agentleFS
MrCipherSmithMrCipherSmith/goodai-base/skills/brd-creator/SKILL.md

brd-creator

Skill0 starsChanged 5 months agoMITView on GitHub

Use when a user request needs to be transformed into a Business Requirements Document (BRD) capturing business context, stakeholders, and success metrics.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always produce these seven sections:

    line 31
  2. Distinctive:

    When all upstream fields are null, prepend:

    line 68

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

BRD-Creator Sub-Agent

1. Purpose

Transforms a user request into a structured Business Requirements Document (BRD) that captures the business context, stakeholders, objectives, and success metrics needed to align teams before any design or implementation work begins.

Operates in two modes:

  • Direct Mode — interacts with the user to gather context and produce a BRD
  • Orchestrated Mode — invoked by spec-orchestrator with structured JSON input; returns document content

2. BRD Document Structure

Always produce these seven sections:

  1. Business Problem — the core problem or opportunity being addressed
  2. Objectives — measurable business goals (use OKR or KPI format where possible)
  3. Stakeholders — who is affected, who decides, who must be informed
  4. Scope — what is included in this initiative
  5. Success Metrics — how success will be measured and by when
  6. Constraints — business, regulatory, budget, and resource constraints
  7. Out of Scope — explicit exclusions to prevent scope creep

3. Orchestrated Mode

3.1 Input Contract

See input-contract.schema.json. Key fields:

{
  "request": "<original user request — always required>",
  "upstream": {
    "raw_requirements": "<raw-requirements.md content or null>",
    "brainstorm":       "<brainstorm.md content or null>"
  },
  "current_draft":      "<existing brd.md content — present only in refinement mode>",
  "reviewer_findings":  [
    { "id": "P-N", "location": "<section>", "severity": "blocker|major|minor", "description": "<what is wrong>" }
  ],
  "upstream_warnings":  ["<DONE_WITH_CONCERNS note from a prior stage>"]
}

3.2 Generation Mode (no current_draft)

Produce a BRD from scratch using request and any available upstream content.

When all upstream fields are null, prepend:

> Note: generated from raw request only — no upstream artifacts were available.

3.3 Refinement Mode (reviewer_findings present)

Address every finding in reviewer_findings within current_draft. Do not regenerate the document from scratch — preserve the original structure and revise only what the findings require. Mark addressed findings with inline notes if the change is non-obvious.

3.4 Output

Return the complete BRD document as a plain markdown string. Prefix your response with:

STATUS: DONE

The orchestrator writes the returned content to brd.md. Do not write files yourself in orchestrated mode.


4. Direct Mode

Interact with the user. Ask up to 5 clarifying questions if the request is ambiguous (prefer multiple-choice). Save the BRD to docs/brd/ following rules/core/documentation-management.mdc.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.