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-core
skills/iikit-core/SKILL.md
Discovery
92%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 clearly articulates specific capabilities and includes explicit trigger guidance. The description effectively uses third person voice and covers both the 'what' and 'when' aspects. The main weakness is potential overlap with other project/workflow management skills due to some generic terminology, though the IIKit-specific naming provides reasonable distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Initialize an IIKit project', 'check feature progress', 'select the active feature', and 'display the workflow command reference'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (initialize project, check progress, select feature, display commands) AND when with explicit 'Use when...' clause covering multiple trigger scenarios (starting project, running init, checking status, switching features, looking up commands). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'starting a new project', 'running init', 'checking status', 'switching between features', 'available commands and phases'. Good coverage of variations like 'init' and 'initialize'. | 3 / 3 |
Distinctiveness Conflict Risk | While 'IIKit' is a specific tool name providing some distinctiveness, terms like 'project', 'status', 'commands', and 'features' are generic and could overlap with other project management or CLI-related skills. The IIKit branding helps but doesn't fully eliminate conflict risk. | 2 / 3 |
Total | 11 / 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 excellent skill file that demonstrates strong technical writing. It efficiently documents a complex multi-subcommand CLI tool with clear execution flows, explicit validation steps, and well-organized progressive disclosure to external templates and references. The content assumes Claude's competence while providing all necessary specifics for execution.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables and structured lists to convey information without explaining concepts Claude already knows. No unnecessary padding or verbose explanations of basic concepts. | 3 / 3 |
Actionability | Provides fully executable bash/PowerShell commands with exact paths, specific JSON field names to parse, and concrete decision tables. Commands are copy-paste ready with platform alternatives included. | 3 / 3 |
Workflow Clarity | Multi-step init process has clear numbered steps with explicit validation checkpoints (Step 5 validates PREMISE.md, Step 0 detects environment before proceeding). Auto-skip conditions and gates are clearly specified with feedback loops for validation failures. | 3 / 3 |
Progressive Disclosure | Well-organized with clear overview structure, subcommands cleanly separated, and appropriate references to external files (templates, references) that are one level deep and clearly signaled with relative paths. | 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.