speckit.analyze

Analyze spec.md, plan.md, and tasks.md for inconsistencies, gaps, and constitution violations.

Updated Aug 20, 2026
One-click install
npx skills add https://github.com/hduoc2003/leviathan-guardian --skill speckit-analyze-hduoc2003
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speckit.analyze
Source: https://github.com/hduoc2003/leviathan-guardian/tree/main/.agents/skills/speckit-analyze
Command: npx skills add https://github.com/hduoc2003/leviathan-guardian --skill speckit-analyze-hduoc2003

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Specification-driven development produces multiple artifacts (spec, plan, tasks) that can drift apart, leaving duplicated requirements, ambiguous wording, uncovered requirements, and conflicts with project principles that only surface during implementation. ## Core Features & Use Cases - Cross-Artifact Consistency Analysis: Detects duplications, ambiguities, underspecification, terminology drift, and conflicting requirements across spec.md, plan.md, and tasks.md. - Coverage Mapping: Builds a requirement-to-task coverage map and reports requirements with zero tasks and tasks with no mapped requirement. - Constitution Enforcement: Validates artifacts against the project constitution, treating MUST-principle violations as CRITICAL findings. - Use Case: After running /speckit.tasks to generate tasks.md, run this analysis to receive a severity-ranked report with a coverage summary and metrics before starting implementation. ## Quick Start Run the speckit analyze command to check my spec, plan, and tasks files for inconsistencies and coverage gaps before implementation.

Frequently Asked Questions about speckit.analyze

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check spec, plan, and tasks files for inconsistencies?▼

Run the analysis after tasks.md is generated. It loads spec.md, plan.md, and tasks.md, builds requirement and task inventories, and reports duplications, ambiguities, coverage gaps, and conflicts in a severity-ranked table.

When should I run a specification consistency analysis?▼

Run it after /speckit.tasks has produced a complete tasks.md and before /speckit.implement. The command aborts with an error if any required artifact is missing, since it needs all three files to perform cross-artifact detection.

Does the analysis modify my spec or tasks files?▼

No, the analysis is strictly read-only and never modifies files. It outputs a structured report and only offers remediation suggestions, which require explicit user approval before any follow-up editing commands are invoked.

What severity levels does the analysis report use?▼

Findings are classified as CRITICAL, HIGH, MEDIUM, or LOW. Constitution MUST violations and uncovered core requirements are CRITICAL, while style issues are LOW. The report limits output to 50 findings with an overflow summary.

What happens if requirements have no matching tasks?▼

Requirements with zero associated tasks appear in the coverage summary table and metrics. If the gap blocks baseline functionality it is flagged CRITICAL, and the report recommends resolving it before proceeding to implementation.