analyze
Skill98 starsChanged 9 months agoMITView on GitHub
Analyze consistency across spec, plan, tasks, and checklist. Use before implementation. Triggers on: analyze consistency, check artifacts, validate feature.
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 53 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 35
Read all feature artifacts
- Distinctive: line 36
Check for consistency issues
- Very specific: line 81
Verify that prd.json contains for EVERY story:
- Distinctive: line 96
Verify that ALL THREE quality gates are present in acceptance criteria:
- Distinctive: line 147
WARNING: Should fix before implementation
- Very specific: line 162
Use the template at templates/analysis-report.md:
- Distinctive: line 202
Update progress.txt with analysis results
- Distinctive: line 215
Run before starting implementation
“Common” is measured: kept by at least 6 in 10 of the 53 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Cross-Artifact Consistency Analyzer
Validate consistency across feature artifacts before implementation.
SpecKit Workflow
This skill is Step 5 of 6 in the Relentless workflow:
specify → plan → tasks → convert → analyze → implement
Prerequisites (ALL must exist):
spec.md- Feature specificationplan.md- Technical implementation plantasks.md- User stories and tasksprd.json- Converted PRD with routing metadata (run convert first)checklist.md- Quality validation checklist (recommended)
Purpose:
- Validate consistency across ALL artifacts
- Catch gaps before implementation begins
- Ensure TDD and routing compliance
- Verify quality gates are defined
The Job
- Read all feature artifacts
- Check for consistency issues
- Validate TDD compliance
- Validate routing metadata
- Validate quality gates
- Validate against constitution
- Generate analysis report
Files to Analyze
Required:
relentless/constitution.mdrelentless/features/NNN-feature/spec.mdrelentless/features/NNN-feature/plan.mdrelentless/features/NNN-feature/tasks.mdrelentless/features/NNN-feature/prd.jsonrelentless/features/NNN-feature/checklist.md
Optional:
relentless/features/NNN-feature/progress.txt
Validation Checks
1. Completeness
- All functional requirements from spec have tasks
- All tasks reference spec requirements
- Plan addresses all spec requirements
- Checklist covers all tasks
2. TDD Compliance Validation (MANDATORY)
Verify that:
- Every story in tasks.md has test acceptance criteria
- Test specifications exist in plan.md
- Checklist includes test validation items
- No stories marked "tests optional"
- Given/When/Then format used in acceptance criteria
Flag as CRITICAL if TDD requirements are missing.
3. Routing Metadata Validation (MANDATORY)
Verify that prd.json contains for EVERY story:
routing.complexity- simple/medium/complex/expertrouting.harness- claude/gemini/codex/opencode/amp/droidrouting.model- specific model namerouting.mode- free/cheap/good/geniusrouting.estimatedCost- cost in USD
Also verify:
- Routing preference in spec.md matches prd.json routing mode
- Complexity classifications are reasonable for story scope
Flag as CRITICAL if routing metadata is missing.
4. Quality Gates Validation (MANDATORY)
Verify that ALL THREE quality gates are present in acceptance criteria:
- Typecheck requirement (
bun run typecheckpasses with 0 errors) - Lint requirement (
bun run lintpasses with 0 errors AND 0 warnings) - Test requirement (
bun testpasses)
Flag as CRITICAL if any quality gate is missing.
5. Constitution Compliance
- Plan follows MUST rules
- Tasks include required quality checks
- Testing requirements met
- Security requirements addressed
- No
anytypes planned
6. Dependency Consistency
- Task dependencies are valid (no circular refs)
- Referenced dependencies exist
- Dependency order makes sense
7. Scope Consistency
- Plan doesn't include out-of-scope items
- Tasks match plan scope
- No scope creep in checklist
8. Data Model Consistency
- Entities mentioned in spec are in plan
- Plan data models match spec requirements
- Tasks create required entities
9. API Consistency
- Endpoints in plan match spec scenarios
- Tasks implement all planned endpoints
- Checklist validates all endpoints
10. Testing Coverage
- Each task has test acceptance criteria
- Checklist includes test validation
- Test types match constitution requirements
Issue Severity
CRITICAL: Blocks implementation - MUST fix before proceeding
- Constitution MUST rule violations
- Missing TDD requirements
- Missing routing metadata in prd.json
- Missing quality gate requirements
- Circular dependencies
- Missing required artifacts
WARNING: Should fix before implementation
- Incomplete coverage of requirements
- Ambiguous acceptance criteria
- Missing test criteria for some stories
- Routing preference mismatch (spec vs prd.json)
INFO: Nice to have
- Style inconsistencies
- Minor gaps in checklist
- Optimization opportunities
Report Format
Use the template at templates/analysis-report.md:
# Consistency Analysis Report
**Feature:** [feature-name]
**Date:** [date]
**Status:** [PASS | FAIL | WARNINGS]
## Summary
| Category | Status | Issues |
|----------|--------|--------|
| Completeness | ✅/❌ | [count] |
| TDD Compliance | ✅/❌ | [count] |
| Routing Validation | ✅/❌ | [count] |
| Quality Gates | ✅/❌ | [count] |
| Constitution | ✅/❌ | [count] |
| Dependencies | ✅/❌ | [count] |
## Critical Issues
### CRIT-001: [Issue Title]
**Location:** [file]
**Details:** [description]
**Fix:** [required action]
## Recommendations
1. [Action item 1]
2. [Action item 2]
**Next Step:** /relentless.implement (if PASS) or fix issues (if FAIL)Output
- Save analysis report to
relentless/features/NNN-feature/analysis-report.md - Update progress.txt with analysis results
- Report:
- Overall status: PASS/FAIL/WARNINGS
- Critical issues count
- TDD compliance: PASS/FAIL
- Routing validation: PASS/FAIL
- Quality gates: PASS/FAIL
- Next step:
/relentless.implementor fix issues
Notes
- Run before starting implementation
- Constitution compliance is non-negotiable
- TDD compliance is non-negotiable
- Routing metadata is required for all stories
- Quality gates (typecheck, lint, test) are mandatory
- Fix critical issues immediately
- Warnings can sometimes be deferred
- Re-run after making fixes
Other versions63 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 63
- anthropics/knowledge-work-plugins★ 34ksame name
- Yeachan-Heo/oh-my-codex★ 34ksame name
- oxsecurity/megalinter★ 2.6ksame name
- H-mmer/pentest-agents★ 815same name
- hardisgroupcom/sfdx-hardis★ 410same name
- nwiizo/tfmcp★ 373same name
- hsantanna88/clo-author★ 262same name
- hugosantanna/clo-author★ 262same name
- atelier-fashion/adlc-toolkit★ 173same name
- assafkip/huntkit★ 72same name
53 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use revise, write and 6 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
stormlightlabsSkillrevise
Address review comments on an open pull request and push the fixes. Use for /edit, /revise, or when asked to respond to review feedback on a PR number.
Also in 3 projects that use this
DockerSkillwrite
Write or edit reader-facing technical prose for immediate comprehension. Use for documentation, PR titles and descriptions, release notes, design documents, user-facing explanations, and substantive comments. Also use when asked to make writing clearer, more natural, less AI-generated, or easier to read. For documentation fixes, handles edits, formatting, self-review, and commits after research identifies what to change. Do not use for code-only tasks with no prose deliverable.
Also in 6 projects that use this
H-mmerSkillsubmit
Draft and submit a vulnerability report to the bug bounty platform. Reads scope.yaml for platform/program, uses brain + findings for content. Always drafts first for review.
Also in 3 projects that use this
Itsokay-coSkilldiscover
Automated pattern discovery — finds what correlates with your best and worst sleep nights. Scans workouts, meals, caffeine, tags, gut scores, and timing patterns. Use when the user wants to know what actually affects their sleep.
Also in 5 projects that use this
MehdibargachSkillpersona
Generate actionable user personas from a product description, user data, or research notes. Not marketing fluff — behavioral personas that drive product decisions.
Also in 3 projects that use this
anshul-garg27Skillrepurpose
Transform one piece of content into 10+ platform-native formats - threads, posts, scripts, newsletters, and more
Also in 3 projects that use this
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- checklistSkill
- clarifySkill
- constitutionSkill
- convertSkill
- implementSkill
- learnSkill
- planSkill
- prdSkill
- relentlessSkill
- specifySkill
- tasksSkill
- taskstoissuesSkill
- validatorsSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

