CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

format-code

Format source code files

53

Quality

67%

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 ./vendors/cc-skill-main/eval/runs/cc-skill-checker-eval/2026-06-01-opus/cases/case-002-minimal-bare-bones/_modified/target-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 admirably lean and appropriately scoped for a simple single-purpose skill, with clean structure and a sensible step order. Its weaknesses are the absence of executable formatter commands and any validation/verification checkpoint for what is a batch file-modifying operation, which hold actionability and workflow clarity at the midpoint.

Suggestions

Provide the concrete run command per detected config, e.g. '.prettierrc → npx prettier --write <files>', 'rustfmt.toml → cargo fmt', '.clang-format → clang-format -i <files>', so the guidance is executable rather than implied.

Add a validation checkpoint after formatting, such as re-running the formatter to confirm no further diffs or checking the exit status before reporting, to satisfy the batch-operation feedback-loop requirement.

Clarify how to detect the config when none of the three named files exists (e.g. fall back to asking the user or checking package.json formatter fields), closing a gap in step 1.

DimensionReasoningScore

Conciseness

The body is nine lean lines with zero padding: 'Run the project's code formatter on specified files' plus a three-item step list. It assumes Claude's competence, explains nothing it already knows, and every token earns its place — a clear match for anchor 5.

5 / 5

Actionability

There is some concrete guidance — specific config filenames ('.prettierrc', 'rustfmt.toml', or '.clang-format') — but 'Run the formatter on the specified files' gives no executable commands (e.g. 'npx prettier --write', 'cargo fmt', 'clang-format -i'), leaving key details missing. This matches anchor 3 ('Some concrete guidance but incomplete... missing key details') rather than 4, since nothing is copy-paste executable.

3 / 5

Workflow Clarity

The sequence (find config → run formatter → report changed files) is clearly ordered, but running a formatter across files is a batch file-modifying operation with no validation or verification step, which caps workflow clarity at 3 per the rubric guideline that overrides the simple-skill exception. It is not 2 because the steps are coherent and step 3 provides partial change-tracking.

3 / 5

Progressive Disclosure

This is a simple skill under 50 lines with no need for external references (no references/, scripts/, or assets/ exist), and the content is organized into a purpose line plus a '## Steps' section. Per the rubric's simple-skill guideline, well-organized sections alone warrant anchor 5.

5 / 5

Total

16

/

20

Passed

Description

45%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 concise and states a clear 'what', but it is a single vague action with no 'Use when...' trigger clause, no tool or language keywords, and no synonyms. It reads like the anchor-level 'Processes PDF files' pattern and would be hard to trigger reliably over similar formatting-related skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to format, prettify, or tidy up code, or mentions formatters like Prettier, rustfmt, or clang-format.'

Enumerate the concrete capabilities, e.g. 'Detect the project's formatter config (.prettierrc, rustfmt.toml, .clang-format), run it on the specified files, and report which files changed.'

Include natural synonyms and file-type keywords (e.g. 'format code', 'pretty-print', 'tidy', language names) to improve trigger-term coverage and distinctiveness.

DimensionReasoningScore

Specificity

The description 'Format source code files' names the domain (source code files) with a single generic action verb ('Format'), mirroring the anchor example 'Processes PDF files'. It does not list concrete actions, tools, languages, or outputs, so it cannot reach anchor 3.

2 / 5

Completeness

It has a clear 'what' (formats source code files) but no 'when' — there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

'Format' and 'source code' are natural phrases a user would say, so it has some relevant keywords, but it misses common variations and synonyms such as 'prettier', 'pretty-print', 'lint', file extensions, or tool names. This matches anchor 3 ('Some relevant keywords but missing common variations or synonyms') better than anchor 2, since 'format' is exactly the natural phrase users say.

3 / 5

Distinctiveness Conflict Risk

Code formatting is a recognizable niche, but the generic trigger 'format' could overlap with document, string, or date formatting skills, and no tool-specific triggers (prettier, rustfmt, clang-format) are given. This fits anchor 3 ('Somewhat specific but could still overlap with similar skills') rather than 4.

3 / 5

Total

11

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

LuminairPrime/git-worktrees-prime

Path

vendors/cc-skill-main/eval/runs/cc-skill-checker-eval/2026-06-01-opus/cases/case-002-minimal-bare-bones/_modified/target-skill/SKILL.md

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.