speckit-analyze

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

1.47x

Quality

67%

Does it follow best practices?

Impact

90%

1.47x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/speckit-analyze/SKILL.md

Evaluation results

82%

25%

Feature Specification Audit

Core analysis workflow with structured report

Criteria

Without context

With context

Prerequisites script usage

FEATURE_DIR path derivation

50%

66%

Findings table present

62%

100%

Stable category-prefixed IDs

100%

Ambiguity flag: vague adjective

75%

100%

Coverage gap: SC-002 or SC-004

100%

Constitution alignment section

33%

100%

CRITICAL severity for constitution violation

25%

100%

Coverage summary table

100%

Metrics section

87%

100%

Next Actions block

87%

100%

Remediation offer

No file modifications

100%

SC exclusion of business KPIs

50%

100%

95%

57%

Pre-Implementation Spec Review with Extension Hooks

Extension hook processing and formatting

Criteria

Without context

With context

Dot-to-hyphen conversion

70%

Disabled hook skipped

30%

100%

Condition hook skipped

30%

100%

Optional pre-hook format

100%

Mandatory pre-hook format

100%

Optional after-hook format

100%

Mandatory after-hook format

75%

Analysis findings table

62%

100%

Coverage summary present

87%

100%

Metrics section present

100%

No file modifications

100%

95%

Specification Consistency Review for Notifications Feature

Six-pass detection and severity classification

Criteria

Without context

With context

TODO placeholder flagged

100%

Vague adjective flagged

100%

Constitution violation: vendor independence

100%

Constitution violation is CRITICAL

100%

Coverage gap: SC-002

100%

SC-003 excluded from buildable SCs

57%

100%

Inconsistency: Twilio specification

87%

100%

Severity classification

100%

Category-prefixed finding IDs

16%

Metrics section

100%

Next Actions: resolve before implement

100%

No file modifications

100%

Repository: mixpanel/mixpanel-headless
Commit: 3ce3191

Evaluated: 2 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Feature Specification Audit Pre-Implementation Spec Review with Extension Hooks Specification Consistency Review for Notifications Feature

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.