agentleFS
Sign inStart free
kiku-jwkiku-jw/codex-skills/spec-bundle/SKILL.md

spec-bundle

Skill0 starsChanged 4 months agoMITView on GitHub

Build an implementation-ready spec bundle when a plain PRD is no longer enough: minimum useful contracts, schema, test plan, blueprint, gates, ADRs, boundaries, and GitHub-ready task breakdown. Use when ambiguity or architecture risk would otherwise slow execution.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Do not use when: a short brief is enough and extra artifacts would be paperwork theater.

    line 10
  2. Distinctive:

    Create only the spec artifacts that materially reduce ambiguity, rework, or review pain so implementation can start from clear contracts …

    line 14
  3. Distinctive:

    If an artifact would be fake theater, leave it out or mark it intentionally deferred.

    line 25

≈ “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

Spec Bundle

Metadata

  • Trigger when: a plain PRD is too soft and the implementation needs contracts, schema, test planning, or architecture boundaries to move safely.
  • Do not use when: a short brief is enough and extra artifacts would be paperwork theater.

Skill Purpose

Create only the spec artifacts that materially reduce ambiguity, rework, or review pain so implementation can start from clear contracts and gates instead of vibes.

Instructions

  1. Decide the smallest honest bundle first: core bundle, architecture pack, and optional ADRs only when the risk profile justifies them. If scaffolding helps, use ~/.codex/skills/spec-bundle/scripts/init_bundle.py with the appropriate flags. Use ~/.codex/skills/spec-bundle/references/bundle-shape.md only when you need the exact shape.
  2. Fill only the artifacts that change implementation quality: prd.md, contracts.md, schema.sql, test-plan.md, epics.md, and only add blueprint.md, gate-matrix.md, or adr/ when architecture risk, gating, or irreversible decisions make them worth keeping.
  3. Validate traceability and consistency. Contracts must point to consuming tasks, gates must name blocking evidence, and bundle artifacts must be updated together when requirements or architecture move.

Non-Negotiable Acceptance Criteria

  • One source of truth per concern: scope, contracts, DB shape, validation, and task breakdown stay separated.
  • Architecture pack artifacts exist only when the risk is real.
  • Local/cloud boundaries are explicit when they matter.
  • If an artifact would be fake theater, leave it out or mark it intentionally deferred.

Output

  • The created or updated bundle artifacts on disk.
  • A short note on bundle size: core only, architecture pack, or architecture pack plus ADRs.
  • Any unresolved gate or assumption that still blocks clean implementation.
  • Next skill options (only if needed): $justdoit — convert the bundle into a live execution plan; $adr-log — capture an irreversible architectural choice; $issue-control-loop — move the bundle into a durable GitHub issue workflow; $agx-orchestrator — dispatch bounded execution after the bundle is stable.

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