CtrlK
BlogDocsLog inGet started
Tessl Logo

iikit-07-implement

Execute the implementation plan by coding each task from tasks.md — writes source files, runs tests, verifies assertion integrity, and validates output against constitutional principles. Use when ready to build the feature, start coding, develop from the task list, or resume a partially completed implementation.

82

1.74x
Quality

88%

Does it follow best practices?

Impact

82%

1.74x

Average score across 14 eval scenarios

SecuritybySnyk

—

The risk profile of this skill

The canonical home for this skill is tessl-labs/intent-integrity-kit

SKILL.md
Quality
Evals
Security

Quality

Content

85%Scale 1-3

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 implementation orchestration skill with strong workflow clarity and excellent progressive disclosure. Its main weakness is moderate verbosity — the BDD verification chain and test enforcement rules are repeated across multiple sections, and the section numbering has gaps (§3 jumps to §6) suggesting incomplete editing. Despite its length, nearly all content serves a purpose for this complex multi-phase workflow.

Suggestions

Consolidate the overlapping test execution enforcement content from §2.1, §2.3, §2.4, and §6.4 into a single authoritative section to reduce redundancy.

Fix the section numbering gap (§3 jumps to §6, missing §4 and §5) which suggests content was reorganized without renumbering.

DimensionReasoningScore

Conciseness

The skill is lengthy but most content is necessary for a complex multi-step orchestration workflow. However, there's some redundancy (e.g., test execution enforcement is restated across §2.1, §2.3, §2.4, and §6.4) and section numbering jumps from §3 to §6, suggesting editing artifacts. Some instructions like the Windows note and dashboard suggestion could be tighter.

2 / 3

Actionability

The skill provides fully executable bash commands with specific flags, concrete commit message formats with templates, exact file paths, specific JSON field names to parse, and clear gate conditions (PASS/BLOCKED/WARN). Every step has concrete, copy-paste-ready commands and explicit expected outcomes.

3 / 3

Workflow Clarity

The workflow is clearly sequenced with numbered phases, explicit validation gates at multiple points (prerequisites check, pre-implementation validation, TDD verification chain with RED/GREEN phases, task completion gates requiring three checks, output validation before file writes). Feedback loops are well-defined: fix and re-validate patterns, failure handling with halt-on-error, and the BDD chain enforces verify→fix→retry cycles.

3 / 3

Progressive Disclosure

The skill effectively references external documents for detailed topics: constitution-loading.md, conversation-guide.md, parallel-execution.md, formatting-guide.md, tessl-integration.md, ignore-patterns.md, and model-recommendations.md. All references are one level deep and clearly signaled with descriptive link text. The main document stays at orchestration level while delegating specifics.

3 / 3

Total

11

/

12

Passed

Description

92%Scale 1-3

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 strong skill description that clearly articulates specific actions and provides explicit trigger guidance via a 'Use when...' clause. The reference to tasks.md and constitutional principles adds domain specificity, though some trigger terms like 'start coding' could overlap with more general coding skills. Overall, it effectively communicates both purpose and activation conditions.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'writes source files, runs tests, verifies assertion integrity, and validates output against constitutional principles.' Also references a specific artifact (tasks.md).

3 / 3

Completeness

Clearly answers both 'what' (execute implementation plan by coding tasks, writing source files, running tests, verifying assertions, validating against constitutional principles) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios).

3 / 3

Trigger Term Quality

Includes natural trigger terms users would say: 'build the feature', 'start coding', 'develop from the task list', 'resume a partially completed implementation'. These cover common variations of how a user would request implementation work.

3 / 3

Distinctiveness Conflict Risk

While it references specific concepts like 'tasks.md', 'assertion integrity', and 'constitutional principles' that create some distinctiveness, terms like 'start coding' and 'build the feature' are broad enough to potentially overlap with general coding or development skills.

2 / 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.

Repository
JaviMontano/mao-iic
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.