Skip to main content
prompt CX Codex GP ChatGPT

speckit.analyze — Claude Code prompt: cross-artifact spec check

speckit.analyze runs a read-only pass over spec.md, plan.md and tasks.md, then prints a report on contradictions, duplicates and requirements that no task covers.

MIT ★ 110 updated 2026-10-19

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/speckit.analyze.md
Open on GitHub

What speckit.analyze does

The command wants a finished feature folder. spec.md, plan.md and a complete tasks.md all have to exist; fire it before /speckit.tasks and it stops with an error telling you which step to run first.

It starts with .specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks from the repo root to find the feature directory and its documents. Then it builds an inventory of requirements with stable keys, maps each task back to a requirement or user story, and runs six checks: near-duplicate requirements, vague adjectives with no measurable criteria, leftover placeholders, constitution conflicts, requirements with zero tasks, terminology drift between files.

Nothing on disk changes. You get a findings table with severity, location and a suggested fix, plus a coverage table and counts, capped at 50 rows. Anything clashing with a MUST rule in .specify/memory/constitution.md is marked CRITICAL and has to be settled in the spec, plan or tasks — the principle itself stays put. Edits happen only if you ask for them.

What it helps with

  • Catch a requirement in spec.md that no task implements
  • Spot a stack mismatch between plan.md and the spec
  • Collect duplicate and vague requirements in one report before coding
  • Check the plan against the project constitution
  • List tasks that trace back to no requirement or user story

Example prompts for the agent

  • /speckit.analyze — check the 003-payments artifacts before I start coding
  • Run /speckit.analyze and show me which requirements have no tasks
  • /speckit.analyze with focus on constitution conflicts

How to install speckit.analyze

Manually: put the files in place

.claude/commands/speckit.analyze.md

Questions about speckit.analyze

How do I install speckit.analyze in Claude Code?

Place the command file at .claude/commands/speckit.analyze.md in your project. It then shows up as /speckit.analyze.

What does speckit.analyze do?

It compares the three artifacts and prints a severity-ranked report on inconsistencies, duplicates, ambiguity and coverage gaps. Your files stay untouched.

When should I run it?

Once /speckit.tasks has written a complete tasks.md, and before implementation. A missing artifact makes the command abort and name the step you skipped.

Source text

speckit.analyze.md · MIT
---
description: Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
---

## User Input

```text
$ARGUMENTS
```

You **MUST** consider the user input before proceeding (if not empty).

## Goal

Identify inconsistencies, duplications, ambiguities, and underspecified items across the three core artifacts (`spec.md`, `plan.md`, `tasks.md`) before implementation. This command MUST run only after `/speckit.tasks` has successfully produced a complete `tasks.md`.

## Operating Constraints

**STRICTLY READ-ONLY**: Do **not** modify any files. Output a structured analysis report. Offer an optional remediation plan (user must explicitly approve before any follow-up editing commands would be invoked manually).

**Constitution Authority**: The project constitution (`.specify/memory/constitution.md`) is **non-negotiable** within this analysis scope. Constitution conflicts are automatically CRITICAL and require adjustment of the spec, plan, or tasks—not dilution, reinterpretation, or silent ignoring of the principle. If a principle itself needs to change, that must occur in a separate, explicit constitution update outside `/speckit.analyze`.

## Execution Steps

### 1. Initialize Analysis Context

Run `.specify/scripts/bash/check-prerequisites.sh --json --require-tasks --include-tasks` once from repo root and parse JSON for FEATURE_DIR and AVAILABLE_DOCS. Derive absolute paths:

- SPEC = FEATURE_DIR/spec.md
- PLAN = FEATURE_DIR/plan.md
- TASKS = FEATURE_DIR/tasks.md

Abort with an error message if any required file is missing (instruct the user to run missing prerequisite command).
For single quotes in args like "I'm Groot", use escape syntax: e.g 'I'\''m Groot' (or double-quote if possible: "I'm Groot").

### 2. Load Artifacts (Progressive Disclosure)

Load only the minimal necessary context from each artifact:

**From spec.md:**

- Overview/Context
- Functional Requirements
- Non-Functional Requirements
- User Stories
- Edge Cases (if present)

**From plan.md:**

- Architecture/stack choices
- Data Model references
- Phases
- Technical constraints

**From tasks.md:**

- Task IDs
- Descriptions
- Phase grouping
- Parallel markers [P]
- Referenced file paths

**From constitution:**

- Load `.specify/memory/constitution.md` for principle validation

### 3. Build Semantic Models

Create internal representations (do not include raw artifacts in output):

- **Requirements inventory**: Each functional + non-functional requirement with a stable key (derive slug based on imperative phrase; e.g., "User can upload file" → `user-can-upload-file`)
- **User story/action inventory**: Discrete user actions with acceptance criteria
- **Task coverage mapping**: Map each task to one or more requirements or stories (inference by keyword / explicit reference patterns like IDs or key phrases)
- **Constitution rule set**: Extract principle names and MUST/SHOULD normative statements

### 4. Detection Passes (Token-Efficient Analysis)

Focus on high-signal findings. Limit to 50 findings total; aggregate remainder in overflow summary.

#### A. Duplication Detection

- Identify near-duplicate requirements
- Mark lower-quality phrasing for consolidation

#### B. Ambiguity Detection

- Flag vague adjectives (fast, scalable, secure, intuitive, robust) lacking measurable criteria
- Flag unresolved placeholders (TODO, TKTK, ???, `<placeholder>`, etc.)

#### C. Underspecification

- Requirements with verbs but missing object or measurable outcome
- User stories missing acceptance criteria alignment
- Tasks referencing files or components not defined in spec/plan

#### D. Constitution Alignment

- Any requirement or plan element conflicting with a MUST principle
- Missing mandated sections or quality gates from constitution

#### E. Coverage Gaps

- Requirements with zero associated tasks
- Tasks with no mapped requirement/story
- Non-functional requirements not reflected in tasks (e.g., performance, security)

#### F. Inconsistency

- Terminology drift (same concept named differently across files)
- Data entities referenced in plan but absent in spec (or vice versa)
- Task ordering contradictions (e.g., integration tasks before foundational setup tasks without dependency note)
- Conflicting requirements (e.g., one requires Next.js while other specifies Vue)

### 5. Severity Assignment

Use this heuristic to prioritize findings:

- **CRITICAL**: Violates constitution MUST, missing core spec artifact, or requirement with zero coverage that blocks baseline functionality
- **HIGH**: Duplicate or conflicting requirement, ambiguous security/performance attribute, untestable acceptance criterion
- **MEDIUM**: Terminology drift, missing non-functional task coverage, underspecified edge case
- **LOW**: Style/wording improvements, minor redundancy not affecting execution order

### 6. Produce Compact Analysis Report

Output a Markdown report (no file writes) with the following structure:

## Specification Analysis Report

| ID | Category | Severity | Location(s) | Summary | Recommendation |
|----|----------|----------|-------------|---------|----------------|
| A1 | Duplication | HIGH | spec.md:L120-134 | Two similar requirements ... | Merge phrasing; keep clearer version |

(Add one row per finding; generate stable IDs prefixed by category initial.)

**Coverage Summary Table:**

| Requirement Key | Has Task? | Task IDs | Notes |
|-----------------|-----------|----------|-------|

**Constitution Alignment Issues:** (if any)

**Unmapped Tasks:** (if any)

**Metrics:**

- Total Requirements
- Total Tasks
- Coverage % (requirements with >=1 task)
- Ambiguity Count
- Duplication Count
- Critical Issues Count

### 7. Provide Next Actions

At end of report, output a concise Next Actions block:

- If CRITICAL issues exist: Recommend resolving before `/speckit.implement`
- If only LOW/MEDIUM: User may proceed, but provide improvement suggestions
- Provide explicit command suggestions: e.g., "Run /speckit.specify with refinement", "Run /speckit.plan to adjust architecture", "Manually edit tasks.md to add coverage for 'performance-metrics'"

### 8. Offer Remediation

Ask the user: "Would you like me to suggest concrete remediation edits for the top N issues?" (Do NOT apply them automatically.)

## Operating Principles

### Context Efficiency

- **Minimal high-signal tokens**: Focus on actionable findings, not exhaustive documentation
- **Progressive disclosure**: Load artifacts incrementally; don't dump all content into analysis
- **Token-efficient output**: Limit findings table to 50 rows; summarize overflow
- **Deterministic results**: Rerunning without changes should produce consistent IDs and counts

### Analysis Guidelines

- **NEVER modify files** (this is read-only analysis)
- **NEVER hallucinate missing sections** (if absent, report them accurately)
- **Prioritize constitution violations** (these are always CRITICAL)
- **Use examples over exhaustive rules** (cite specific instances, not generic patterns)
- **Report zero issues gracefully** (emit success report with coverage statistics)

## Context

$ARGUMENTS

© alfredoperez · MIT · alfredoperez/speckit-companion

Similar prompts

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

From the same set83

The whole set →
speckit.tasks The speckit.tasks prompt turns feature design documents into a dependency-ordered tasks.md, grouped by user story. Use it to prepare an implementation plan from an existing spec. CX Codex GP ChatGPT ★ 110repo stars changelog-entry changelog-entry is a Claude Code command that writes a changelog entry from a PR or current diff and chooses its file and format. Run it with a PR number or no argument. CX Codex +1 ★ 110repo stars eval-speckit-extension eval-speckit-extension is a Claude Code skill that tests speckit-extension against a completed spec, verifying lifecycle hooks and .spec-context.json timestamps. CX Codex +1 ★ 110repo stars bench-experiment bench-experiment is a Claude Code command that runs a Conduit benchmark round and compares results with earlier sweeps to measure changes across selected cells. CX Codex +1 ★ 110repo stars speckit.companion.living-sync speckit.companion.living-sync updates living specs to match current working-tree changes in a single pass. Modifies existing spec files without regenerating them from scratch. CX Codex +1 ★ 110repo stars speckit.implement The speckit.implement prompt turns the plan in tasks.md into an ordered implementation run. It is listed for Claude Code and Codex. CX Codex GP ChatGPT ★ 110repo stars publish-all publish-all releases all four project components at once: the spec-kit extension, VS Code extension, Claude Code mod, and Copilot canvas. Runs only if changes are ready and pass QA checks. CX Codex +1 ★ 110repo stars speckit.companion.doctor speckit.companion.doctor audits spec run health by catching incomplete steps, unverified runs, and drift. Read-only, retroactive, and never halts on failures. CX Codex +1 ★ 110repo stars

Project sponsors

Companies that keep this analytics open