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-03-checklist
skills/iikit-03-checklist/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 hits all the key criteria. It specifies concrete actions (generating scored checklists linked to spec sections), includes natural trigger terms that practitioners would use (PRD, requirements review, acceptance criteria), and provides explicit 'Use when' guidance with multiple relevant scenarios. The description is distinctive enough to avoid conflicts with general review or documentation skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'validate requirements completeness, clarity, and consistency', 'produces scored checklist items linked to specific spec sections (FR-XXX, SC-XXX)'. Clear output format is specified. | 3 / 3 |
Completeness | Clearly answers both what ('Generate quality checklists that validate requirements completeness, clarity, and consistency') AND when ('Use when reviewing a spec for gaps, doing a requirements review, verifying PRD quality, auditing user stories and acceptance criteria, or gating before implementation'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'spec', 'gaps', 'requirements review', 'PRD quality', 'user stories', 'acceptance criteria', 'gating before implementation'. These are terms practitioners naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on requirements/spec validation with distinct triggers like 'FR-XXX', 'SC-XXX', 'PRD quality', 'requirements review'. Unlikely to conflict with general document or code review skills due to specific domain focus. | 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-structured skill with excellent workflow clarity and progressive disclosure. The actionability is strong with executable commands and concrete examples. Minor verbosity from repeated OS-specific command variants and some path repetition prevents a perfect conciseness score, but overall this is a high-quality skill body.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some redundancy (Windows commands repeated inline, verbose path references). The core workflow is clear but could be tightened by consolidating OS-specific commands into a reference. | 2 / 3 |
Actionability | Provides fully executable bash/PowerShell commands, specific file paths, concrete examples of correct vs wrong checklist items, and copy-paste ready code blocks including the jq command for context updates. | 3 / 3 |
Workflow Clarity | Clear 6-step sequence with explicit validation checkpoints (Prerequisites Check, Gap Resolution, Remaining Item Validation). Includes feedback loops for gap resolution and explicit completion criteria (100% before success). | 3 / 3 |
Progressive Disclosure | Well-structured overview with clear one-level-deep references to supporting files (constitution-loading.md, conversation-guide.md, checklist-examples.md, checklist-template.md, model-recommendations.md). Content appropriately split between main skill and reference materials. | 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.