[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CW3Z0HKNXZGSJVQKR4WW4E":3,"skill-same:01M6CW3Z0HKNXZGSJVQKR4WW4E":59},{"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":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M6CW3Z0HKNXZGSJVQKR4WW4E","brief",null,"Set the context for an upcoming review. Run when the user types \u002Fbrief, describes something they want reviewed, or wants to change what the board is focused on. Also triggered automatically when the user asks the board to review something in plain language.","stefans71\u002FFrontierBoard","stefans71","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F66725311?v=4","01M6CW3VPYK13M9K13NZZBXZ36","01M6CW3VTXG8DT51A3FN2SQM1V",6,"MIT","https:\u002F\u002Fgithub.com\u002Fstefans71\u002FFrontierBoard\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fbrief\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25,26],"review","change","run","SET","board","context","user","language","what the","2026-11-10 10:12:30",false,"---\nname: brief\ndescription: Set the context for an upcoming review. Run when the user types \u002Fbrief, describes something they want reviewed, or wants to change what the board is focused on. Also triggered automatically when the user asks the board to review something in plain language.\n---\n\n# Board of Governance — Brief\n\nPrepare the board for a specific review. Read `docs\u002FREVIEW-SOP.md` Section 5 (Brief Requirements) before composing any brief — it defines what agents need.\n\n**Key principle:** Agents are ephemeral. They have zero memory of prior reviews, prior conversations, or anything not in their inbox. The brief is everything. If you don't give it to them, they don't have it.\n\n---\n\n## Step 1: Understand What's Being Reviewed\n\nIf `\u002Fbrief` without context:\n\n> What do you want the board to review? Describe it in plain language — a file, a decision, a proposal, a document, a question.\n\nIf triggered by plain language, confirm what you understood before proceeding.\n\n---\n\n## Step 2: Detect the Domain and Artifact Type\n\nIdentify domain (software, business, HR, finance, legal, etc.) from the user's description. Check `.board\u002Fboard\u002F{agent}\u002Fcontexts\u002F` for existing context files.\n\nAlso identify the **artifact type** — this determines what broader context agents need:\n\n| Artifact Type | What Agents Need Beyond the Artifact |\n|--------------|--------------------------------------|\n| **Code diff** | Architecture of the system being changed, what the code does, why the change was made, what CLIs\u002Ftools are involved, deployment environment |\n| **Plan \u002F proposal** | Current state of the system, what exists today, what's changing, constraints, prior decisions |\n| **Architecture** | Problem being solved, scale, team, existing infrastructure, deployment model |\n| **Business decision** | Constraints, stakeholders, prior commitments, risk tolerance, timeline |\n| **Document \u002F policy** | Audience, enforcement mechanism, existing related docs |\n\nIf matching context exists: offer to use it or tailor further. If no match: tell the user you'll write one now and save it for future reviews.\n\n---\n\n## Step 3: Write or Activate Context\n\nExisting context → read it. New context → write `.board\u002Fboard\u002F{agent}\u002Fcontexts\u002F{domain}.md` for each agent. A context file gives the agent a domain-specific lens — what to look for, what questions to ask. It does not change their identity. Write each one for that specific agent's angle applied to this domain.\n\n---\n\n## Step 4: Load Deferred Work\n\nLoad deferred items from two sources:\n1. `tasks.json` — look for tasks with `\"status\": \"deferred\"`. Include their title, description, trigger condition, and severity.\n2. `.board\u002Fboard\u002FDEFERRED_WORK.md` — if it exists (legacy), read the FULL contents.\n\nDeferred items are **active evaluation targets** — agents must check whether the current review triggers any of them.\n\n---\n\n## Step 5: Gather Broader Context\n\nAsk yourself: **what context would a knowledgeable new reviewer need to evaluate this artifact?** Agents can't look things up — they only know what's in the brief.\n\nFor code reviews, read the relevant source files and include key architecture details. For plans, describe the current state of the system. For business decisions, include constraints and stakeholder context.\n\nDon't assume agents know:\n- How the system works\n- What tools, CLIs, or frameworks are involved\n- What deployment environment exists\n- What prior decisions were made and why\n- What the user's constraints are\n\nInclude what they need. Err on the side of more context, not less.\n\n---\n\n## Step 6: Write the Review Brief\n\nRound 1 (Blind Review) brief — same for all agents:\n\n1. **Context** — what is this, why is it being reviewed, who's the audience\n2. **The artifact** — full text, inline. Code diffs in full. Plans in full. Never summarize what agents can read themselves.\n3. **Broader context** — system architecture, environment, constraints, prior decisions (from Step 5)\n4. **Deferred items** — all deferred tasks from `tasks.json` (status=deferred) and `DEFERRED_WORK.md` (if exists), framed as: \"Evaluate whether your review triggers any of these deferred items. If a trigger condition is met, promote to FIX NOW with evidence.\"\n5. **Evaluation criteria** — what to evaluate, specific questions if any\n6. **Output format** — finding ID, severity (FIX NOW\u002FDEFER\u002FINFO\u002FREJECT), location, finding, recommendation\n7. **User concerns** — anything the user specifically flagged\n\nIf artifact exceeds ~50KB: executive summary + full text + section index. Over ~100KB: split into sessions.\n\n---\n\n## Step 7: Populate Inboxes\n\nFor each agent: copy context to `inbox\u002Fcontext.md`, brief to `inbox\u002Fbrief.md`, clear previous `outbox\u002Freport.md`.\n\n> Brief is ready in all inboxes. Want me to run the board now, or review the brief first?\n\n---\n\n## Round 2+ Briefs\n\nThe `\u002Frun` skill handles subsequent round briefs. If the user asks to re-brief between rounds (add a directive, change the question), this skill runs again. Always include: previous findings with positions, owner directives, deferred items, and the original artifact (ephemeral agents need it every round).\n","# Board of Governance — Brief\n\nPrepare the board for a specific review. Read `docs\u002FREVIEW-SOP.md` Section 5 (Brief Requirements) before composing any brief — it defines what agents need.\n\n**Key principle:** Agents are ephemeral. They have zero memory of prior reviews, prior conversations, or anything not in their inbox. The brief is everything. If you don't give it to them, they don't have it.\n\n---\n\n## Step 1: Understand What's Being Reviewed\n\nIf `\u002Fbrief` without context:\n\n> What do you want the board to review? Describe it in plain language — a file, a decision, a proposal, a document, a question.\n\nIf triggered by plain language, confirm what you understood before proceeding.\n\n---\n\n## Step 2: Detect the Domain and Artifact Type\n\nIdentify domain (software, business, HR, finance, legal, etc.) from the user's description. Check `.board\u002Fboard\u002F{agent}\u002Fcontexts\u002F` for existing context files.\n\nAlso identify the **artifact type** — this determines what broader context agents need:\n\n| Artifact Type | What Agents Need Beyond the Artifact |\n|--------------|--------------------------------------|\n| **Code diff** | Architecture of the system being changed, what the code does, why the change was made, what CLIs\u002Ftools are involved, deployment environment |\n| **Plan \u002F proposal** | Current state of the system, what exists today, what's changing, constraints, prior decisions |\n| **Architecture** | Problem being solved, scale, team, existing infrastructure, deployment model |\n| **Business decision** | Constraints, stakeholders, prior commitments, risk tolerance, timeline |\n| **Document \u002F policy** | Audience, enforcement mechanism, existing related docs |\n\nIf matching context exists: offer to use it or tailor further. If no match: tell the user you'll write one now and save it for future reviews.\n\n---\n\n## Step 3: Write or Activate Context\n\nExisting context → read it. New context → write `.board\u002Fboard\u002F{agent}\u002Fcontexts\u002F{domain}.md` for each agent. A context file gives the agent a domain-specific lens — what to look for, what questions to ask. It does not change their identity. Write each one for that specific agent's angle applied to this domain.\n\n---\n\n## Step 4: Load Deferred Work\n\nLoad deferred items from two sources:\n1. `tasks.json` — look for tasks with `\"status\": \"deferred\"`. Include their title, description, trigger condition, and severity.\n2. `.board\u002Fboard\u002FDEFERRED_WORK.md` — if it exists (legacy), read the FULL contents.\n\nDeferred items are **active evaluation targets** — agents must check whether the current review triggers any of them.\n\n---\n\n## Step 5: Gather Broader Context\n\nAsk yourself: **what context would a knowledgeable new reviewer need to evaluate this artifact?** Agents can't look things up — they only know what's in the brief.\n\nFor code reviews, read the relevant source files and include key architecture details. For plans, describe the current state of the system. For business decisions, include constraints and stakeholder context.\n\nDon't assume agents know:\n- How the system works\n- What tools, CLIs, or frameworks are involved\n- What deployment environment exists\n- What prior decisions were made and why\n- What the user's constraints are\n\nInclude what they need. Err on the side of more context, not less.\n\n---\n\n## Step 6: Write the Review Brief\n\nRound 1 (Blind Review) brief — same for all agents:\n\n1. **Context** — what is this, why is it being reviewed, who's the audience\n2. **The artifact** — full text, inline. Code diffs in full. Plans in full. Never summarize what agents can read themselves.\n3. **Broader context** — system architecture, environment, constraints, prior decisions (from Step 5)\n4. **Deferred items** — all deferred tasks from `tasks.json` (status=deferred) and `DEFERRED_WORK.md` (if exists), framed as: \"Evaluate whether your review triggers any of these deferred items. If a trigger condition is met, promote to FIX NOW with evidence.\"\n5. **Evaluation criteria** — what to evaluate, specific questions if any\n6. **Output format** — finding ID, severity (FIX NOW\u002FDEFER\u002FINFO\u002FREJECT), location, finding, recommendation\n7. **User concerns** — anything the user specifically flagged\n\nIf artifact exceeds ~50KB: executive summary + full text + section index. Over ~100KB: split into sessions.\n\n---\n\n## Step 7: Populate Inboxes\n\nFor each agent: copy context to `inbox\u002Fcontext.md`, brief to `inbox\u002Fbrief.md`, clear previous `outbox\u002Freport.md`.\n\n> Brief is ready in all inboxes. Want me to run the board now, or review the brief first?\n\n---\n\n## Round 2+ Briefs\n\nThe `\u002Frun` skill handles subsequent round briefs. If the user asks to re-brief between rounds (add a directive, change the question), this skill runs again. Always include: previous findings with positions, owner directives, deferred items, and the original artifact (ephemeral agents need it every round).\n",{"name":5,"description":7},"main","e01303ad28862b5c26c950358250aeb4f74090e6",".claude\u002Fskills\u002Fbrief",1,"https:\u002F\u002Fgithub.com\u002Fstefans71\u002FFrontierBoard","https:\u002F\u002Fgithub.com\u002Fstefans71","2026-04-20 07:23:08",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add stefans71\u002FFrontierBoard --skill brief",{"tool":45,"command":46},"bunx","bunx skills add stefans71\u002FFrontierBoard --skill brief",{"tool":48,"command":49},"pnpm","pnpm dlx skills add stefans71\u002FFrontierBoard --skill brief","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstefans71\u002FFrontierBoard\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fbrief\u002FSKILL.md",true,[53],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"agents\u002Fopenai.yaml","REFERENCE","参考文档",227,"https:\u002F\u002Fgithub.com\u002FEthanYoQ\u002FSkill-hub\u002Fblob\u002Fmine\u002Fskills\u002F01-agent-engineering\u002Fyq-simplify-code\u002Fagents\u002Fopenai.yaml",[60,72,90,101,110,127],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":27},"01M6CW5BKYDY1PC8YPCHNZN1V5","teardown","Remove a FrontierBoard installation. Run when the user types \u002Fteardown or asks to uninstall, remove, or clean up the board.","https:\u002F\u002Fgithub.com\u002Fstefans71\u002FFrontierBoard\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fteardown\u002FSKILL.md",[],[62,67,20,22,24,68,69,70,71],"uninstall","remove","up","clean","installation",{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":83,"publishedAt":27},"01M6CW599G8TXF87JTYRPHRKJ7","smoke-test","Validate a board installation works end-to-end. Run when the user types \u002Fsmoke-test or asks to test, validate, or verify the board setup.","https:\u002F\u002Fgithub.com\u002Fstefans71\u002FFrontierBoard\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsmoke-test\u002FSKILL.md",[78],{"categoryNo":79,"categoryName":80,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[84,85,86,24,87,88,20,89,22,71],"smoke test","smoke","test","validate","setup","verify",{"skillNo":91,"name":88,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":27},"01M6CW56Q6B52QVY7YFDXJCDP2","Set up the Board of Governance. Run when the user types \u002Fsetup or asks to set up, install, or configure the board for the first time.","https:\u002F\u002Fgithub.com\u002Fstefans71\u002FFrontierBoard\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsetup\u002FSKILL.md",[],[88,22,24,96,69,97,98,99,100,20,21],"install","time","first","configure","governance",{"skillNo":102,"name":20,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":27},"01M6CW5435Q93Y2Q1427PSDWMA","Run the board agents and synthesise their reports. Run when the user types \u002Frun, asks to run the board, or after \u002Fbrief when the user confirms they're ready to go.","https:\u002F\u002Fgithub.com\u002Fstefans71\u002FFrontierBoard\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frun\u002FSKILL.md",[],[20,107,5,22,24,108,109],"go","ready","reports",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":27},"01M6CW518M6QPGGW3DAT6JNEZQ","review-release","Review a GitHub repo or release using the board. Use when the user types \u002Freview-release, asks to \"review a release\", \"check if this is safe to install\", \"look at the latest version of [repo]\", wants to \"try installing it and see what breaks\", or any variant of reviewing an external GitHub project before contributing to it or installing it.","https:\u002F\u002Fgithub.com\u002Fstefans71\u002FFrontierBoard\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Freview-release\u002FSKILL.md",[],[117,118,18,119,120,121,122,123,124,22,24,96,125,126],"review release","release","look","safe","github","contributing","repo","check","use","version",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":136,"publishedAt":27},"01M6CW4YSSPY6FXCR6DMZWF9XX","project-tests","Generate test specs (Skeptic writes) and verify test code (Skeptic reviews). Two modes — \u002Fproject tests for specs, \u002Fproject tests --verify for code review.","https:\u002F\u002Fgithub.com\u002Fstefans71\u002FFrontierBoard\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fproject\u002Ftests\u002FSKILL.md",[133],{"categoryNo":134,"categoryName":135,"taxonomyType":81,"taxonomyTypeDesc":82},"01JBSEEDCAT000000000000007","代码审查",[137,138,139,86,18,140,141,89,142],"project tests","code","generate","verify test","skeptic","code review"]