agentleFS
bordenetbordenet/superpowers-plus/skills/engineering/domain-build/skill.md

domain-build

Skill8 starsChanged 6 months agoMITView on GitHub

Use when building, deploying, and documenting skills from a completed domain-design output. Handles the walking skeleton -> remaining P0s -> cookbook -> handoff cycle.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 10 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Use todo-management skill for all 4 phases.

    line 34
  2. Very specific:

    Create skills/{domain}/{skill-name}/skill.md with frontmatter:

    line 46
  3. Distinctive:

    Verify the skill is discoverable: run the discovery command for your skill system.

    line 58
  4. Distinctive:

    Test against a real data source (not mocked/fabricated output).

    line 59
  5. Distinctive:

    Test against real data.

    line 71
  6. Distinctive:

    Create documentation with real-world recipes.

    line 78
  7. Distinctive:

    Add a "Chaining Recipes" section showing multi-skill workflows.

    line 85
  8. Distinctive:

    Add a "What's Coming Next" section: blocked skills + their ticket links + owners.

    line 86
  9. Distinctive:

    Data freshness: All examples MUST use real data from the current session.

    line 90
  10. Distinctive:

    Tracking page: Add build phase rows. Add "What's Blocked" with ticket details.

    line 95
  11. Distinctive:

    Repo: All skills committed and pushed.

    line 96
  12. Very specific:

    250-line cap for skill.md: If a skill exceeds 250 lines, split into skill.md (core, <=250L) + examples.md + references/*.md.

    line 103
  13. Distinctive:

    Do NOT report "Domain Build Complete" until ALL items are checked.

    line 109

≈ “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

Domain Build -- Build, Deploy, Document

Purpose: Execute the build/deploy/document cycle for a designed skill domain. Prerequisite: A completed domain-design output -- prioritized skill roster, architecture decision, infrastructure map.

Announce at start: "I'm using the domain-build skill to implement the designed domain."

TODO Persistence

Use todo-management skill for all 4 phases. Tag tasks #plan-build-{domain}. Track each phase + post-build gates.


The 4-Phase Process

Input from domain-design: P0-P3 roster + architecture decision + walking skeleton design.

Phase 1: WALKING SKELETON

Build the simplest P0 skill to prove the full pattern end-to-end.

  1. Create skills/{domain}/{skill-name}/skill.md with frontmatter:
    ---
    name: skill-name
    source: superpowers-plus
    triggers: [...]
    description: Use when...
    ---
  2. Include the verified query/API call from the domain design.
  3. Define the output format the agent should produce.
  4. Install/deploy the skill per your overlay's install mechanism.
  5. Verify the skill is discoverable: run the discovery command for your skill system.
  6. Test against a real data source (not mocked/fabricated output).
  7. Commit and push.

Gate: Walking skeleton must be discoverable AND return real data before proceeding.

Phase 2: REMAINING P0s

For each remaining P0 skill in the roster:

  1. Create skills/{domain}/{skill-name}/skill.md.
  2. Deploy: run the install mechanism.
  3. Verify discoverable.
  4. Test against real data.
  5. Commit and push.

Batch commits are acceptable for remaining P0s.

Phase 3: COOKBOOK

Create documentation with real-world recipes. For each P0 skill, write one recipe with:

  • When to use -- scenario description
  • Ask the agent -- exact prompt to copy-paste
  • What you get back -- real output (run the actual query, do not fabricate)
  • Behind the scenes -- the query/API call

Add a "Chaining Recipes" section showing multi-skill workflows. Add a "What's Coming Next" section: blocked skills + their ticket links + owners.

Publish to your team's documentation platform nested under the design document.

Data freshness: All examples MUST use real data from the current session.

Phase 4: HANDOFF

  1. Design document: Mark P0 skills as Shipped with dates. Update file layout. Verify all ticket links.
  2. Tracking page: Add build phase rows. Add "What's Blocked" with ticket details. Update Key Findings.
  3. Repo: All skills committed and pushed. Skills discoverable via your install system.
  4. Report to user: Table of skills + status, blockers with tickets + owners, documentation links.

Hard Limits

250-line cap for skill.md: If a skill exceeds 250 lines, split into skill.md (core, <=250L) + examples.md + references/*.md. Verify: wc -l skills/{domain}/{skill-name}/skill.md.


Completion Checklist

Do NOT report "Domain Build Complete" until ALL items are checked.

Per-Skill Gates

  • skill.md created with valid YAML frontmatter
  • skill.md is under 250 lines (wc -l)
  • Install/deploy exits 0
  • Skill is discoverable via the skill system
  • Tested against real data (no fabricated output)
  • Committed and pushed

Documentation

  • Design document -- P0 skills marked Shipped with dates, file layout updated
  • Tracking page -- build phase rows added, blockers current
  • Cookbook -- published with real data from the current session
  • Skills index (if applicable) -- new skills listed with trigger conditions
  • Skill count -- any file that states a total skill count is updated

Failure Modes

ModeSymptomRecovery
Fabricated test outputSkill "works" in demo but fails in productionAlways run against real data; never mock
Skipped validationBuild fails silentlyVerify discovery + real-data test before claiming done
Cookbook uses stale dataRecipes mislead usersPull fresh data during the current session
Incomplete checklist"Done" declared prematurelyThe checklist is a hard gate; partial completion = not done

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.