[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DNEHYWZSTWVWV60HWR8CC3":3,"skill-same:01M6DNEHYWZSTWVWV60HWR8CC3":58},{"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":18,"publishedAt":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M6DNEHYWZSTWVWV60HWR8CC3","aac-forge-idea",null,"Domain-agnostic Socratic idea pressure-testing. Use when the user has a half-formed idea and wants to harden or kill it cheaply, one question at a time. Supports an adversarial attack mode and optional persona rooms resolved from the installed agent roster. Menu code FI.","msayedshokry\u002FAgileAgentCanvasExt","msayedshokry","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F35009459?v=4","01M6DN5RZZ297CGWTNJ6ERZQ8W","Mohamed Sayed","01M6DN5S4XS7SVCSXZRW2XR0XF",3,"MIT","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Fskills\u002Faac-forge-idea\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31],"forge","idea","aac forge idea","testing","code","persona","question","user","use","kill","domain","time","harden","2026-11-10 10:12:30",false,"---\nname: aac-forge-idea\ndescription: 'Domain-agnostic Socratic idea pressure-testing. Use when the user has a half-formed idea and wants to harden or kill it cheaply, one question at a time. Supports an adversarial attack mode and optional persona rooms resolved from the installed agent roster. Menu code FI.'\n---\n\n# Forge Idea\n\nPressure-test a half-formed idea through Socratic, one-question-at-a-time interrogation until the idea hardens, proves out, or dies cheaply. The point of forge-idea is **not** to generate more ideas — that is brainstorming's job. The point is to take one idea and see if it survives contact with a hostile interlocutor.\n\n## When to Use\n\n- The user says \"I have an idea\" \u002F \"what do you think of X\" \u002F \"should I build this\" \u002F \"forge this\" \u002F \"FI\" \u002F \"pressure-test this\"\n- The user has a half-formed concept that needs sharpening before any planning\n- A brainstorming session produced a candidate the user wants to validate\n- The user is at the very start of a project and wants to discover the real shape of the problem\n\nDo NOT use for:\n\n- Bulk ideation (use `aac-brainstorming`)\n- Implementation details (use `aac-create-architecture` or `aac-spec`)\n- Document review (use `aac-advanced-elicitation`)\n\n## Modes\n\n- **Socratic** (default) — one question at a time, deepening. The agent asks; the user answers; the agent reflects and asks the next question that targets the current weakest link.\n- **Adversarial** — switch on with `--attack` or by answering \"Attack: on\" to the mode prompt. The agent's questions become hostile: pre-mortem, red team, kill shot. The user is forced to defend. Best for \"I think this is great, prove me wrong.\"\n- **Persona room** — switch on with `--room` or by answering \"Room: on\". Each question comes from a different persona resolved from the installed agent roster (PM, Dev, QA, Architect, etc.). Multiple agents, in turn, attack the idea from their angle. Best for cross-functional validation.\n- **Combined** — `--attack --room` is the strongest setup: hostile questions from rotating personas. Use sparingly; it is exhausting.\n\n## The Loop\n\n1. The user states the idea in one or two sentences. The agent does not paraphrase back — paraphrasing is friction.\n2. The agent asks **ONE** question. Waits for the answer. Never bundles two questions into one round.\n3. Based on the answer, the agent:\n   - Notes a residue (a fact, assumption, or contradiction the answer revealed) — kept in conversation memory, not persisted unless the user opts in\n   - Picks the next question — the one that most threatens the idea's weakest link **right now**\n   - Asks it. Waits.\n4. After N rounds (default 7, configurable with `--rounds N`), the agent offers a verdict:\n   - **HARDENED** — the idea has survived the pressure. Move to brief or implementation.\n   - **DEAD** — the idea collapsed. Note why. Do not revive unless the user asks.\n   - **UNRESOLVED** — the user is still defending gaps. Offer to continue, switch modes, or stop.\n\nThe verdict is honest, not optimistic. A \"HARDENED\" verdict is rare and should be earned.\n\n## On Activation\n\n1. **Parse arguments** — check for `--attack`, `--room`, `--rounds N`, `--headless`.\n2. **Load config** from `{project-root}\u002F_bmad\u002Fcore\u002Fconfig.yaml`:\n   - `user_name` for greeting\n   - `communication_language` for all speech\n3. **Resolve the agent roster** (only if `--room` is set) by running:\n   ```bash\n   python3 {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_config.py --project-root {project-root} --key agents\n   ```\n   Pick 3-5 personas with the most orthogonal expertise to the idea. Each will ask one question per round in turn.\n4. **Welcome the user** and surface the modes:\n   - \"Socratic (default) — I ask one question at a time. You answer. We go deeper.\"\n   - \"Adversarial (`--attack`) — I try to kill the idea. You defend.\"\n   - \"Persona room (`--room`) — Different agents take turns questioning. Useful for cross-functional check.\"\n   - \"Combined (`--attack --room`) — Hostile questions from rotating personas. Intense.\"\n5. **Ask for the idea**: \"State it in one or two sentences. Don't polish.\"\n\n## Question Crafting\n\nThe agent's discipline:\n\n- **One question per round.** No \"and\". No comma-spliced pairs. If two questions feel necessary, pick the one that closes more risk.\n- **Target the weakest link, not the strongest.** The strongest part of the idea is already defended; pressure-testing it wastes a round.\n- **Concretize.** Replace \"users\" with a specific person. Replace \"fast\" with a number. Replace \"easy\" with a scenario. Vague answers reveal vague ideas.\n- **Force a stance.** \"What would have to be true for this to work?\" beats \"do you think this will work?\"\n- **Track what you have learned.** The residue list grows. When the user contradicts an earlier answer, name it.\n\nCommon question types to rotate through:\n\n- **Concretize** — \"Give me a specific user. Not a persona, a person.\"\n- **Why-now** — \"What changed in the world that makes this possible or necessary now?\"\n- **Pre-mortem** — \"It's 18 months from now and this failed. Why?\"\n- **Substitution** — \"What if you removed the central mechanism — does anything survive?\"\n- **Adjacency** — \"What is the closest existing thing? Why doesn't it just do this?\"\n- **Cost** — \"What does this cost if it succeeds? Not money — attention, focus, optionality.\"\n- **Counter-user** — \"Who loses if this wins?\"\n- **Unstated assumption** — \"You just claimed X. What if X is wrong?\"\n\n## Output (Optional)\n\nAt the verdict step, the agent offers to write:\n\n- **A brief** — 1-page summary of the hardened idea: problem, who, why now, shape, next concrete step. This brief feeds `aac-spec` (full spec) or `aac-quick-dev` (small change). Format matches the upstream `aac-product-brief` schema.\n- **A residue log** — append-only log of the rounds, the questions, the answers, the assumptions revealed. Useful as input to a future forge-idea session, or to seed a future `aac-advanced-elicitation` review.\n\nThe brief is opt-in. The user may want to keep the idea private until they have shared it elsewhere first.\n\n## Halt Conditions\n\nHalt immediately if:\n\n- The user says \"stop\" \u002F \"kill\" \u002F \"done\" \u002F \"that's enough\" — any natural phrasing\n- The user has nothing substantive to add (twice in a row, the second time is the halt)\n- The idea has clearly died (the user agrees with the kill assessment)\n\nWhen halting, do not pad with summaries unless the user asks. A clean exit is the point of the skill.\n\n## Headless Mode\n\n`--headless` runs the loop non-interactively:\n\n1. The idea is read from `{project-root}\u002Fforge-input.md` (or the first user message).\n2. The agent runs all N rounds in one pass, asking questions and answering them itself as a hostile user-of-one (best-effort — headless is weaker than interactive for forge-idea because the user is the source of new information).\n3. The verdict and brief are written to `{project-root}\u002Fforge-output.md`.\n4. The residue is written to `{project-root}\u002Fforge-residue.md`.\n\nHeadless is useful for overnight batch processing of idea backlogs, not for the idea you actually care about.\n\n## Success Metrics\n\n- The user states the idea clearly within 2 sentences (no prompt-induced bloat)\n- One question per round, never a barrage\n- Each question targets the current weakest link, not the strongest\n- The verdict (HARDENED \u002F DEAD \u002F UNRESOLVED) is honest, not optimistic\n- The optional brief is concise (1 page) and actionable (has a next concrete step)\n- The residue log is append-only and never edited\n\n## Failure Modes\n\n- Asking two questions in one round (\"What about X? And also Y?\") — wastes a round\n- Paraphrasing the user's idea back to them — friction\n- Generating ideas instead of testing one — that's brainstorming\n- Marking HARDENED too early — undermines the skill\n- Marking DEAD before the user has defended — paternalism\n- Continuing past UNRESOLVED without checking in — the user may be stuck\n","# Forge Idea\n\nPressure-test a half-formed idea through Socratic, one-question-at-a-time interrogation until the idea hardens, proves out, or dies cheaply. The point of forge-idea is **not** to generate more ideas — that is brainstorming's job. The point is to take one idea and see if it survives contact with a hostile interlocutor.\n\n## When to Use\n\n- The user says \"I have an idea\" \u002F \"what do you think of X\" \u002F \"should I build this\" \u002F \"forge this\" \u002F \"FI\" \u002F \"pressure-test this\"\n- The user has a half-formed concept that needs sharpening before any planning\n- A brainstorming session produced a candidate the user wants to validate\n- The user is at the very start of a project and wants to discover the real shape of the problem\n\nDo NOT use for:\n\n- Bulk ideation (use `aac-brainstorming`)\n- Implementation details (use `aac-create-architecture` or `aac-spec`)\n- Document review (use `aac-advanced-elicitation`)\n\n## Modes\n\n- **Socratic** (default) — one question at a time, deepening. The agent asks; the user answers; the agent reflects and asks the next question that targets the current weakest link.\n- **Adversarial** — switch on with `--attack` or by answering \"Attack: on\" to the mode prompt. The agent's questions become hostile: pre-mortem, red team, kill shot. The user is forced to defend. Best for \"I think this is great, prove me wrong.\"\n- **Persona room** — switch on with `--room` or by answering \"Room: on\". Each question comes from a different persona resolved from the installed agent roster (PM, Dev, QA, Architect, etc.). Multiple agents, in turn, attack the idea from their angle. Best for cross-functional validation.\n- **Combined** — `--attack --room` is the strongest setup: hostile questions from rotating personas. Use sparingly; it is exhausting.\n\n## The Loop\n\n1. The user states the idea in one or two sentences. The agent does not paraphrase back — paraphrasing is friction.\n2. The agent asks **ONE** question. Waits for the answer. Never bundles two questions into one round.\n3. Based on the answer, the agent:\n   - Notes a residue (a fact, assumption, or contradiction the answer revealed) — kept in conversation memory, not persisted unless the user opts in\n   - Picks the next question — the one that most threatens the idea's weakest link **right now**\n   - Asks it. Waits.\n4. After N rounds (default 7, configurable with `--rounds N`), the agent offers a verdict:\n   - **HARDENED** — the idea has survived the pressure. Move to brief or implementation.\n   - **DEAD** — the idea collapsed. Note why. Do not revive unless the user asks.\n   - **UNRESOLVED** — the user is still defending gaps. Offer to continue, switch modes, or stop.\n\nThe verdict is honest, not optimistic. A \"HARDENED\" verdict is rare and should be earned.\n\n## On Activation\n\n1. **Parse arguments** — check for `--attack`, `--room`, `--rounds N`, `--headless`.\n2. **Load config** from `{project-root}\u002F_bmad\u002Fcore\u002Fconfig.yaml`:\n   - `user_name` for greeting\n   - `communication_language` for all speech\n3. **Resolve the agent roster** (only if `--room` is set) by running:\n   ```bash\n   python3 {project-root}\u002F_bmad\u002Fscripts\u002Fresolve_config.py --project-root {project-root} --key agents\n   ```\n   Pick 3-5 personas with the most orthogonal expertise to the idea. Each will ask one question per round in turn.\n4. **Welcome the user** and surface the modes:\n   - \"Socratic (default) — I ask one question at a time. You answer. We go deeper.\"\n   - \"Adversarial (`--attack`) — I try to kill the idea. You defend.\"\n   - \"Persona room (`--room`) — Different agents take turns questioning. Useful for cross-functional check.\"\n   - \"Combined (`--attack --room`) — Hostile questions from rotating personas. Intense.\"\n5. **Ask for the idea**: \"State it in one or two sentences. Don't polish.\"\n\n## Question Crafting\n\nThe agent's discipline:\n\n- **One question per round.** No \"and\". No comma-spliced pairs. If two questions feel necessary, pick the one that closes more risk.\n- **Target the weakest link, not the strongest.** The strongest part of the idea is already defended; pressure-testing it wastes a round.\n- **Concretize.** Replace \"users\" with a specific person. Replace \"fast\" with a number. Replace \"easy\" with a scenario. Vague answers reveal vague ideas.\n- **Force a stance.** \"What would have to be true for this to work?\" beats \"do you think this will work?\"\n- **Track what you have learned.** The residue list grows. When the user contradicts an earlier answer, name it.\n\nCommon question types to rotate through:\n\n- **Concretize** — \"Give me a specific user. Not a persona, a person.\"\n- **Why-now** — \"What changed in the world that makes this possible or necessary now?\"\n- **Pre-mortem** — \"It's 18 months from now and this failed. Why?\"\n- **Substitution** — \"What if you removed the central mechanism — does anything survive?\"\n- **Adjacency** — \"What is the closest existing thing? Why doesn't it just do this?\"\n- **Cost** — \"What does this cost if it succeeds? Not money — attention, focus, optionality.\"\n- **Counter-user** — \"Who loses if this wins?\"\n- **Unstated assumption** — \"You just claimed X. What if X is wrong?\"\n\n## Output (Optional)\n\nAt the verdict step, the agent offers to write:\n\n- **A brief** — 1-page summary of the hardened idea: problem, who, why now, shape, next concrete step. This brief feeds `aac-spec` (full spec) or `aac-quick-dev` (small change). Format matches the upstream `aac-product-brief` schema.\n- **A residue log** — append-only log of the rounds, the questions, the answers, the assumptions revealed. Useful as input to a future forge-idea session, or to seed a future `aac-advanced-elicitation` review.\n\nThe brief is opt-in. The user may want to keep the idea private until they have shared it elsewhere first.\n\n## Halt Conditions\n\nHalt immediately if:\n\n- The user says \"stop\" \u002F \"kill\" \u002F \"done\" \u002F \"that's enough\" — any natural phrasing\n- The user has nothing substantive to add (twice in a row, the second time is the halt)\n- The idea has clearly died (the user agrees with the kill assessment)\n\nWhen halting, do not pad with summaries unless the user asks. A clean exit is the point of the skill.\n\n## Headless Mode\n\n`--headless` runs the loop non-interactively:\n\n1. The idea is read from `{project-root}\u002Fforge-input.md` (or the first user message).\n2. The agent runs all N rounds in one pass, asking questions and answering them itself as a hostile user-of-one (best-effort — headless is weaker than interactive for forge-idea because the user is the source of new information).\n3. The verdict and brief are written to `{project-root}\u002Fforge-output.md`.\n4. The residue is written to `{project-root}\u002Fforge-residue.md`.\n\nHeadless is useful for overnight batch processing of idea backlogs, not for the idea you actually care about.\n\n## Success Metrics\n\n- The user states the idea clearly within 2 sentences (no prompt-induced bloat)\n- One question per round, never a barrage\n- Each question targets the current weakest link, not the strongest\n- The verdict (HARDENED \u002F DEAD \u002F UNRESOLVED) is honest, not optimistic\n- The optional brief is concise (1 page) and actionable (has a next concrete step)\n- The residue log is append-only and never edited\n\n## Failure Modes\n\n- Asking two questions in one round (\"What about X? And also Y?\") — wastes a round\n- Paraphrasing the user's idea back to them — friction\n- Generating ideas instead of testing one — that's brainstorming\n- Marking HARDENED too early — undermines the skill\n- Marking DEAD before the user has defended — paternalism\n- Continuing past UNRESOLVED without checking in — the user may be stuck\n",{"name":5,"description":7},"main","473351382920a74eb8f353f979a06f6f05bb5f59","resources\u002F_aac\u002Fskills\u002Faac-forge-idea",0,"https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt","https:\u002F\u002Fgithub.com\u002Fmsayedshokry","2026-08-29 02:00:07",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add msayedshokry\u002FAgileAgentCanvasExt --skill aac-forge-idea",{"tool":50,"command":51},"bunx","bunx skills add msayedshokry\u002FAgileAgentCanvasExt --skill aac-forge-idea",{"tool":53,"command":54},"pnpm","pnpm dlx skills add msayedshokry\u002FAgileAgentCanvasExt --skill aac-forge-idea","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Fskills\u002Faac-forge-idea\u002FSKILL.md",true,[],[59,86,105,118,141,157],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":75,"publishedAt":32},"01M6DNRTHE3M1XG3KDJTEF6BG6","bmad-teach-me-testing","Teach testing progressively through structured sessions. Use when user says \"lets learn testing\" or \"I want to study test practices\"","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Ftea\u002Fworkflows\u002Ftestarch\u002Fbmad-teach-me-testing\u002FSKILL.md",[65,70],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":71,"categoryName":72,"taxonomyType":73,"taxonomyTypeDesc":74},"01JBSEEDCAT000000000000039","教师与教育","PROFESSION","适用职业",[76,77,78,79,80,22,81,82,83,26,27,84,85],"bmad","me","bmad teach me testing","teach me","teach","test","sessions","learn","study","structured",{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":93,"publishedAt":32},"01M6DNRG27V77JEGMPMJVRY0Q5","aac-testarch-trace","Generate traceability matrix and quality gate decision. Use when the user says \"lets create traceability matrix\" or \"I want to analyze test coverage\"","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Ftea\u002Fworkflows\u002Ftestarch\u002Faac-testarch-trace\u002FSKILL.md",[92],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},[94,95,81,96,97,98,99,100,101,26,102,27,103,104],"aac testarch trace","trace","quality gate","create","generate","analyze","quality","decision","coverage","test coverage","gate",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":112,"publishedAt":32},"01M6DNR70G1S0DGDSHRWT1S1DD","aac-testarch-test-review","Review test quality using best practices validation. Use when user says \"lets review tests\" or \"I want to evaluate test quality\"","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Ftea\u002Fworkflows\u002Ftestarch\u002Faac-testarch-test-review\u002FSKILL.md",[111],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},[113,114,81,115,116,100,26,27,117],"review","aac testarch test review","best practices","validation","tests",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":131,"publishedAt":32},"01M6DNQXV8F40EE78ZMWGWRPJM","aac-testarch-test-design","Create system-level or epic-level test plans. Use when the user says \"lets design test plan\" or \"I want to create test strategy\"","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Ftea\u002Fworkflows\u002Ftestarch\u002Faac-testarch-test-design\u002FSKILL.md",[124,125,128],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},{"categoryNo":126,"categoryName":127,"taxonomyType":68,"taxonomyTypeDesc":69},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":129,"categoryName":130,"taxonomyType":73,"taxonomyTypeDesc":74},"01JBSEEDCAT000000000000032","设计师",[132,133,81,134,26,97,135,136,137,138,27,139,140],"aac testarch test design","test design","design","test plan","plan","system","strategy","test strategy","plans",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":32},"01M6DNQNG0T7Q5DKV3C03RY35D","aac-testarch-nfr","Audit NFR evidence for performance, security, reliability, and scalability. Use when implementation evidence exists and the user says \"audit NFR evidence\", \"audit NFRs\", or \"evaluate non-functional requirements\"","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Ftea\u002Fworkflows\u002Ftestarch\u002Faac-testarch-nfr\u002FSKILL.md",[],[148,149,150,151,152,153,26,154,155,27,156],"aac testarch nfr","reliability","evidence","implementation","scalability","requirements","audit","performance","security",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":164,"publishedAt":32},"01M6DNQDPTGB49D8AAJV4GN2H8","aac-testarch-framework","Initialize test framework with Playwright or Cypress. Use when the user says \"lets setup test framework\" or \"I want to initialize testing framework\"","https:\u002F\u002Fgithub.com\u002Fmsayedshokry\u002FAgileAgentCanvasExt\u002Fblob\u002Fmain\u002Fresources\u002F_aac\u002Ftea\u002Fworkflows\u002Ftestarch\u002Faac-testarch-framework\u002FSKILL.md",[163],{"categoryNo":66,"categoryName":67,"taxonomyType":68,"taxonomyTypeDesc":69},[165,166,167,26,27,168,169,170,81,171,22,172],"aac testarch framework","framework","initialize","testing framework","setup","test framework","playwright","cypress"]