consistency
Skill2 starsChanged 4 months agoMITView on GitHub
Read-only cross-consistency analysis between a spec and the rest of the factory's artifacts (business rules, ADRs, as-is, .claude/rules rules, task plan). Use before the DoR gate and the Architecture gate, or when asked to "analyze consistency" of a spec.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- jthingelstad/elixir-mcptheir own version, first seen Nov 4, 2026
- jantichy/claudetheir own version, first seen Oct 27, 2026
- DoKu67/claude-code-skilstheir own version, first seen Oct 16, 2026
- feelthefusion/skill-starter-kittheir own version, first seen Oct 13, 2026
- RubyEyedReaper/Odin-Skillstheir own version, first seen Aug 15, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- jantichy/claude★ 45same name
- DoKu67/claude-code-skils★ 4same name
- jthingelstad/elixir-mcp★ 1same name
- feelthefusion/skill-starter-kit★ 0same name
- RubyEyedReaper/Odin-Skills★ 0same name
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.
In this repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- as-is-learnSkill
- as-isSkill
- as-is-syncSkill
- clarifySkill
- context-reportSkill
- convergeSkill
- harness-initSkill
- implement-taskSkill
- orchestrateSkill
- repo-addSkill
- repo-mapSkill
- spec-createSkill
- spec-reviewSkill
- system-mapSkill
The file
Files
Analyze the consistency of spec $ARGUMENTS against the factory's knowledge. STRICTLY READ-ONLY: do not edit any artifact; only report.
Semantic model (build first)
- Spec inventory: stories (Hx, priority), ACs in Gherkin, SC-xx, RN-xx cited, plan tasks (Tx with repo label).
- Contrast artifacts:
knowledge/business-rules.md,knowledge/decisions/(current ADRs),knowledge/as-is/(INDEX and affected repos),.claude/rules/*.md(including the domain profile if the repo declares it in repos.yaml), context packs of the affected repos.
Six detection passes
- A · Duplication: stories/ACs/SCs that repeat the same thing in other words.
- B · Ambiguity: non-measurable adjectives ("fast, robust, scalable,
intuitive, secure" without a number), pronouns without a referent, pending
[NEEDS CLARIFICATION]markers. - C · Underspecification: story without AC, AC without an observable outcome, SC without a threshold, dependency mentioned but not registered in repos.yaml.
- D · Alignment with rules: contradictions with
.claude/rules/*or withknowledge/business-rules.md(cited RN that does not exist, or a current one the spec violates). Every conflict in this pass is automatically CRITICAL. - E · Coverage: requirements (AC/SC) without a task in the plan and tasks
without a requirement justifying them — in BOTH directions. Task REPO
labels that are neither registered repos nor
[workspace](the[P]parallelism marker and the[P1]/[P2]/[P3]story priorities are not repo labels; do not flag them). If the spec has no plan yet, skip the pass and declare it. - F · Contradictions: spec vs as-is (claims something the code
contradicts), spec vs current ADR, terminology drift (same entity with
two names), tasks whose order violates
deploy_order.
Report (maximum 50 findings)
| ID | Pass | Severity | Location | Finding | Recommendation | Severities: CRITICAL (blocks gate) / HIGH / MEDIUM / LOW. Then an AC/SC ↔ tasks coverage table. Final verdict:
- FIT FOR GATE — no CRITICAL and no unjustified HIGH.
- DO NOT PASS THE GATE — there are CRITICAL (or unjustified HIGH) findings; prioritized list of corrections. The changes are applied by the create-review-improve cycle, never by this skill.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.