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-04-testify
skills/iikit-04-testify/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 excels across all dimensions. It provides specific concrete actions, includes comprehensive natural trigger terms that developers would actually use, explicitly addresses both what and when, and carves out a distinctive niche in the BDD/TDD space with unique technical markers like assertion integrity hashes.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generate Gherkin .feature files', 'produces executable BDD scenarios with traceability tags', 'computes assertion integrity hashes', and 'locks acceptance criteria'. These are precise, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (generate Gherkin files, produce BDD scenarios, compute hashes, lock criteria) AND when with explicit 'Use when...' clause listing five specific trigger scenarios including TDD, spec-based test creation, and red-green-refactor workflows. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'TDD', 'writing tests first', 'test cases from a spec', 'acceptance criteria', 'red-green-refactor', 'Gherkin', '.feature files', 'BDD scenarios'. These match how developers naturally discuss test-driven development. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: focuses specifically on pre-implementation BDD/Gherkin generation with hash verification. The combination of 'Gherkin', '.feature files', 'assertion integrity hashes', and 'traceability tags' creates a unique fingerprint unlikely to conflict with general testing or documentation skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent actionability and workflow clarity. The multi-step TDD process is clearly sequenced with validation gates, hash verification for integrity, and comprehensive error handling. Minor verbosity from duplicating Windows commands throughout and some sections that could be more concise prevent a perfect score on token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (e.g., repeating Windows equivalents for every command, verbose error handling table). The content assumes Claude's competence in most areas but could be tightened in places like the tag conventions section. | 2 / 3 |
Actionability | Provides fully executable bash/PowerShell commands, specific file paths, concrete Gherkin tag conventions, and exact commit message formats. The transformation rules reference templates and examples, making guidance copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear numbered sequence with explicit validation checkpoints (prerequisites check, checklist gate, acceptance scenario validation, hash storage). Includes error handling table with specific recovery actions and idempotency rules for handling existing files. | 3 / 3 |
Progressive Disclosure | Well-structured with clear section hierarchy. Appropriately references external files (constitution-loading.md, gherkin-reference.md, testspec-template.md) for detailed content while keeping the main skill focused on workflow. References are one level deep and clearly signaled. | 3 / 3 |
Total | 11 / 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.