{
  "briefs": [
    {
      "id": "brf_brand_voice_skill",
      "name": "This repo's own brief-adjacent skill: brand-voice",
      "discipline": "in-repo",
      "summary": "This repository has no dedicated legal-coworker skill and no campaign-brief skill under plugins/cwc-product-management (verified by search this session: cwc-product-management ships exactly one skill, brand-voice). The closest in-repo artifact to a \"brief\" convention is that skill's own discipline — source a real quoted example before drafting any guideline, present the draft for human confirmation, and record only a sourced, gated write — the same source-before-draft discipline every other row in this table describes for its own discipline.",
      "structure_md": "- **Read first** — check subagentbrands.com's existing brand_guidelines before drafting anything new\n- **Source, never invent** — pull a genuine quoted example from a real sibling-site file (e.g. `workers/subagentcache/src/index.ts`)\n- **Draft + present** — show the drafted row (quote, source, guideline text) and wait for explicit operator confirmation\n- **Gated write** — only record via `POST subagentbrands.com/api/brand-guidelines` after confirmation, per `gates.toml`'s `guideline_write` gate",
      "source_doc": "plugins/cwc-product-management/skills/brand-voice/SKILL.md",
      "created_at": "2026-07-02 06:01:18",
      "cite_as": "https://subagentbriefs.com/api/briefs/brf_brand_voice_skill"
    },
    {
      "id": "brf_legal_case_brief",
      "name": "Legal case brief (IRAC)",
      "discipline": "legal",
      "summary": "A concise summary and analysis of a court opinion, prepared for classroom discussion or practice, that establishes the parties, the issue, the rule, and the outcome before any argument is built on top of it.",
      "structure_md": "- **Issue** — the question the court must answer, framed as a question\n- **Rule** — the legal principle the court announces, stated portably without case-specific facts\n- **Application** — how the court applies the rule to the facts\n- **Conclusion/Holding** — the court's answer applied to these facts\n\nCommonly extended to **FIRAC** (adds a separate **Facts** section) or reordered as **CREAC**/**CRAC** — same four core elements, different sequencing.",
      "source_doc": "https://pressbooks.uwf.edu/healthcarelaw/part/irac-analysis/",
      "created_at": "2026-07-02 06:01:18",
      "cite_as": "https://subagentbriefs.com/api/briefs/brf_legal_case_brief"
    },
    {
      "id": "brf_creative_brief",
      "name": "Creative / marketing campaign brief",
      "discipline": "marketing",
      "summary": "A short planning document an account team hands to a creative team before production begins, fixing the objective, audience, and deliverables so creative work has a measurable target rather than an open-ended brainstorm.",
      "structure_md": "- **Project summary & objective** — the strategic goal, stated as something measurable\n- **Target audience** — demographics, psychographics, needs and pain points\n- **Key messages & brand guidelines** — what must be communicated, and within what voice constraints\n- **Deliverables & formats** — the specific assets expected, with sizes/specs and distribution channels\n- **Timeline & budget**\n- **Success metrics**\n- **Approval workflow**",
      "source_doc": "https://asana.com/resources/how-write-creative-brief-examples-template",
      "created_at": "2026-07-02 06:01:18",
      "cite_as": "https://subagentbriefs.com/api/briefs/brf_creative_brief"
    },
    {
      "id": "brf_claude_task_brief",
      "name": "Briefing Claude on a task (prompt engineering)",
      "discipline": "prompt-engineering",
      "summary": "Anthropic's own prompting guidance converges on the same shape as the legal and marketing brief conventions above, applied to instructing Claude: state the task explicitly, name who the output is for, and define what \"done\" looks like before generation starts.",
      "structure_md": "- **Task** — name the task explicitly rather than leaving it implicit\n- **Audience** — identify who the output is for\n- **Format / length / purpose** — specific details up front, not left for Claude to infer\n- **Done criteria** — clear expectations for what a correct/complete output looks like, set before any generation begins",
      "source_doc": "https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices",
      "created_at": "2026-07-02 06:01:18",
      "cite_as": "https://subagentbriefs.com/api/briefs/brf_claude_task_brief"
    }
  ]
}