# speckit.analyze

speckit.analyze inspects spec.md, plan.md, and tasks.md for conflicts, gaps, and constitution violations before code generation. Runs in read-only mode.

- command · `type=command` · Claude Code, Codex, GitHub Copilot, Gemini CLI · ★ 117 repo stars
- Author: Chat2AnyLLM
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Chat2AnyLLM/awesome-claude-plugins/tree/HEAD/.claude/commands/speckit.analyze.md
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/commands/speckitanalyze

## What it does

The command evaluates consistency across a feature's specification, architectural plan, and task backlog. It is intended to run right after `/speckit.tasks` generates `tasks.md`. It extracts requirement slugs, maps them to planned tasks, and verifies constraints against `.specify/memory/constitution.md`.

The generated review highlights vocabulary drift, missing acceptance criteria, orphaned tasks, and conflicts with constitutional rules. Any contradiction with mandatory project principles is tagged as critical. Findings are capped at 50 table rows to keep token consumption low.

File modifications are completely locked out during execution. You get an inspection breakdown and optional remediation guidance instead. The process fails immediately if `.specify/scripts/bash/check-prerequisites.sh` or any of the three core documents are missing.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/commands/speckit.analyze.md` — Call it with /speckit.analyze. For all projects use ~/.claude/commands/

### Codex

**Manually: put the files in place**
- File: `~/.codex/prompts/speckit.analyze.md` — Call it with /prompts:speckit.analyze. Codex marks this format deprecated in favour of skills

### GitHub Copilot

**Manually: put the files in place**
- File: `.github/prompts/speckit.analyze.prompt.md`

### Gemini CLI

**Manually: put the files in place**
- File: `.gemini/commands/speckit.analyze.toml` — Gemini stores commands as TOML: the prompt text goes into the prompt field

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Chat2AnyLLM/awesome-claude-plugins/tree/HEAD/.claude/commands/speckit.analyze.md

## When to use it
- detect inconsistencies between specification, plan, and task files
- spot functional requirements missing execution tasks
- catch violations against mandatory rules in constitution.md
- flag ambiguous wording and lingering placeholder tokens

## Example prompts
- /speckit.analyze
- /speckit.analyze "focus on auth module"

## Similar
- [speckit-baseline](https://affpapa.org/en/nevibecode/skills/speckit-baseline.md) — skill · 1600 installs
- [speckit.companion.status](https://affpapa.org/en/nevibecode/commands/speckitcompanionstatus.md) — command · ★ 110 repo stars
- [speckit.companion.resume](https://affpapa.org/en/nevibecode/commands/speckitcompanionresume.md) — command · ★ 110 repo stars
- [tlc-spec-lean](https://affpapa.org/en/nevibecode/skills/tlc-spec-lean.md) — skill · ★ 7191 repo stars
- [speckit-specify](https://affpapa.org/en/nevibecode/skills/speckit-specify.md) — skill · 2700 installs
- [03-shadow-areas](https://affpapa.org/en/nevibecode/skills/03-shadow-areas.md) — skill · ★ 571 repo stars

From the same set: [chat2anyllm/awesome-claude-plugins](https://affpapa.org/en/nevibecode/by/chat2anyllm/awesome-claude-plugins.md) — 9 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
