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-05-tasks
skills/iikit-05-tasks/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 follows best practices. It uses third person voice, provides specific capabilities, includes a clear 'Use when...' clause with natural trigger terms, and carves out a distinct niche in project planning and task breakdown. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generate dependency-ordered task breakdown', 'breaking features into implementable tasks', 'planning sprints', 'creating work items with parallel markers'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Generate dependency-ordered task breakdown from plan and specification') and when ('Use when breaking features into implementable tasks, planning sprints, or creating work items with parallel markers') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'task breakdown', 'features', 'tasks', 'planning sprints', 'work items', 'parallel markers'. These cover common project management and development planning terminology. | 3 / 3 |
Distinctiveness Conflict Risk | Has a clear niche focused on dependency-ordered task generation from plans/specs. The specific mention of 'dependency-ordered', 'parallel markers', and 'sprints' distinguishes it from generic planning 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 clear workflow sequencing and appropriate progressive disclosure. The main weakness is moderate verbosity from repeated Windows command alternatives and some sections that could be more concise. The validation checkpoints and error handling are exemplary for a complex multi-step workflow.
Suggestions
Consider consolidating Windows/bash command pairs into a single reference or using a shorthand notation to reduce repetition
The 'Task Format (REQUIRED)' section examples are thorough but could be slightly condensed by combining the correct examples into a single block
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (e.g., Windows commands repeated for every script, verbose section headers). Some sections could be tightened without losing clarity. | 2 / 3 |
Actionability | Provides fully executable bash/powershell commands, exact file paths, concrete task format examples with correct/wrong comparisons, and specific git commit commands. Copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Clear sequential phases with explicit validation checkpoints (Prerequisites Check, Plan Readiness Validation, Dependency Graph Validation). Includes error handling (ERROR if cycles found), confirmation gates, and semantic diff handling for re-runs. | 3 / 3 |
Progressive Disclosure | Well-structured overview with clear one-level-deep references to external files (constitution-loading.md, conversation-guide.md, formatting-guide.md, tasks-template.md, model-recommendations.md). Content appropriately split between main skill and reference documents. | 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.