CtrlK
BlogDocsLog inGet started
Tessl Logo

clean-code

This skill embodies the principles of "Clean Code" by Robert C. Martin (Uncle Bob). Use it to transform "code that works" into "code that is clean."

50

Quality

55%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/clean-code/SKILL.md

The canonical home for this skill is clean-code in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

61%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.

The body is a tidy, well-structured Clean Code reference with concrete examples and a useful checklist, but as guidance it is heavier on abstract heuristics than on executable, sequenced instruction.

Suggestions

Add a short worked example per major section (e.g. a before/after refactor under Functions) to lift actionability toward executable guidance.

Convert the closing checklist into an ordered review workflow with explicit validation checkpoints (apply -> check -> iterate) to improve workflow clarity.

Trim the repeated description line and the Booch quote to tighten conciseness, since both restate the skill's purpose.

DimensionReasoningScore

Conciseness

The body is a lean bulleted reference of Clean Code heuristics with terse one-line items, fitting the 'efficient; minor instances of over-explanation that could be trimmed' anchor; the only mild padding is the repeated description line and the Booch quote, and it stops short of the verbose 3-anchor.

4 / 5

Actionability

It gives some concrete illustrations (e.g. 'elapsedTimeInDays instead of d', the Python benefits example) and a closing checklist, but most sections are abstract heuristics ('Do One Thing', 'No Side Effects') without executable steps or commands, matching the 'some concrete guidance but incomplete' anchor rather than the mostly-executable 4-anchor.

3 / 5

Workflow Clarity

There is no multi-step procedure — the skill is a principles reference rather than a sequenced workflow; the closing checklist supplies implicit checkpoints but no ordered sequence with validation, matching the 'steps listed but validation gaps; checkpoints implicit' anchor.

3 / 5

Progressive Disclosure

The body is well-organized into clearly headed sections (Names, Functions, Comments, ...) with no bundle files and no nested references; at ~88 self-contained lines it sits just above the <50-line simple-skill exception, so 'good structure; content appropriately placed; minor gaps' fits better than a clean 5.

4 / 5

Total

14

/

20

Passed

Description

48%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.

The description is clearly voiced in third person and stakes out a recognizable niche, but it is more of a purpose statement than a trigger-rich description: it lacks concrete actions and an explicit 'Use when...' clause.

Suggestions

Add 2-3 concrete actions, e.g. 'Review pull requests, refactor legacy code, and apply naming/function conventions.'

Replace 'Use it to transform...' with an explicit trigger clause: 'Use when reviewing PRs, refactoring legacy code, or improving code quality and team standards.'

Include natural trigger terms users would say — refactor, code review, code smells, code quality — alongside 'Clean Code'.

DimensionReasoningScore

Specificity

The description names the domain (Clean Code principles) but only offers a single generic action — "transform 'code that works' into 'code that is clean'" — with no concrete operations like refactor, review, or rename, fitting the 'names the domain but actions are minimal or generic' anchor rather than the 3-anchor which requires 1-2 concrete actions.

2 / 5

Completeness

The 'what' is clear (embodies Clean Code principles to clean up code), but the 'when' is only weakly implied via 'Use it to transform...' which restates purpose rather than giving explicit trigger conditions; per the guideline a missing explicit 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

It surfaces a recognizable term ("Clean Code") and the phrase "code that works" / "code that is clean", but omits common natural variations users would say such as refactor, code review, code smells, or code quality, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The Clean Code / Uncle Bob framing carves a fairly distinct niche with only minor overlap risk against generic refactoring or code-review skills, matching the 'mostly distinct; minor overlap risk' anchor and falling short of 5 only because 'code that is clean' is still somewhat broad.

4 / 5

Total

12

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.