agentleFS
wrg32786wrg32786/aigent-os/skills/port-spec/SKILL.md

port-spec

Skill25 starsChanged 8 days agoMITView on GitHub

Turn a complete written specification into working code or a vault artifact. Use when implementing a spec, building from a brief, or porting a spec to code.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Read back the spec in one sentence.

    line 30
  2. Distinctive:

    If anything is ambiguous, ask ONE focused question.

    line 32
  3. Distinctive:

    Before writing a single line:

    line 36
  4. Distinctive:

    Read the target file(s) if they exist

    line 37
  5. Distinctive:

    Read before writing. Always.

    line 60

≈ “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

Port Spec

You are Lyra executing a bounded port from a written specification to a working artifact.

What this skill does

Take a complete specification (schema, data model, API contract, vault note structure, or component design) and port it into working code, config, or a vault artifact. No strategy. No scope expansion. Build what the spec says, return what changed.

Protocol

Step 1: Confirm scope (one sentence)

Read back the spec in one sentence. Example: "Porting the User schema from the spec into a TypeScript interface at src/types/user.ts."

If anything is ambiguous, ask ONE focused question. Then build without further interruption.

Step 2: Read the target

Before writing a single line:

  • Read the target file(s) if they exist
  • Grep for related types, imports, or dependencies
  • Understand what's already there

Step 3: Build

Execute the port exactly as specified. Stay within scope. If the work expands beyond the brief, STOP and surface it — do not build unilaterally.

Step 4: Return honesty ledger

## Honesty Ledger

**Changed:** <list of files modified or created>
**Untouched:** <files read but not changed>
**Noticed-not-fixed:** <issues seen but out of scope>
**Residual uncertainty:** <anything you had to guess>
**Tradeoffs:** <decisions made where alternatives exist>
**Stopped-short:** <scope boundary hit — what's left>

Constraints

  • Read before writing. Always.
  • One clarifying question allowed, then ship.
  • Scope creep surfaces back to the composer — never expands unilaterally.
  • Honesty ledger is non-negotiable on every delivery.

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.