agentleFS
virtualmasevirtualmase/lifecycle-skills/skills/builder/SKILL.md

builder

Skill1 starsChanged 3 months agoMITView on GitHub

Implement reviewed specifications as portable, accessible, source-controlled systems. Use for websites, applications, integrations, schemas, tests, migration work, and deployment packages that require acceptance checks, data boundaries, and rollback paths.

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Use this skill to turn an approved specification into maintainable implementation.

    line 8
  2. Distinctive:

    Add automated checks proportionate to risk.

    line 19
  3. Distinctive:

    Document dependencies, configuration, upgrade and rollback procedures, validation results, and known limitations.

    line 20
  4. Distinctive:

    Do not store secrets in source, introduce hidden vendor lock-in, deploy data-bearing or risky changes without named approval, silently …

    line 28

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “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

Builder

Use this skill to turn an approved specification into maintainable implementation. Prefer portable standards, documented dependencies, minimal architecture, and explicit separation between public content, private data, and operational systems.

Intake

Require an approved specification, property role, acceptance criteria, security and data boundary, source and asset rights, deployment target, rollback path, reviewer, and public-claim review status. Do not build an unbounded system from an unreviewed ambition.

Workflow

  1. Inspect existing conventions, dependencies, and interfaces before adding new dependencies or abstractions.
  2. Choose the smallest portable architecture that meets the acceptance criteria and keeps ownership clear.
  3. Implement accessible semantics, descriptive media, responsive behavior, visible error states, and safe defaults.
  4. Add automated checks proportionate to risk. Test invalid input, error and recovery paths, permissions, link integrity, and build output—not only the happy path.
  5. Document dependencies, configuration, upgrade and rollback procedures, validation results, and known limitations.

Deliverable

Provide source-controlled implementation, validation evidence, dependency inventory, deployment instructions, rollback instructions, and a maintainer handoff. State the acceptance criteria met, residual risk, release owner, and reviewer.

Boundaries

Do not store secrets in source, introduce hidden vendor lock-in, deploy data-bearing or risky changes without named approval, silently change a property’s role or identity, or make unverified public claims.

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.