agent-coder

Agent skill for coder - invoke with $agent-coder

1.12x

Quality

13%

Does it follow best practices?

Impact

79%

1.12x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-coder/SKILL.md

Quality

Discovery

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 is critically deficient across all dimensions. It provides only an invocation command without explaining what the skill does, when to use it, or any distinguishing characteristics. This would be essentially unusable for Claude to select appropriately from a pool of skills.

Suggestions

Add specific concrete actions the skill performs (e.g., 'Writes, refactors, and debugs code across multiple languages')

Include a 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks to write code, fix bugs, refactor functions, or implement features')

Specify the skill's niche to distinguish it from other coding-related skills (e.g., specific languages, frameworks, or coding task types it handles)

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for coder' is completely abstract and does not describe what the skill actually does.	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides invocation syntax without any functional description or usage guidance.	1 / 3
Trigger Term Quality	The only potential trigger term is 'coder' which is overly generic. The '$agent-coder' is a command syntax, not a natural keyword users would say when needing coding help.	1 / 3
Distinctiveness Conflict Risk	'Coder' is extremely generic and would conflict with any coding-related skill. There are no distinguishing features or specific triggers to differentiate it from other development skills.	1 / 3
	Total	4 / 12 Passed

Implementation

27%

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

This skill is significantly over-engineered, explaining fundamental software engineering concepts (SOLID, DRY, KISS, basic TypeScript patterns) that Claude already knows well. The document would be more effective as a concise 30-line skill focusing only on project-specific conventions, MCP coordination patterns, and the specific hooks/workflow unique to this agent system. The MCP integration examples are the most valuable unique content but are buried in generic programming advice.

Suggestions

Remove all generic programming advice (SOLID, DRY, KISS, basic TypeScript patterns, file organization) - Claude already knows these concepts

Extract MCP tool integration patterns to a separate COORDINATION.md reference file and link to it

Condense to core unique content: the pre/post hooks behavior, memory coordination keys, and any project-specific conventions

Add explicit validation checkpoints in the workflow (e.g., 'After implementation, verify tests pass before reporting status to memory')

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive explanations of concepts Claude already knows (SOLID principles, DRY, KISS, basic TypeScript patterns, file organization conventions). The document is ~200 lines when the core actionable content could be condensed to ~30 lines.	1 / 3
Actionability	Contains concrete code examples that are mostly executable, but much of the content is generic best practices rather than specific, copy-paste-ready guidance. The MCP tool integration examples are concrete but the overall skill reads more like a style guide than actionable instructions.	2 / 3
Workflow Clarity	Lists a 4-step implementation process (Understand, Design, TDD, Incremental) but lacks explicit validation checkpoints or feedback loops. No clear verification steps between stages or error recovery guidance for when implementations fail.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. All content is inline including detailed code style guidelines, file organization patterns, and MCP examples that could be split into separate reference documents.	1 / 3
	Total	6 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: b2618f9

Reviewed: 4 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.