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.

64

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/deep-module-refactor/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

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

A well-structured, appropriately concise process skill with concrete agent prompts and clear sequencing. Its main defect is bundling: three links to REFERENCE.md point at a file absent from the skill bundle, and the outward-facing gh-issue step lacks any verification checkpoint.

Suggestions

Ship REFERENCE.md in the bundle (or inline the four dependency categories and the issue template into SKILL.md) — the workflow cannot be executed as bundled because every reference to [REFERENCE.md](REFERENCE.md) is a broken link.

Add a lightweight validation checkpoint before or after 'gh issue create' (e.g., render the RFC body for correctness of cluster/dependency-category fields, or verify the returned URL), since creating a public GitHub issue is an outward-facing, hard-to-reverse action.

Trim emphasis-only phrases (e.g., 'The friction you encounter IS the signal') and fold step headings 3 and 6 into their preceding sections to tighten token usage.

DimensionReasoningScore

Conciseness

The body is lean and instructional with only minor trimmable padding — the one-line Ousterhout definition grounds the terminology rather than re-teaching it, and 'The friction you encounter IS the signal' is a slight flourish. Not 5 because a few phrases add emphasis rather than information.

4 / 5

Actionability

Gives concrete executable guidance: 'Use the Agent tool with subagent_type=Explore', verbatim sub-agent prompts ('Minimize the interface — aim for 1-3 entry points max'), a numbered output format per agent, and 'gh issue create'. Not 5 because key details — 'the four categories' and the issue template — are deferred to REFERENCE.md, which is not present in the bundle.

4 / 5

Workflow Clarity

A clearly sequenced 7-step process with user-decision checkpoints at steps 2/3 ('Which of these would you like to explore?') and 6. Not 5 because there is no validation around the final outward-facing step — 'Do NOT ask the user to review before creating — just create it' skips any verification of the issue content or of command success.

4 / 5

Progressive Disclosure

References to [REFERENCE.md](REFERENCE.md) are clearly signaled and one level deep, but the bundle contains no references/, scripts/, or assets/ directories — the referenced file does not exist, so navigation to the dependency categories and the RFC template is broken. Clearly signaled structure, but a dangling reference to a missing file cannot count as good organization.

3 / 5

Total

15

/

20

Passed

Description

83%Weight 40%Scale 1-5

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 description: third-person, concrete about what the skill does, with an explicit 'Use when...' clause containing natural trigger phrases. Minor room to broaden trigger synonyms and mention the GitHub-issue deliverable.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Explore a codebase to find opportunities for architectural improvement', 'making the codebase more testable by deepening shallow modules', 'consolidate tightly-coupled modules' — with only a minor coverage gap (the GitHub-issue RFC output step is not mentioned).

4 / 5

Completeness

Explicitly answers both: what ('Explore a codebase to find opportunities for architectural improvement... deepening shallow modules') and when ('Use when user wants to improve architecture, find refactoring opportunities...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

'improve architecture', 'refactoring opportunities', 'consolidate tightly-coupled modules', and 'AI-navigable' are phrases users would naturally say, but common synonyms like 'code smells', 'decoupling', or 'module design' are missing.

4 / 5

Distinctiveness Conflict Risk

The module-deepening/testability framing carves a clear niche distinct from generic refactor or code-review skills, with only minor overlap risk against those closely related skills.

4 / 5

Total

17

/

20

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.

Validation — 15 / 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.