agent-code-analyzer

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

2.05x

Quality

13%

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

27%

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

The content is a verbose catalog of generic code-analysis concepts with little executable guidance beyond orchestration scaffolding, and it lacks validation checkpoints or any progressive file structure. It explains what Claude already knows rather than encoding a tight, actionable workflow.

Suggestions

Cut the generic capability lists and metric definitions Claude already knows; keep only the concrete workflow steps and any project-specific thresholds.

Replace abstract directives like 'Run linters and type checkers' with specific, copy-paste-ready commands and expected outputs.

Add explicit validation checkpoints (e.g., verify scan completed, re-run on failure) and fix the '$' templating artifacts in paths like 'analysis$code-quality' and 'UserController$search'.

Dimension	Reasoning	Score
Conciseness	The body is padded with capabilities Claude already knows (cyclomatic complexity, Big O analysis, coupling/cohesion, code duplication) and long generic bullet enumerations that add no novel information.	1 / 3
Actionability	The only executable commands are claude-flow orchestration hooks ('npx claude-flow@alpha hooks pre-search ...'), while the actual analysis steps ('Run linters', 'Execute security scanners') are described abstractly without specific commands.	2 / 3
Workflow Clarity	Three phases are sequenced, but Phase 2 is generic and there are no validation/verification checkpoints or feedback loops for the batch analysis work, which caps clarity at 2.	2 / 3
Progressive Disclosure	It is a monolithic single-file wall of text with no bundle files and no references to separate materials; metrics tables, the example report, and memory keys that could be split out are all inline.	1 / 3
	Total	6 / 12 Passed

Description

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 frontmatter description is a generic invocation wrapper rather than a functional description: it names a domain but conveys no concrete capabilities, no natural trigger terms, and no use-when guidance. It reads as scaffolding metadata, not a triggerable skill description.

Suggestions

Replace the description with concrete actions, e.g. 'Assesses code quality, detects security vulnerabilities, and flags technical debt. Use when reviewing code quality, hunting for vulnerabilities, or planning refactors.'

Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g., 'code review', 'code smells', 'dependency vulnerabilities').

Drop the invocation token '$agent-code-analyzer' and tool-name framing so the description states what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for code-analyzer - invoke with $agent-code-analyzer' names a domain but lists zero concrete actions (e.g., assess quality, scan vulnerabilities), only an invocation instruction.	1 / 3
Completeness	It gives only a faint 'what' (a wrapper skill) and no 'when to use it' clause; missing explicit trigger guidance leaves both what and when very weak.	1 / 3
Trigger Term Quality	'code-analyzer' is a tool name and '$agent-code-analyzer' an invocation token, not natural phrasing a user would say; no common terms like 'code review' or 'find bugs'.	1 / 3
Distinctiveness Conflict Risk	As a meta-invocation descriptor it does not carve out a distinct functional niche and could overlap with any code-related skill.	1 / 3
	Total	4 / 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
Path: .agents/skills/agent-code-analyzer/SKILL.md
Commit: 26c35b5

Reviewed: about 7 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.