Skip to main content
skill CX Codex

adopt-spec — Claude Code skill: typed spec from CLAUDE.md

Turns an existing CLAUDE.md or AGENTS.md into a typed CLAUDE.md.spec.ts without touching the original file. Useful when you want lint-checked instructions but dread rewriting them.

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

What adopt-spec does

The skill reads your instruction file and splits it into commands, rules and prose sections. Each rule gets classified: enforce() when a linter annotation sits next to it, guidance() for advice or a code-review pointer. Rules with no annotation are marked TODO so you can sort them out yourself.

The core promise is that nothing breaks. Your CLAUDE.md stays where it is; the skill only writes the new .spec.ts and never runs compile over your file. Switching to spec-managed mode is a separate step you run yourself after reading the diff. There is a way back too: vigiles eject <file> hands the file back as plain markdown.

Before writing anything, the skill shows the generated spec and a conversion summary, and only writes once you say yes. If vigiles is missing from devDependencies, it suggests npm install -D vigiles. One thing to keep in mind: the keyFiles field is deprecated, so a "Key Files" list from the old file carries over as a plain prose section until you decide where each entry belongs.

What it helps with

  • get a typed spec out of a hand-written CLAUDE.md
  • classify rules as enforce or guidance without rewriting them
  • catch stale file references through file() and cmd()
  • verify instructions with vigiles lint
  • eject the spec back to markdown with vigiles eject

Example prompts for the agent

  • Parse my CLAUDE.md and build CLAUDE.md.spec.ts from it, leave the original alone
  • Run adopt-spec on AGENTS.md and show how many rules landed in enforce, guidance and TODO
  • Generate the spec from CLAUDE.md but show me the result and summary first, don't write yet

How to install adopt-spec

1Skills CLI (Vercel)

npx skills add zernie/vigiles --skill adopt-spec -a claude-code

2Manually: put the files in place

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

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

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

Questions about adopt-spec

How do I install adopt-spec in Claude?

Run npx skills add zernie/vigiles --skill adopt-spec -a claude-code. The skill file then lands at ~/.claude/skills/adopt-spec/SKILL.md.

What does adopt-spec do?

It takes your existing CLAUDE.md or AGENTS.md and builds a typed CLAUDE.md.spec.ts from it. The original file is not edited.

Does it switch my rules to strict enforcement?

No. guidance() stays guidance(), and moving to enforce() is a separate step handled by the strengthen skill. That needs config and plugins, and can produce false positives.

Source text

SKILL.md · MIT
---
name: adopt-spec
description: Adopt a typed .spec.ts for an existing hand-written CLAUDE.md — start from the file you already have, non-destructively
disable-model-invocation: true
argument-hint: <path to CLAUDE.md, defaults to CLAUDE.md>
---

Start a typed `CLAUDE.md.spec.ts` from an existing hand-written CLAUDE.md (or AGENTS.md). This is the non-destructive adoption path — you keep your existing instruction file as the starting point and get type safety going forward.

## Adoption rules

Adoption is the **safe, faithful on-ramp — never an upgrade in disguise.** These are non-negotiable:

- **Faithful.** Preserve every rule, command, and prose section as-is. Invent nothing — the spec must compile back to ~the user's existing file. The one exception is a file map ("Key Files"): never emit the deprecated `keyFiles` field — see the guideline under Step 3.
- **Non-destructive.** Never edit the original `CLAUDE.md` / `AGENTS.md`. Only write the new `.spec.ts`. Never auto-`compile` over the file — switching it to spec-managed is a separate, explicit step the user runs with a diff to review.
- **Don't escalate enforcement.** Keep `guidance()` as `guidance()`. Upgrading to `enforce()` has a cost (config/plugins, possible false positives) and is a separate opt-in step — the `strengthen` skill. Adoption is **not** turning on strict / `workflow` gating.
- **Reversible.** `vigiles eject <file>` hands the file back as plain hand-owned markdown anytime — it's never a one-way door. Tell the user this.
- **Ask before writing.** Present the generated spec and a conversion summary first; write only on the user's yes.
- **A lighter touch exists.** For no spec at all, inline `<!-- vigiles:enforce ... -->` comments are verified by `vigiles lint` with the same engine.

## Instructions

### Step 1: Read the Existing File

Read the target instruction file (default: `CLAUDE.md` in the repo root). If the user specified a path, use that.

Also check if vigiles is installed: look for `vigiles` in `package.json` devDependencies. If not, suggest:

```bash
npm install -D vigiles
```

### Step 2: Parse the Structure

Identify these sections in the markdown:

- **Commands** — lines like `` `npm run build` — description `` or ``- `command` — description``
- **A file map ("Key Files")** — lines like `` `src/foo.ts` — description `` listing important files. Never becomes `keyFiles` (deprecated); see the guideline under Step 3
- **Rules** — `###` headings with `**Enforced by:**`, `**Claimed (unverified):**` or `**Guidance only**` annotations
- **Prose sections** — everything else (positioning, architecture, principles, etc.)

For each rule, classify it:

- Has `**Enforced by:** \`linter/rule\``→`enforce("linter/rule", "why")`
- Has `**Claimed (unverified):** \`linter/rule\``→`enforce("linter/rule", "why")` too — the last compile could not verify it; the next one will say why
- Has `**Enforced by:** \`code-review\``or similar non-linter →`guidance("...")`
- Has `**Guidance only**` → `guidance("...")`
- Has no annotation → mark as TODO for the user to classify

### Step 3: Generate the Spec File

Create `CLAUDE.md.spec.ts` (or the appropriate name based on the source file) with this structure:

```typescript
import {
  claude,
  enforce,
  guidance,
  file,
  cmd,
  ref,
  instructions,
} from "vigiles/spec";

export default claude({
  sections: {
    // Prose sections here
  },

  // No `keyFiles`: the field is deprecated (removed next major). A "Key Files"
  // list in the original file is NOT carried over as a map — see the
  // guideline below.

  commands: {
    // Commands here
  },

  rules: {
    // Rules here
  },
});
```

**Important guidelines:**

- Use `file()` refs in sections where file paths appear in backticks — this enables stale reference detection
- 🔴 **Never emit `keyFiles`.** The field is deprecated and removed in the next major (`vigiles lint` warns as `deprecated-key-files`). For a "Key Files" / file-map section in the original, apply the migration recipe (`docs/rules/deprecated-key-files.md` in the vigiles repository) and show the user, per entry, where it goes — the first that fits: (1) the file's header, the docs or the path already say it (or the path no longer exists) → delete it; (2) a fact about that one file → that file's header comment; (3) a rule for working in one folder → that folder's nested `CLAUDE.md` (its own `<folder>/CLAUDE.md.spec.ts`); (4) nothing else would lead an agent to the file → a one-line `file()` pointer in the section where the decision that needs it is written. Where each entry goes is the user's call; that the map does not become `keyFiles` is not. Until they decide, carry the list over as a plain prose section so adoption stays faithful
- Use `cmd()` refs for any `npm run` commands mentioned in sections
- Convert `**Enforced by:** \`code-review\``rules to`guidance()` — code review is not a mechanical enforcement
- For rules with no annotation, add a `// TODO: classify as enforce() or guidance()` comment
- Keep rule IDs as kebab-case versions of the heading text
- Preserve the `**Why:**` text as the second argument to `enforce()` or `guidance()`
- If sections reference other files or skills, use `ref()` for cross-references

### Step 4: Verify the Spec Compiles

Run:

```bash
npm run build
npx vigiles compile CLAUDE.md.spec.ts
```

Compare the compiled output against the original file. Key differences are expected (formatting, section ordering), but all rules, commands, and prose content should be preserved (a file map is the exception — see the `keyFiles` guideline above).

### Step 5: Present the Result

Show the user:

1. The generated spec file
2. How many rules were converted (enforce vs guidance vs TODO)
3. How many file/cmd refs were added for stale reference detection
4. The command to compile: `npx vigiles compile`
5. The command to verify: `npx vigiles lint`

Ask if they want you to write the file. If yes, also suggest adding to `.gitignore` or updating CI to run `vigiles compile` and `vigiles lint`.

### Step 6: Optional — Set Up CI

If the user wants CI integration, suggest adding to their GitHub Actions workflow:

```yaml
- name: Compile specs
  run: npx vigiles compile
- name: Verify references + integrity
  run: npx vigiles lint
```

Or using the vigiles GitHub Action:

```yaml
- uses: zernie/vigiles@v1
  with:
    command: lint
```

© zernie · MIT · zernie/vigiles

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set7

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor