spec-integrity-analysis
Skill1 starsChanged 6 months agoMITView on GitHub
Perform quality gate analysis on ISO-style specifications to ensure completeness, consistency, and atomicity.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- agent-ix/quoinedited, first seen Jun 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- agent-ix/quoin★ 2074% same
Wrote their own version · 0
None found.
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 repository19 other files it gives its agents.
- spec-app-reviewSkill
- spec-blueprintSkill
- spec-dependency-analysisSkill
- spec-evidence-analysisSkill
- spec-failure-domain-analysisSkill
- specifySkill
- spec-matrixSkill
- spec-object-reviewSkill
- spec-reviewSkill
- spec-risk-complexity-analysisSkill
- spec-scope-boundary-analysisSkill
- spec-security-analysisSkill
- spec-to-planSkill
- spec-us-to-frSkill
- spec-write-frSkill
- spec-write-itSkill
- spec-write-nfrSkill
- spec-write-strSkill
- spec-write-usSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
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 13
Verify every User Story (US) maps to >= 1 Functional/System Requirement (FR/SR).
- Distinctive: line 14
Verify every FR/SR maps to >= 1 Stakeholder Requirement (StR).
- Distinctive: line 15
Verify every FR/SR maps to >= 1 verification method.
- Distinctive: line 16
Verify every NFR is explicitly scoped and referenced by affected FR/SR.
- Distinctive: line 23
Rule: No requirement may have more than one valid interpretation.
- Very specific: line 40
Ensure each FR/SR/StR defines a *single* behavior/obligation.
- Distinctive: line 41
Ensure behavior is externally observable.
- Distinctive: line 42
Ensure behavior is verifiable by test, inspection, analysis, or demonstration.
- Very specific: line 46
Before finalizing, verify against spec-failure-domain-analysis:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Specification Integrity Analysis
This skill performs a quality gate analysis on specifications (User Stories, FR/SR, StR, NFR) before task generation.
Process
- Completeness Analysis:
- Verify every User Story (US) maps to >= 1 Functional/System Requirement (FR/SR).
- Verify every FR/SR maps to >= 1 Stakeholder Requirement (StR).
- Verify every FR/SR maps to >= 1 verification method.
- Verify every NFR is explicitly scoped and referenced by affected FR/SR.
- Deliverable: Traceability matrix (US -> FR/SR -> StR -> Verification).
Consistency & Conflict Analysis:
- Identify contradictory constraints (e.g., latency vs security).
- Identify duplicated requirements with different wording.
- Identify hidden assumptions embedded in prose.
- Rule: No requirement may have more than one valid interpretation.
Hidden Assumption Probes
For every FR, explicitly check for these patterns:
Pattern Probe Question FR delegates to an external CLI (git, gh, cookiecutter, etc.) Is there an NFR declaring the tool's minimum version, detection method, and user-facing error when absent? FR performs a lookup over multiple sources (registries, plugins, taps) Is there an explicit tie-breaking policy when two sources return the same key? (first-wins, last-wins, error, merge — must be a stated decision) FR calls an external API that returns paginated results Does an NFR state whether full enumeration is required? If a cap is acceptable, is it documented as a known limitation? FR calls an external API in a loop or concurrently Does an NFR declare max concurrency, rate limit awareness, retry policy, and that errors must surface (not be silently swallowed)? FR involves a scaffolding or generation command Are both an interactive mode (human at terminal) and a scripted/CI mode explicitly specified with their flags? FR calls an authenticated external API Does an NFR declare the required auth scopes and mandate a clear user-facing error when scope is insufficient (not silent empty results)? FR depends on a package or service not yet implemented Is the interim fallback and eventual resolution chain documented? Is the hardcoded default traceable to a known stub? - Atomicity & Testability Analysis:
- Ensure each FR/SR/StR defines a single behavior/obligation.
- Ensure behavior is externally observable.
- Ensure behavior is verifiable by test, inspection, analysis, or demonstration.
- Action: Flag non-testable requirements for rewriting or splitting.
Failure Domain Check
Before finalizing, verify against spec-failure-domain-analysis:
- Extension failures, Identity keys, Evaluation purity, Topological robustness.
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.

