agent-code-analyzer

Agent skill for code-analyzer - invoke with $agent-code-analyzer

2.05x

Quality

—

Does it follow best practices?

Impact

80%

2.05x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

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 body is a well-structured but padded capability catalog that leans on describing concepts Claude already knows rather than giving lean, executable instruction. It has a sequenced workflow and some concrete commands, but lacks validation checkpoints and external reference structure.

Suggestions

Trim the capability and metric bullet catalogs that restate knowledge Claude already has; keep only the concrete commands and the example report.

Add a validation/verification checkpoint in the Report Generation phase, e.g. confirm stored memory keys or sanity-check the summary before notifying.

Move the long metrics and memory-keys reference material into a separate reference file and link to it from the SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	The body mixes concrete commands with large capability and metric catalogs ('Analyze code structure and organization', 'Cyclomatic complexity', 'Big O complexity analysis') that describe concepts Claude already knows. It is mostly structured but padded with descriptive bullets that do not earn their tokens, so it falls short of the lean score 3.	2 / 3
Actionability	It provides some executable commands (e.g. 'npx claude-flow@alpha memory retrieve --key ...') and a concrete example report, but the bulk of the body ('Identify performance bottlenecks', 'Evaluate design patterns usage') describes rather than instructs. Guidance is concrete in places but incomplete overall.	2 / 3
Workflow Clarity	A sequenced 3-phase workflow (Initial Scan → Deep Analysis → Report Generation) is present, but there are no validation checkpoints or feedback loops — analysis results are stored without any verify step. This matches the score 2 anchor of steps listed but checkpoints missing.	2 / 3
Progressive Disclosure	The ~180-line body is a single monolithic file with no bundle references (no references/scripts/assets exist), and capability catalogs and metrics that could live in separate files are inline. It has section structure but content that should be split out is not, so it does not reach score 3.	2 / 3
	Total	8 / 12 Passed

Description

32%

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 generic packaging label that names a domain but states no concrete capabilities and provides no 'use when' trigger guidance. It is barely adequate as a skill description and would not help a user or Claude know when to invoke it.

Suggestions

Replace the label-style description with concrete actions, e.g. 'Performs comprehensive code reviews, identifies security vulnerabilities, and detects performance bottlenecks.'

Add an explicit 'Use when...' trigger clause, e.g. 'Use when the user asks for a code review, quality assessment, or security scan of a codebase.'

Drop the technical 'invoke with $agent-code-analyzer' invocation string from the description; it is not natural user language.

Dimension	Reasoning	Score
Specificity	The description names the domain ('code-analyzer') but lists no concrete actions — 'Agent skill for code-analyzer - invoke with $agent-code-analyzer' is essentially a label rather than a capability statement. It is above score 1 because a domain is named, but below score 3 because no specific actions (e.g. reviews code, finds vulnerabilities) are enumerated.	2 / 3
Completeness	The description answers neither 'what does this do' (no concrete actions) nor 'when should Claude use it' (no 'Use when...' trigger guidance), matching the score 1 anchor of both being very weak. It cannot reach 2 because the 'what' is essentially absent.	1 / 3
Trigger Term Quality	'code-analyzer' and 'code analysis' are relevant keywords, but 'invoke with $agent-code-analyzer' is a technical invocation string rather than natural user language. Common variations such as 'code review', 'code quality', or 'security scan' are missing, so it is not score 3.	2 / 3
Distinctiveness Conflict Risk	'code-analyzer' gives it a recognizable niche, but the generic framing ('Agent skill for code-analyzer') could overlap with code reviewer, security analyzer, or quality-gate skills, so it does not reach the clearly-distinct score 3.	2 / 3
	Total	7 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: 03d4f84

Reviewed: 2 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.