CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

everything-claude-code-conventions

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

Quality

56%

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 ./.claude/skills/everything-claude-code/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 content delivers genuinely concrete conventions — real commit examples, naming tables, specific file paths, and well-sequenced workflow steps — but it is undermined by padding and duplication. Roughly a third of the document is verbatim step lists presented as 'Example commit sequence' blocks, and no workflow includes validation or verification steps. Splitting the workflow catalog into reference files and adding checkpoints would lift the weakest dimensions.

Suggestions

Remove or replace the seven 'Example commit sequence' blocks that merely restate the preceding numbered steps; either use real commit examples (as the Database Migration and Feature Development sections do) or delete the blocks.

Add explicit validation checkpoints to workflows, e.g., 'Run the test suite (`npm test`) before committing' after feature work, and 'Verify the counts match the actual filesystem' for Sync Catalog Counts.

Trim empty/duplicated headings and boilerplate (the repeated 'hybrid organization' statements, the '### Commit Style' heading with no content, the auto-generated footer), and consider splitting the per-workflow details into a references/ file so SKILL.md stays a lean overview.

DimensionReasoningScore

Conciseness

The body is noticeably padded: seven 'Example commit sequence' blocks (Add New Skill, Add New Agent, Add New Command, Sync Catalog Counts, Add Cross Harness Skill Copies, Add Or Update Hook, Address Review Feedback) restate the preceding numbered steps verbatim, and phrases like 'This project uses a hybrid organization' and 'This project uses **hybrid** module organization' are duplicated, with empty headings such as '### Commit Style: Conventional Commits' followed by no content. This matches anchor 2 (noticeably verbose; several padded sections); it is not 1 because it never explains basic concepts Claude already knows.

2 / 5

Actionability

The guidance is mostly concrete and executable: nine real commit message examples ('feat(rules): add C# language support'), a naming-conventions table, specific config file paths, and per-workflow steps with file globs ('skills/*/SKILL.md', 'rules/*/coding-style.md'). It is not 5 because no runnable commands are given (no test or lint invocation; 'No specific test framework detected'), and the import/export examples are labeled '```typescript' in a JavaScript project.

4 / 5

Workflow Clarity

The ten workflows each have a clear numbered sequence with frequency and files involved, but no validation checkpoints appear anywhere — no 'run tests', no 'verify counts match the filesystem' for Sync Catalog Counts, and no CI check before committing. This matches anchor 3 (steps listed but validation gaps; checkpoints missing or implicit) rather than 4, where most checkpoints would be present.

3 / 5

Progressive Disclosure

This is a single ~440-line file with no references/ or other bundle files; the ten-workflow catalog is fully inlined where an overview plus per-topic reference files would fit. Section headers are clear and navigable (better than anchor 2's minimal structure), but nothing is offloaded to separate files, so it sits at anchor 3 (some structure but could be better organized) rather than 4.

3 / 5

Total

12

/

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 identifies the target repository and a few concrete facts (JavaScript, conventional commits), but it reads more like a metadata summary than a trigger-oriented description. It completely lacks a 'when to use' clause and natural trigger phrases, capping completeness and trigger-term quality. Adding an explicit 'Use when...' sentence with concrete triggers would substantially improve it.

Suggestions

Add an explicit trigger clause, e.g., 'Use when making changes to the everything-claude-code repository, writing commit messages, or adding skills, agents, commands, or hooks.'

Enumerate the concrete content areas in the description (commit message format, naming conventions, testing patterns, common workflows like adding skills/agents/hooks) instead of the generic 'Development conventions and patterns'.

Include natural trigger terms users would actually say — 'commit message', 'code style', 'naming', 'pull request' — to raise trigger-term quality and distinctiveness.

DimensionReasoningScore

Specificity

The description names the domain ('Development conventions and patterns for everything-claude-code') but the concrete specifics are limited to 'JavaScript project with conventional commits' — actions/content areas are minimal and generic. It does not enumerate even 1-2 concrete capability areas (e.g., commit format, naming conventions, testing patterns), so it falls at anchor 2 rather than 3.

2 / 5

Completeness

The 'what' is stated (development conventions and patterns, JavaScript, conventional commits) but there is no 'Use when...' clause or any 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 implicit.

3 / 5

Trigger Term Quality

'conventional commits' is a natural phrase users would say, and 'JavaScript' plus the repo name add some relevance, but common variations like 'commit messages', 'code style', or 'naming conventions' are missing. This matches anchor 3 (some relevant keywords, missing common variations) rather than 4, since natural-term coverage is thin.

3 / 5

Distinctiveness Conflict Risk

The explicit repo name ('everything-claude-code') gives it a niche, but the phrases it exposes — 'conventional commits' and 'JavaScript' — overlap with generic commit-message and code-style skills that would trigger on the same terms. Anchor 3 (somewhat specific but could still overlap with similar skills) fits better than 4.

3 / 5

Total

11

/

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

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Repository

ysyecust/everything-claude-code

Path

.claude/skills/everything-claude-code/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.