agent-code-analyzer

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

2.05x

Quality

31%

Does it follow best practices?

Impact

80%

2.05x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-code-analyzer/SKILL.md

Quality

Content

42%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 is a well-sectioned but verbose description of an analysis agent's responsibilities rather than executable analysis instructions: concrete commands are limited to claude-flow orchestration, and the actual analysis steps are generic bullet lists with no validation checkpoints. It also carries a malformed duplicate frontmatter block.

Suggestions

Replace generic capability/metric bullet lists with executable guidance — concrete commands or tools for each analysis type — to raise actionability.

Add validation checkpoints to the workflow (e.g. verify scan results before reporting, confirm findings against the codebase) and a fix-and-retry loop.

Remove the duplicate second YAML frontmatter block and trim the metrics/capabilities lists that restate knowledge Claude already has to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose — long bullet lists of generic capabilities and metrics (cyclomatic complexity, Big O, vulnerability types) Claude already knows, plus a spurious duplicate YAML frontmatter block — which matches 'several unnecessary explanations or padded sections'; it is more than 'minor' so it stays below 3.	2 / 5
Actionability	It provides concrete bash commands (npx claude-flow hooks/memory), but these orchestrate the agent rather than perform the actual code analysis, which is left as vague bullet directives ('Analyze code structure', 'Identify performance bottlenecks'); this 'some concrete guidance but incomplete' fits score 3 and is below the fully-executable 4.	3 / 5
Workflow Clarity	The three phases (Initial Scan, Deep Analysis, Report Generation) give a clear sequence with commands, but there are no validation or verification checkpoints and no feedback loops, matching 'steps listed but validation gaps'.	3 / 5
Progressive Disclosure	No references/scripts/assets bundle exists and the skill is a single ~210-line file with section headers; content that could be split (metrics tables, memory keys, example report) is inlined, matching 'some structure but could be better organized' rather than the well-split 4 or 5.	3 / 5
	Total	11 / 20 Passed

Description

21%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 metadata about the skill rather than a statement of what it does and when to use it: it names the domain and an invocation token but provides no concrete actions or natural trigger phrases. It would rarely be selected from a user's natural request.

Suggestions

Rewrite the description to list concrete actions, e.g. 'Performs comprehensive code reviews: detects quality issues, security vulnerabilities, performance bottlenecks, and technical debt.'

Add an explicit trigger clause such as 'Use when the user asks for a code review, code quality analysis, or security/performance assessment of a codebase.'

Drop the 'invoke with $agent-code-analyzer' invocation token and use third-person action verbs to satisfy the trigger-term and specificity anchors.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for code-analyzer - invoke with $agent-code-analyzer' names the domain (code-analyzer) but lists no concrete actions, only how to invoke it; it is not entirely abstract so it sits above 1 but well below the 'several specific actions' anchors.	2 / 5
Completeness	It offers a vague 'what' ('Agent skill for code-analyzer') and no 'when'/'Use when...' trigger guidance — the missing trigger clause caps completeness at 3, and the vague-what-plus-no-when fits the score-2 anchor.	2 / 5
Trigger Term Quality	The only keyword is the technical invocation token '$agent-code-analyzer'; there are no natural phrases a user would say ('code review', 'analyze code quality'), matching the 'only technical jargon' anchor.	1 / 5
Distinctiveness Conflict Risk	'code-analyzer' is somewhat specific to code analysis but extremely broad and likely to overlap with many existing code-quality or review skills, matching the 'somewhat specific but could still overlap' anchor.	3 / 5
	Total	8 / 20 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/ruflo
Path: .agents/skills/agent-code-analyzer/SKILL.md
Commit: fa13ee4

Reviewed: about 5 hours 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.