agentleFS
Sign inStart free
sparkline-venturessparkline-ventures/product-eval/skills/to-build-brief/SKILL.md

to-build-brief

Skill15 starsChanged 5 months agoMITView on GitHub

Transform an approved decision into an agent-ready build spec, --code for Claude Code/Codex, --design for Figma/wireframe/Gemini. Use when the user says "turn this into a spec", "make it buildable", "build brief", "hand this to Claude Code / Figma", or after a brief is approved. Strips narrative voice; outputs structured, testable markdown.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Write to .product-eval/<scope>/build/ and note it's ready to hand to the target tool.

    line 27

≈ “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

To Build Brief

Turn the approved Opportunity Brief / decision into a structured spec an implementation or design agent can execute. This artifact is for builders: literal requirements, screens, states, data, acceptance criteria, and metrics. Reads .product-eval/<scope>/; writes to .product-eval/<scope>/build/. Two modes; strip persuasion and prose, builders want literal, testable detail (see references/build-brief.md).

Preconditions

Only run on an approved decision. Verify a passing decision-readiness verdict exists for this item in .product-eval/<scope>/decisions-log.md; if it has not passed, refuse, do not generate a build spec for an unvalidated bet (say what is missing and point to decision-readiness / design-test). Run the conformance preflight in DATA-CONTRACT.md (Validation) on the scope files first, so a build spec is never generated from a malformed decisions-log.md or scores.md.

--code (Claude Code / Codex)

Emit: scope in/out (explicit non-goals); primary user flows; P0/P1 functional requirements each with Given/When/Then acceptance criteria; data model / key entities; states and edge/error cases; constraints, dependencies, interfaces; success metrics + instrumentation; and a "build this MVP slice first" callout. Markdown, hierarchical, no narrative voice.

--design (Figma / wireframe / Gemini)

Emit: a screen-by-screen breakdown, each view, its elements, and its states (empty / loading / error / success); flows as numbered steps; the primary action/CTA per screen; key copy; brand/platform/responsive constraints. Optionally push to Figma via its MCP path.

Workflow

  1. Load the approved brief, decision, and scores from the scope.
  2. Render the requested mode from references/build-brief.md.
  3. Carry the success metrics over, so the builder produces something measurable.
  4. Write to .product-eval/<scope>/build/ and note it's ready to hand to the target tool.

Output

The build brief in the requested mode, in plain markdown so Claude Code, Codex, Gemini, and Figma's tooling all parse it. Lead with the scope and the MVP slice. End with Next move: and name the handoff target: Codex/Claude Code for implementation, or the design tool/agent for wireframes and interaction work.

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.

Check your setup, free