CtrlK
BlogDocsLog inGet started
Tessl Logo

tessl-labs/intent-integrity-kit

Closing the intent-to-code chasm - specification-driven development with BDD verification chain

95

Does it follow best practices?

Validation for skill structure

Overview
Skills
Evals
Files

iikit-07-implement

skills/iikit-07-implement/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 clearly specifies concrete actions (writing files, running tests, verification), includes natural trigger terms users would actually say, explicitly separates the 'what' from the 'when', and carves out a distinct niche around task-based implementation workflows.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'coding each task', 'writes source files', 'runs tests', 'verifies assertion integrity', and 'validates output against constitutional principles'. These are clear, actionable capabilities.

3 / 3

Completeness

Clearly answers both what ('Execute the implementation plan by coding each task...writes source files, runs tests, verifies assertion integrity') AND when ('Use when ready to build the feature, start coding, develop from the task list, or resume a partially completed implementation').

3 / 3

Trigger Term Quality

Includes natural keywords users would say: 'build the feature', 'start coding', 'develop from the task list', 'resume a partially completed implementation', plus references to 'tasks.md' which is a specific artifact trigger.

3 / 3

Distinctiveness Conflict Risk

Has a clear niche focused on executing from tasks.md with specific workflow elements (assertion integrity, constitutional principles). The reference to a specific file (tasks.md) and the implementation-from-plan workflow makes it distinct from general coding 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 high-quality, complex implementation skill with excellent workflow clarity and actionability. The BDD verification chain, task completion gates, and parallel execution handling are well-documented with explicit validation steps. Minor verbosity in some sections (Windows command repetition, some explanatory text) prevents a perfect conciseness score, but overall the skill is well-crafted for its complex purpose.

Suggestions

Consolidate Windows command notes into a single reference section or footnote rather than repeating inline throughout the document

Consider moving the detailed error handling table to a reference file to reduce main document length

DimensionReasoningScore

Conciseness

The skill is comprehensive but includes some redundancy (e.g., Windows commands repeated multiple times, verbose error handling tables). Some sections could be tightened, though most content is necessary for the complex workflow.

2 / 3

Actionability

Provides fully executable bash/PowerShell commands throughout, specific file paths, concrete JSON parsing instructions, and copy-paste ready code blocks. Every step has explicit commands or clear decision criteria.

3 / 3

Workflow Clarity

Excellent multi-step sequencing with explicit validation gates (BDD verification chain, task completion gates, pre-implementation validation). Clear feedback loops for error recovery (§2.1-2.4, §6.5). Numbered phases with explicit checkpoints throughout.

3 / 3

Progressive Disclosure

Well-structured overview with clear one-level-deep references to supporting documents (constitution-loading.md, conversation-guide.md, parallel-execution.md, tessl-integration.md, etc.). Content appropriately split between main skill and reference files.

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.