CtrlK
BlogDocsLog inGet started
Tessl Logo

everything-claude-code

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

42

Quality

42%

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

Quality

Content

56%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 delivers genuinely useful, concrete convention data (commits, naming, structure, workflows) organized with clear headers, but is bloated by systematic padding — step-echo 'commit sequences', repeated facts, and redundant examples. As a single monolithic file with no progressive disclosure, ~40% of its length could be trimmed or split without losing actionable content.

Suggestions

Delete or replace the 'Example commit sequence' blocks that merely restate the workflow steps — either show actual representative commit messages or drop the blocks entirely, saving ~60 lines of pure duplication.

Trim the nine commit-message examples to two or three distinct patterns (conventional feat/fix, a merge, a revert) since the format rule is already stated in prose.

Move the ten workflow recipes into a references/ file (e.g., references/workflows.md) linked from a short overview section, so SKILL.md loads as a lean summary and detail is disclosed on demand.

DimensionReasoningScore

Conciseness

The body is noticeably padded: six of the ten workflows repeat their numbered steps verbatim as an 'Example commit sequence' (e.g., 'Create a new directory under rules/{language}/... ' appears identically in both blocks), the hybrid organization fact is stated three times, and nine commit-message examples are shown where two or three would establish the pattern. This matches 'Noticeably verbose; several unnecessary explanations or padded sections' and is above score 1 because most lines are still terse factual statements rather than explanations of concepts Claude already knows.

2 / 5

Actionability

Concrete, usable guidance dominates: a naming-convention table, an executable import example, a complete try/catch pattern, concrete commit prefixes and rules, and per-workflow file globs like 'skills/*/SKILL.md' and 'hooks/hooks.json'. It falls short of score 5 because of vague leftovers like 'Follow existing patterns when adding new code' and a test section that says 'No specific test framework detected — use the repository's existing test patterns' without pointing to where those patterns live.

4 / 5

Workflow Clarity

The ten workflows each present a clearly sequenced numbered step list with frequency and involved files, which matches 'Clear sequence with most checkpoints present'. It is not score 5 because there are no verification steps and some 'Example commit sequence' blocks are misleading — the Database Migration section's example shows unrelated commits (skills/rules additions) and most others just echo the step text instead of showing real commit sequences, a minor but real clarity gap.

4 / 5

Progressive Disclosure

The file is well-sectioned with headers, but it is a single ~440-line monolith with no bundle files at all; the ten workflow recipes and the commit-example gallery are inline content that would serve better split into reference files loaded on demand. This matches 'Some structure but could be better organized; content that should be separate is inline' — above score 2 (no structure/buried references) but below score 4, which requires most bulk content to be appropriately placed outside the main file.

3 / 5

Total

13

/

20

Passed

Description

28%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 a terse auto-generated label: it identifies the target repo and tech stack but gives no concrete actions and no usage triggers. It fails the core 'what AND when' test, with the 'when' clause entirely missing.

Suggestions

Rewrite as concrete third-person actions, e.g., 'Applies the development conventions of everything-claude-code: conventional commit format, camelCase naming, relative imports, and test placement.'

Add an explicit trigger clause: 'Use when making changes in this repository, writing commit messages, or adding skills/agents/hooks to it.'

Include natural trigger keywords users would actually say (commit message, pull request, code style, naming) rather than only generic labels like 'conventions and patterns'.

DimensionReasoningScore

Specificity

The description names the domain ("Development conventions and patterns for everything-claude-code", "JavaScript project with conventional commits") but states what the skill is rather than any concrete action it performs, matching the anchor 'Names the domain but actions are minimal or generic'. It is above score 1 because the domain and tech context are identified, but below score 3 because no verb-based capabilities (e.g., 'follows commit conventions', 'generates commit messages') are listed.

2 / 5

Completeness

A vague 'what' is present ('Development conventions and patterns') but the 'when' is entirely absent — there is no 'Use when...' clause, which also caps this dimension at 3 per the judging guidelines. It fits anchor 2 ('Has a vague what and no when') and is not score 3 because the 'what' is a category label rather than a clear capability statement.

2 / 5

Trigger Term Quality

Only 'JavaScript', 'conventional commits', and 'development conventions' appear — a couple of generic keywords with no natural user phrasing such as 'commit message', 'code style', or 'working in this repo'. This matches 'One or two generic keywords; missing the natural phrases users say' and falls short of score 3, where relevant keywords would at least be present with only synonym gaps.

2 / 5

Distinctiveness Conflict Risk

Tying the description to the specific repository 'everything-claude-code' gives it a niche, but 'Development conventions and patterns' is broad wording that overlaps with any general conventions/code-style skill. This matches 'Somewhat specific but could still overlap with similar skills' — above score 2 (very broad, high overlap with many skills) but below score 4, which would require mostly distinct trigger signals.

3 / 5

Total

9

/

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
affaan-m/ECC
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.