Skip to content
Back to skills

Speckit.Analyze

ASecurity

Consistency Checker - Audit spec, plan, tasks, constitution, and evidence for gaps and conflicts.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 24, 2026
ai-agentsrailsdockersecurity

Security analysis

A100/100

Scanned September 24, 2026

npx -y skills add wedabro/bro-skills --skill speckit.analyze --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Speckit.Analyze?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Speckit.Analyze
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/wedabro-speckit-analyze/badge)](https://www.skillsdirectory.com/skills/wedabro-speckit-analyze)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: speckit.analyze
description: Consistency Checker - Audit spec, plan, tasks, constitution, and evidence for gaps and conflicts.
---

## Mission
Produce a reproducible, read-only consistency audit before implementation.

## Inputs and Outputs
- Read `spec.md`, `plan.md`, `tasks.md`, constitution, and referenced artifacts.
- Write `.agents/memory/analyze-report.md` and print a gap table with coverage score.

## Protocol
1. Validate files, headings, IDs, user-story links, paths, and dependency references; report malformed inputs.
2. Map every requirement and scenario to a plan section and task. Mark missing, ambiguous, conflicting, or unverified links.
3. Compare technical choices and gates against constitution, security, Docker, ENV, and scope rules.
4. Reconcile data models, contracts, migrations, tests, and operational tasks; calculate `matched / total * 100`.
5. Classify gaps as Critical/High/Medium/Low and propose the smallest corrective artifact without editing source files.

## Completion Gate
Coverage is complete only when every requirement has a traceable plan and task, all conflicts are listed, and the report states its evidence limits.

## Guard Rails
Read-only. Never silently infer missing requirements or edit spec, plan, tasks, or code.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.