CtrlK
BlogDocsLog inGet started
Tessl Logo

deep-module-refactor

Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, concise workflow with clear sequencing and good use of parallel sub-agents. It is held back by an absent REFERENCE.md that the body depends on, and by a lack of verification before the irreversible GitHub-issue creation step.

Suggestions

Provide the missing REFERENCE.md (dependency categories, dependency strategy, issue RFC template) or inline its essential content so the skill is self-contained.

Add a verification checkpoint before Step 7's `gh issue create` (e.g., confirm the issue body renders or that the chosen interface is captured), since issue creation is outward-facing and hard to reverse.

Tighten Step 5's sub-agent output spec toward a concrete, checkable deliverable (e.g., a defined interface signature plus a passing usage example) rather than open-ended prose, to lift actionability.

DimensionReasoningScore

Conciseness

Lean and efficient throughout — defines only the one non-obvious term ('deep module', sourced), gives concrete friction cues, and assumes Claude's competence without padding.

3 / 3

Actionability

Sub-agent design constraints and the friction checklist are concrete, but Step 7's 'gh issue create' leans on a template in [REFERENCE.md](REFERENCE.md) that is not present, and the interface-design output is open-ended rather than executable; some key detail is missing.

2 / 3

Workflow Clarity

The 7-step sequence is clearly numbered with user decision points, but validation is mostly implicit (user picks) and there is no verification checkpoint before the outward-facing, hard-to-reverse 'gh issue create' step, which the rubric caps at 2.

2 / 3

Progressive Disclosure

The body is well-organized into overview plus process steps, but it references [REFERENCE.md](REFERENCE.md) three times for dependency categories, a dependency strategy, and the issue template — and that file does not exist in the bundle, breaking the one-level-deep reference pattern.

2 / 3

Total

9

/

12

Passed

Description

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.

A strong, third-person description that states concrete capabilities and pairs them with an explicit, naturally-worded 'Use when' trigger clause. It carves a clear niche around deep-module refactoring with minimal risk of conflicting with other skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Explore a codebase', 'find opportunities for architectural improvement', 'consolidate tightly-coupled modules', 'make a codebase more testable' — matching the multi-action anchor.

3 / 3

Completeness

Answers both 'what' (explore, surface friction, propose deepening refactors) and 'when' via the explicit 'Use when user wants to improve architecture, find refactoring opportunities...' clause.

3 / 3

Trigger Term Quality

Covers natural phrases users would say — 'improve architecture', 'find refactoring opportunities', 'consolidate tightly-coupled modules' — plus variations; good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

The 'deepening shallow modules' framing and AI-navigability angle carve a clear niche unlikely to trigger for other skills; uses third-person voice throughout.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
zebbern/claude-code-guide
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.