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-bugfix
skills/iikit-bugfix/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 a well-crafted skill description that excels across all dimensions. It provides specific concrete actions, uses natural trigger terms users would actually say, includes an explicit 'Use when...' clause with multiple scenarios, and clearly distinguishes itself from related skills by mentioning what it doesn't do (full specification process).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'creates a structured bugs.md record', 'generates fix tasks in tasks.md', and 'imports from or creates GitHub issues'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (creates bugs.md record, generates fix tasks, handles GitHub issues) AND when with explicit 'Use when...' clause covering multiple trigger scenarios (fixing bugs, reporting defects, importing GitHub issues, triaging errors). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'bug', 'defect', 'GitHub issue', 'error', 'fixing a bug', 'triaging'. Good coverage of variations a user might naturally use when reporting problems. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on bug reporting workflow with distinct triggers (bugs.md, GitHub issues, defects). The mention of 'without running the full specification process' explicitly differentiates it from related specification 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 process is clearly sequenced with validation checkpoints, conditional flows, and comprehensive error handling. Minor conciseness issues exist with repeated platform-specific command blocks and a duplicate step number, but these don't significantly impact usability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (e.g., repeating Unix/Windows command variants throughout, duplicate step numbering with two Step 13s). Some sections could be tightened, but overall respects Claude's intelligence. | 2 / 3 |
Actionability | Provides fully executable bash/PowerShell commands, specific file paths, concrete markdown templates, and exact git commit formats. All guidance is copy-paste ready with clear variable substitution patterns. | 3 / 3 |
Workflow Clarity | Clear 13-step sequence with explicit validation checkpoints (Step 4 validates feature, Step 10.4 verifies hash), conditional branching (GitHub vs text input, TDD vs non-TDD), and error handling table with specific responses for each failure mode. | 3 / 3 |
Progressive Disclosure | Well-structured with clear references to external files (constitution-loading.md, bugs-template.md) that are one level deep. Content is appropriately organized with numbered steps, tables for errors, and templates inline where needed. | 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.