tessl-labs/intent-integrity-kit
Closing the intent-to-code chasm - specification-driven development with BDD verification chain
94
Quality
94%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
iikit-06-analyze
skills/iikit-06-analyze/SKILL.md
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates specific validation capabilities (requirement tracing, tech stack matching, constitution compliance) and provides explicit trigger conditions. The description uses proper third-person voice, includes natural user terminology, and carves out a distinct niche that would be easily distinguishable from other skills in a large skill library.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'checks that every spec requirement traces to tasks', 'plan tech stack matches task file paths', and 'constitution principles are satisfied across all artifacts'. These are precise, verifiable operations. | 3 / 3 |
Completeness | Clearly answers both what (validate cross-artifact consistency with three specific checks) AND when (explicit 'Use when...' clause listing four trigger scenarios: consistency check, requirements traceability, detecting conflicts, auditing alignment). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'consistency check', 'requirements traceability', 'conflicts between design docs', 'auditing alignment', 'spec requirement', 'tech stack'. Good coverage of domain-specific but user-accessible terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focusing on cross-artifact validation, requirements traceability, and constitution principles. The specific combination of spec-to-task tracing, tech stack matching, and constitution compliance is unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary skill document that demonstrates excellent token efficiency while providing comprehensive, actionable guidance for a complex multi-step analysis workflow. The clear sequencing with explicit validation checkpoints, concrete output formats, and well-organized progressive disclosure make it highly effective. The skill appropriately assumes Claude's competence while providing precise specifications for detection passes, severity levels, and output formatting.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is dense and efficient, using terse bullet points, tables, and code blocks without explaining concepts Claude already knows. Every section serves a specific purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides fully executable bash/PowerShell commands, specific file paths, exact output formats with markdown tables, and concrete detection criteria. The health score formula and JSON schema are copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear numbered sequence from prerequisites through execution to commit and dashboard refresh. Includes explicit validation gates (checklist gate, prerequisites check), error handling (re-run if needs_selection), and decision points (CRITICAL issues block progression). | 3 / 3 |
Progressive Disclosure | Main skill provides overview with well-signaled one-level-deep references to supporting docs (constitution-loading.md, conversation-guide.md, checklist-gate.md, phase-separation-rules.md, model-recommendations.md). Content is appropriately split between inline instructions and referenced materials. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.