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-02-plan
skills/iikit-02-plan/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, includes natural trigger terms users would actually say, explicitly addresses both what the skill does and when to use it, and carves out a distinct niche in technical design document generation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'selects frameworks', 'defines data models', 'produces API contracts', and 'creates a dependency-ordered implementation strategy'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (generate technical design docs with frameworks, data models, API contracts, implementation strategy) AND when (explicit 'Use when...' clause with multiple trigger scenarios including planning features, writing design docs, choosing libraries, defining schemas). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'technical design document', 'feature spec', 'planning how to build', 'choosing libraries', 'database schemas', 'Tessl tiles'. Good coverage of both common and domain-specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on technical design document generation from feature specs. The specific combination of framework selection, API contracts, and 'Tessl tiles' reference creates a distinct identity unlikely to conflict with general coding 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-structured, highly actionable skill with excellent workflow clarity and appropriate progressive disclosure. The main weakness is moderate verbosity—Windows command alternatives are repeated throughout rather than consolidated, and some explanatory sections could be more compact. Overall, it's a strong skill that provides clear, executable guidance for a complex multi-step planning process.
Suggestions
Consolidate Windows command alternatives into a single reference section or note at the top rather than repeating for each command
Compress the classification rules section—Claude understands these categories without detailed examples for each
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundant patterns (Windows alternatives repeated throughout, verbose jq examples). The structure is good but could be tightened—some sections like the classification rules could be more compact. | 2 / 3 |
Actionability | Provides fully executable bash/PowerShell commands, concrete jq examples, specific file paths, and exact commit message formats. Every step has copy-paste ready commands with clear parameters. | 3 / 3 |
Workflow Clarity | Excellent multi-step sequencing with numbered phases, explicit validation checkpoints (Spec Quality Gate, Constitution Check Post-Design, Phase Separation Validation), clear prerequisites, and error handling (ERROR/WARNING conditions, re-run loops). | 3 / 3 |
Progressive Disclosure | Well-structured with clear section hierarchy and appropriate references to external files (constitution-loading.md, conversation-guide.md, tessl-tile-discovery.md, formatting-guide.md). References are one level deep and clearly signaled with markdown links. | 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.