everything-claude-code-conventions

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

50%

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

The skill is a well-structured auto-generated conventions document with useful commit examples, naming tables, and workflow globs, but it suffers from redundant example blocks, absent validation checkpoints, and a monolithic layout that doesn't leverage progressive disclosure. It is functional but leaves clear room for tightening and verification guidance.

Suggestions

Replace the 'Example commit sequence' blocks that merely restate the Steps (Add New Skill, Add New Agent, Add New Command, etc.) with actual representative commits, or remove them to cut redundancy.

Add explicit validation/verification steps to workflows involving batch or shared-state changes (Sync Catalog Counts, Add Or Update Hook, Database Migration), e.g. run tests or re-check counts before committing.

Move per-language rule and per-workflow detail into reference files under references/ and link to them one level deep, so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient enumeration, but many 'Example commit sequence' blocks merely repeat the preceding Steps verbatim (e.g. Add New Skill, Add New Agent) and the long config-file list and repeated commit-message examples add padding that could be trimmed.	2 / 3
Actionability	It gives concrete commit examples, a naming-convention table, import samples, and file globs per workflow, but several example sequences are non-illustrative step restatements rather than real executable commits, leaving the guidance partly abstract.	2 / 3
Workflow Clarity	Workflows list numbered steps and involved files, but no validation or verification checkpoints appear for any of the batch/destructive-style operations (catalog syncs, hook updates, migrations), capping workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are well organized, but with no bundle files the entire 440-line body is a single monolithic SKILL.md; per-language rules and per-workflow detail that could be split out remain inline.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 skill's domain and a couple of concrete conventions but stops short of explicit trigger guidance, so a user or router has limited signal for when to invoke it. It is competent but generic and would benefit from an explicit 'Use when...' clause.

Suggestions

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

Broaden trigger terms to include natural phrasings users would say, such as 'commit message format', 'project conventions', or 'code style for this repo'.

Name a few more concrete capabilities (test patterns, naming conventions, hook updates) to raise specificity beyond the generic 'conventions and patterns'.

Dimension	Reasoning	Score
Specificity	Phrases 'Development conventions and patterns' and 'conventional commits' name the domain and a few actions, but the action set is not comprehensive (no mention of tests, naming, architecture guidance).	2 / 3
Completeness	It states what the skill covers ('Development conventions and patterns for everything-claude-code') but has no explicit 'Use when...' trigger clause, so the 'when' is only implied and completeness is capped at 2.	2 / 3
Trigger Term Quality	It surfaces some relevant keywords ('conventional commits', 'JavaScript project'), but misses common natural variations a user might actually say ('commit message format', 'code style', 'project conventions').	2 / 3
Distinctiveness Conflict Risk	Binding to the specific repo name 'everything-claude-code' gives it a niche, but the descriptive language ('conventions and patterns') is generic and could overlap with other convention-style skills.	2 / 3
	Total	8 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Commit: 4130457

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.