claude-code-guide

To provide a comprehensive reference for configuring and using Claude Code (the agentic coding tool) to its full potential. This skill synthesizes best practices, configuration templates, and advanced usage patterns.

Quality

22%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/antigravity-awesome-skills/skills/claude-code-guide/SKILL.md

Quality

Content

22%Scale 1-3

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

This skill attempts to be a comprehensive Claude Code guide but mostly restates generic advice that Claude already knows about itself and its own tooling. The CLAUDE.md template provides some concrete value, but the rest is padded with vague best practices and obvious debugging tips. The skill lacks executable workflows, validation steps, and any advanced or non-obvious configuration patterns that would justify its existence.

Suggestions

Remove sections that explain things Claude already knows (thinking keywords, generic debugging advice) and focus on non-obvious configuration patterns, edge cases, or project-specific templates.

Add concrete, executable workflows with validation checkpoints—e.g., a step-by-step process for setting up CLAUDE.md in a new project, verifying it works, and iterating on it.

Replace vague best practices with specific examples showing input/output pairs or before/after configurations that demonstrate the difference good CLAUDE.md configuration makes.

Remove the boilerplate 'When to Use' and 'Limitations' sections which add no actionable information for Claude.

Dimension	Reasoning	Score
Conciseness	The skill explains concepts Claude already knows well—Claude Code is Claude's own tool. Sections like 'Thinking Keywords' listing phrases like 'Think step-by-step' and debugging tips like 'be extremely specific' are generic advice Claude doesn't need. The 'When to Use' and 'Limitations' boilerplate sections add no value. Much of this is padding.	1 / 3
Actionability	The CLAUDE.md template is somewhat concrete and copy-paste ready, but most other sections are vague advice rather than executable guidance. 'Thinking Keywords' are just prompt suggestions, debugging tips are generic, and best practices are high-level recommendations without specific commands or examples.	2 / 3
Workflow Clarity	There is no clear multi-step workflow with sequencing or validation checkpoints. The debugging section lists loosely connected tips rather than a structured process. The CLAUDE.md template's workflow section is minimal and doesn't include validation or error recovery steps.	1 / 3
Progressive Disclosure	The content has some section structure (Configuration, Advanced Features, Best Practices) but everything is inline in a single file with no references to supporting documents. For a skill claiming to be a 'comprehensive reference,' the lack of any external references or layered content organization is a weakness, though the content volume is modest enough that a single file is not unreasonable.	2 / 3
	Total	6 / 12 Passed

Description

22%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads more like a document abstract than a skill description. It relies on vague, high-level language ('comprehensive reference', 'best practices', 'advanced usage patterns') without specifying concrete actions or when the skill should be triggered. The absence of a 'Use when...' clause and lack of specific, actionable capabilities make it poorly suited for skill selection among many options.

Suggestions

Replace abstract language with concrete actions, e.g., 'Configures Claude Code settings, sets up hooks, manages permissions, customizes slash commands, and optimizes .claude/ project files.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about Claude Code configuration, .claude/settings.json, hooks setup, MCP server configuration, or customizing Claude Code behavior.'

Remove filler phrases like 'comprehensive reference' and 'synthesizes best practices' — describe what the skill actually does rather than what it aspires to be.

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'comprehensive reference', 'best practices', 'configuration templates', and 'advanced usage patterns' without listing any concrete actions Claude would perform.	1 / 3
Completeness	The 'what' is vaguely described as providing a 'comprehensive reference' and the 'when' is entirely missing — there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps this at 2, but the 'what' is also weak enough to warrant a 1.	1 / 3
Trigger Term Quality	It includes some relevant keywords like 'Claude Code', 'agentic coding tool', and 'configuration', but lacks natural user trigger terms. Users are unlikely to say 'synthesizes best practices' — they'd say things like 'configure Claude Code', 'set up hooks', or 'customize settings'.	2 / 3
Distinctiveness Conflict Risk	Mentioning 'Claude Code' specifically provides some distinctiveness, but 'best practices' and 'advanced usage patterns' are generic enough to overlap with many other skills related to Claude Code usage or configuration.	2 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: popey/claude-code-skills
Path: plugins/antigravity-awesome-skills/skills/claude-code-guide/SKILL.md
Commit: a5a6601

Reviewed: 5 days 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.