Task is complex\u002Flarge enough that it must traverse the entire SDLC workflow (requirements → architecture → implementation → test\u002Fdocs → review). | Consult `product-manager` first to decompose into subtasks, then orchestrate per-subtask SDLC teams via `triage-agent`. |\n\n### Selection decision tree\n\n1. **Can a single agent fully own this task?**\n   - Yes → Mode 1 (Direct single-agent delegation). Hand off and stop.\n   - No → continue.\n2. **Are the sub-tasks independent (no collaboration needed between them)?**\n   - Yes → Mode 2 (Parallel independent subagents). Spawn in parallel; `triage-agent` synthesizes.\n   - No → continue.\n3. **Is the task simple-but-SDLC OR complex\u002Flarge?**\n   - Consult `product-manager` to break the task into subtasks.\n   - Then choose between Mode 3 (one Agent Team per subtask, sequential SDLC) or Mode 4 (full SDLC traversal across multiple subtasks, coordinated by `triage-agent`).\n4. **Continuously monitor.** If progress reveals new constraints or scope, return to step 1 and re-select.\n\n## Rules for Multi-Agent Workflow Orchestration\n\n- **Agent artifact work** → delegate directly to `agent-manager` (Mode 1). **Hard rule** — agent definitions, skills, hooks, rules\u002Finstructions, and commands\u002Fprompts must never be handled by `software-engineer` or routed through any SDLC chain. Triggers: create, update, fix, or add any of: agent, skill, hook, rule, instruction, command, prompt.\n\n- **Research work** → delegate to `research-assistant`. For broad, multi-angle research (comparison studies, surveys of competing options), spawn **3–5 `research-assistant` subagents in parallel**, each with a distinct angle; `triage-agent` then synthesizes findings into a single report. Triggers: \"external knowledge needed\", \"library\u002FAPI\u002FSDK docs\", \"unfamiliar framework\", \"validate assumption before design\", \"deep cross-cutting code exploration where Explore is insufficient\".\n- **Design and implementation work** → follow the SDLC workflow with `triage-agent` orchestrating end to end.\n  - When a complex task is decomposed into subtasks, run an SDLC workflow **per subtask**:\n    - **No collaboration needed within a subtask** → spawn parallel subagent teams per SDLC role to work simultaneously; `triage-agent` synthesizes outputs.\n    - **Collaboration needed within a subtask** → spawn an **Agent Team** that follows the sequential SDLC workflow with clear, explicit handoffs between roles.\n  - **Collaboration needed across the whole complex task** → spawn an Agent Team per subtask; each team follows the sequential SDLC; within each team, use parallel subagents per role where it accelerates the work without harming coherence. `triage-agent` coordinates inter-team handoffs.\n- **Always prefer the smallest orchestration that fits.** Do not escalate to Mode 3 or 4 if Mode 1 or 2 will suffice.\n- **Never skip `product-manager`** for backlog-affecting or release-affecting work.\n- **Never skip `triage-agent`** when more than one agent is involved.\n\n### Handoff Checklist\n\nWhen delegating to any agent (single or part of a team), the handoff must include:\n\n- **Required context** — links to the originating user prompt, prior agent outputs, relevant files, and constraints discovered so far.\n- **Instructions** — the specific question to answer or work to perform, scoped to the agent's role.\n- **Expected output format** — e.g., findings report, ADR, design document, code diff, test plan, review comments.\n- **Success criteria** — how the receiving agent (or `triage-agent`) will know the handoff is complete and acceptable.\n- **Next-hop hint** — which agent (if any) receives this agent's output, so the receiving agent can shape its output appropriately.\n","# Agent Selection and Orchestration\n\nThis is the expert agent selection skill. Use PROACTIVELY to select the most suitable agent for a given task, based on the task requirements and agent capabilities. Also use this skill to orchestrate multi-agent workflows when a task requires multiple agents, skills, or expertise.\n\n## Workflow\n\n```\n(research-assistant — optional, when knowledge-dependent) → requirement-analyst → software-architect + system-engineer → software-engineer → (sqa-engineer + documentation-writer) → code-reviewer\n```\n\nUse `triage-agent` to orchestrate multi-agent workflows. When the work depends on external knowledge (library\u002FAPI\u002FSDK docs, unfamiliar framework, current best practices, validating assumptions before design, deep cross-cutting code exploration), prepend `research-assistant` as the first step before any specialist work. After `software-engineer` completes any implementation work (feature, bug fix, or refactor), `sqa-engineer` and `documentation-writer` start in parallel.\n\n## Agent Reference\n\n- **research-assistant** — Read-only research specialist. Invoke when external knowledge is needed: library\u002FAPI\u002FSDK docs, unfamiliar framework behavior, version-migration info, current best practices, validating assumptions before design or implementation, or non-trivial cross-cutting code exploration where a single search is insufficient. Returns a cited, structured findings report. Prefer this over any agent doing ad-hoc web search themselves. Valid as a **first step** in sequential SDLC chains when the work is knowledge-dependent (e.g., before `requirement-analyst` or `software-architect` when external tech is involved).\n\n- **requirement-analyst** — Analyzes requirements. Invoke before any feature work begins.\n\n- **software-architect** — Designs high-level system architecture. Invoke after `requirement-analyst` completes, and after `software-engineer` finishes to validate architectural integrity.\n\n- **system-engineer** — Designs low-level structure: SOLID, design patterns, monads, discriminated unions. Collaborates with `software-architect` to translate requirements into concrete design. Also validates implementation after `software-engineer` finishes.\n\n- **software-engineer** — Implements features, fixes bugs, refactors. Invoke after architecture and design are defined.\n\n- **code-reviewer** — Reviews implementation and test cases after `software-engineer`, `sqa-engineer`, and `documentation-writer` complete their work.\n\n- **sqa-engineer** — Designs and writes test cases, validates tests after `software-engineer` implements features, fixes bugs, and refactors code. Runs in parallel with `documentation-writer`.\n\n- **triage-agent** — Orchestrates and manages multi-agent workflows. Use when a task spans multiple agents or requires coordinated parallel execution.\n\n- **product-manager** — Owns the product backlog, prioritization, and release planning. Consult before starting Feature or TechDebt work. Invoke for release planning and backlog health reviews.\n\n- **documentation-writer** — Writes and maintains documentation, updates README, and updates other documentation such as release notes. Invoked after `software-engineer` completes any implementation work. Runs in parallel with `sqa-engineer`.\n\n- **agent-manager** — **Exclusive owner of all agent artifacts.** Always route here (Mode 1, direct delegation — no SDLC chain) for: agent definitions (`.github\u002Fagents\u002F`, `.claude\u002Fagents\u002F`), skill files (`.github\u002Fskills\u002F`), hooks, rules\u002Finstructions (`.claude\u002Frules\u002F`, `.github\u002Finstructions\u002F`), and commands\u002Fprompts (`.claude\u002Fcommands\u002F`, `.github\u002Fprompts\u002F`). Also handles agent memory prune, audit, and refresh. **Never route these requests to `software-engineer` or any SDLC chain.**\n\n## Decision Framework\n\nUse the following decision tree to pick the right orchestration mode. Always start by analyzing the task: desired outcome, constraints, required expertise, and whether collaboration between roles is required.\n\n### The four orchestration modes\n\n| Mode | When to use | How to execute |\n|------|-------------|----------------|\n| **1. Direct single-agent delegation** | One agent's expertise fully covers the task. No collaboration or SDLC traversal needed. | Select the agent, hand off with the full Handoff Checklist below. Done. |\n| **2. Parallel independent subagents** | Task naturally splits into sub-tasks that do NOT need to talk to each other (e.g., research, parallel reviews, independent analyses). | Spawn multiple subagents in parallel. `triage-agent` synthesizes the combined output. |\n| **3. Agent Teams (sequential SDLC)** | Task requires collaboration between roles — design must inform implementation, implementation must inform testing, etc. | Spawn one or more Agent Teams. Each team follows the sequential SDLC chain with explicit handoffs. |\n| **4. Full SDLC routing** | Task is complex\u002Flarge enough that it must traverse the entire SDLC workflow (requirements → architecture → implementation → test\u002Fdocs → review). | Consult `product-manager` first to decompose into subtasks, then orchestrate per-subtask SDLC teams via `triage-agent`. |\n\n### Selection decision tree\n\n1. **Can a single agent fully own this task?**\n   - Yes → Mode 1 (Direct single-agent delegation). Hand off and stop.\n   - No → continue.\n2. **Are the sub-tasks independent (no collaboration needed between them)?**\n   - Yes → Mode 2 (Parallel independent subagents). Spawn in parallel; `triage-agent` synthesizes.\n   - No → continue.\n3. **Is the task simple-but-SDLC OR complex\u002Flarge?**\n   - Consult `product-manager` to break the task into subtasks.\n   - Then choose between Mode 3 (one Agent Team per subtask, sequential SDLC) or Mode 4 (full SDLC traversal across multiple subtasks, coordinated by `triage-agent`).\n4. **Continuously monitor.** If progress reveals new constraints or scope, return to step 1 and re-select.\n\n## Rules for Multi-Agent Workflow Orchestration\n\n- **Agent artifact work** → delegate directly to `agent-manager` (Mode 1). **Hard rule** — agent definitions, skills, hooks, rules\u002Finstructions, and commands\u002Fprompts must never be handled by `software-engineer` or routed through any SDLC chain. Triggers: create, update, fix, or add any of: agent, skill, hook, rule, instruction, command, prompt.\n\n- **Research work** → delegate to `research-assistant`. For broad, multi-angle research (comparison studies, surveys of competing options), spawn **3–5 `research-assistant` subagents in parallel**, each with a distinct angle; `triage-agent` then synthesizes findings into a single report. Triggers: \"external knowledge needed\", \"library\u002FAPI\u002FSDK docs\", \"unfamiliar framework\", \"validate assumption before design\", \"deep cross-cutting code exploration where Explore is insufficient\".\n- **Design and implementation work** → follow the SDLC workflow with `triage-agent` orchestrating end to end.\n  - When a complex task is decomposed into subtasks, run an SDLC workflow **per subtask**:\n    - **No collaboration needed within a subtask** → spawn parallel subagent teams per SDLC role to work simultaneously; `triage-agent` synthesizes outputs.\n    - **Collaboration needed within a subtask** → spawn an **Agent Team** that follows the sequential SDLC workflow with clear, explicit handoffs between roles.\n  - **Collaboration needed across the whole complex task** → spawn an Agent Team per subtask; each team follows the sequential SDLC; within each team, use parallel subagents per role where it accelerates the work without harming coherence. `triage-agent` coordinates inter-team handoffs.\n- **Always prefer the smallest orchestration that fits.** Do not escalate to Mode 3 or 4 if Mode 1 or 2 will suffice.\n- **Never skip `product-manager`** for backlog-affecting or release-affecting work.\n- **Never skip `triage-agent`** when more than one agent is involved.\n\n### Handoff Checklist\n\nWhen delegating to any agent (single or part of a team), the handoff must include:\n\n- **Required context** — links to the originating user prompt, prior agent outputs, relevant files, and constraints discovered so far.\n- **Instructions** — the specific question to answer or work to perform, scoped to the agent's role.\n- **Expected output format** — e.g., findings report, ADR, design document, code diff, test plan, review comments.\n- **Success criteria** — how the receiving agent (or `triage-agent`) will know the handoff is complete and acceptable.\n- **Next-hop hint** — which agent (if any) receives this agent's output, so the receiving agent can shape its output appropriately.\n",{"name":5,"description":7},"main","00b2c68281930728ee390bb16cec32b88d2caac7",".github\u002Fskills\u002Fagent-selection","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":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add rafsanulhasan\u002FHypermediaEngine --skill agent-selection",{"tool":62,"command":63},"bunx","bunx skills add rafsanulhasan\u002FHypermediaEngine --skill agent-selection",{"tool":65,"command":66},"pnpm","pnpm dlx skills add rafsanulhasan\u002FHypermediaEngine --skill agent-selection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fagent-selection\u002FSKILL.md",true,[],[71,100,120,139,168,187],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":80,"publishedAt":44},"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",[77],{"categoryNo":78,"categoryName":79,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,29],"write tests","write","tests","testing","design","test","project conventions","test plan","Bash","plan","quality","xunit","read","edit","coverage","engineer","mutation testing","project","mutation",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":44},"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",[],[107,82,108,109,110,111,112,89,113,114,115,116,93,94,117,98,83,118,119,29],"documentation","write documentation","writing","directory","workflow","architecture","src","repo","decisions","README","files","updates","at",{"skillNo":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":44},"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",[],[127,82,128,85,129,112,130,131,132,133,115,93,134,135,98,136,137,29,138],"adr","write adr","docs","architect","decision","choice","grep","architecture decision record","record","software","opus","architecture decision",{"skillNo":140,"name":141,"nameZh":6,"description":142,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":143,"categories":144,"keywords":151,"publishedAt":44},"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",[145,146],{"categoryNo":78,"categoryName":79,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":147,"categoryName":148,"taxonomyType":149,"taxonomyTypeDesc":150},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[84,152,153,154,155,156,157,109,158,159,160,161,162,163,164,165,83,166,167,29],"playwright","ui","playwright ui testing","ui testing","tunit","tunit playwright ui testing","official","dev","examples","ci","lifecycle","model","page","inheritance","end","object",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":175,"publishedAt":44},"01M6KWE44A738GDK65QS02XJBG","triage","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.","https:\u002F\u002Fgithub.com\u002Frafsanulhasan\u002FHypermediaEngine\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ftriage\u002FSKILL.md",[174],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[170,176,177,37,178,179,30,180,181,182,183,184,185,186],"routing","classification","user","dependency","priorities","decomposition","user request","mapping","with","break","request",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":197,"publishedAt":44},"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",[193,196],{"categoryNo":194,"categoryName":195,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":147,"categoryName":148,"taxonomyType":149,"taxonomyTypeDesc":150},[85,198,199,200,201,202,203,133,93,26,204,205,31,206,207,136,208,209,184,210],"system","system design","web","design systems","learning","haiku","design patterns","design principles","patterns","systems","architectures","principles","implementing"]