Skip to main content
skill CX Codex

port-spec — Claude Code skill: what it does, how to install

The port-spec Claude Code skill turns a complete written specification into code or a vault artifact. It activates for spec implementation, brief-based builds, and ports from specs.

MIT ★ 26 updated 2026-11-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add wrg32786/aigent-os --skill port-spec -a claude-code
Open on GitHub

What port-spec does

port-spec converts a written specification into working code, configuration, or a vault artifact. It handles schemas, data models, API contracts, vault note structures, and component designs. Before changing anything, it reads the target files and searches for related types, imports, and dependencies.

The work stays within the brief. If a requirement is ambiguous, the skill asks one focused question; if the task exceeds the stated scope, it stops and reports what remains. Each delivery includes an honesty ledger covering changed and untouched files, out-of-scope issues, uncertainty, tradeoffs, and unfinished work.

What it helps with

  • turn a data schema from a spec into code
  • implement an API contract from a written brief
  • create a vault artifact from a defined structure
  • report work that falls outside the specification

Example prompts for the agent

  • Port this specification into the project code.
  • Implement the API contract from this brief.
  • Create a vault artifact that follows this structure.

How to install port-spec

1Skills CLI (Vercel)

npx skills add wrg32786/aigent-os --skill port-spec -a claude-code

2Manually: put the files in place

~/.claude/skills/port-spec/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/port-spec/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about port-spec

How do I install port-spec in Claude Code?

Run npx skills add wrg32786/aigent-os --skill port-spec -a claude-code. The skill file is at ~/.claude/skills/port-spec/SKILL.md.

What does port-spec do?

It turns a complete written specification into code, configuration, or a vault artifact. It reads relevant project files before editing and returns a ledger of changes, open issues, and unfinished work.

How does port-spec handle ambiguous requirements or scope changes?

It asks one focused question when a requirement is ambiguous. If the work goes beyond the brief, it stops and reports what remains instead of expanding the task.

Source text

SKILL.md · MIT
---
name: port-spec
agent: lyra
description: "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."
allowed-tools: Read, Write, Edit, Bash, Grep, Glob, Agent
user-invocable: true
triggers:
  - port this spec
  - implement this spec
  - build from spec
  - port spec
  - implement from brief
  - execute this brief
  - build this
  - port to code
---

# 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.

© wrg32786 · MIT · wrg32786/aigent-os

Similar skills

SKILL.md skills catalog →

From the same set58

The whole set →
resume Restores context for unfinished work. Run /resume to compare the saved capsule with live memory and take the next step. CX Codex +1 ★ 26repo stars research-deep The research-deep Claude Code skill combines vault notes, web sources, and GitHub research into a cited briefing with evidence and a recommendation. It runs on requests to investigate a topic or compare sources. CX Codex +1 ★ 26repo stars reconcile This Claude Code skill compares seven days of project attention with stated Tier-1 shares. Run it to reconcile attention or check for priority drift. CX Codex +1 ★ 26repo stars Promote The Promote Claude Code skill turns useful conversation insights into lasting vault notes. It activates when a decision, fact, or idea should remain available after the session. CX Codex +1 ★ 26repo stars pause The pause Claude Code skill saves a task’s state when work needs to stop temporarily. The next session offers a way to resume it. CX Codex +1 ★ 26repo stars orient The orient Claude Code skill points to the project map section relevant to a question about structure, ownership, rules, or next steps. It activates when someone asks where to look or how to proceed. CX Codex +1 ★ 26repo stars operator-setup The operator-setup Claude Code skill interviews a business operator and saves the answers for later sessions. It turns the stated goals and time-consuming work into three tailored next steps. CX Codex +1 ★ 26repo stars open This Claude Code skill loads workspace context and surfaces items that need attention at the start of a session. Running /open checks priorities and recovers unfinished work. CX Codex +1 ★ 26repo stars

Project sponsors

Companies that keep this analytics open