# Spec Linter

> Review a feature spec for clarity, testability, and completeness before implementation. Use when this capability is needed.

- Skill: `tomevault-io/spec-linter` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add tomevault-io/spec-linter`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/spec-linter/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: tomevault-io (https://skillmd.com/u/tomevault-io)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/tomevault-io/spec-linter

---


1) Read the target `spec/features/<feature-id>-<slug>.md` and project conventions from `AGENTS.md`.
   - `<feature-id>` must use `F<epic>.<feature>` (example: `F1.1`).
2) Check for:
   - Clear problem statement and scope/non-scope
   - Acceptance criteria that are testable and unambiguous
   - Inputs/outputs defined (formats, schemas, examples)
   - Edge cases + error handling expectations
   - Test plan is present (unit/integration/e2e as appropriate)
   - ADR linkage if decisions are involved
3) Produce a short “Spec Gaps” list, then either:
   - Propose edits, or
   - Apply edits directly if the user asks.
4) End by recommending the next skill (usually `write-tests` or `implement-feature`).

---
> Converted and distributed by [TomeVault](https://tomevault.io/claim/rafaie) — claim your Tome and manage your conversions.
<!-- tomevault:4.0:skill_md:2026-04-13 -->