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 findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-coder/SKILL.md

Quality

Content

27%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 is a generic software engineering best practices document that teaches Claude things it already knows extensively (SOLID, DRY, KISS, naming conventions, testing practices, file organization). The MCP tool integration section is the only genuinely novel content. The skill would benefit enormously from being reduced to ~30 lines focusing solely on project-specific conventions, MCP coordination patterns, and the agent's specific role in the swarm.

Suggestions

Remove all generic software engineering advice (SOLID, DRY, KISS, naming conventions, security basics, testing best practices) that Claude already knows—this could cut 70%+ of the content.

Focus the skill on what's unique: the MCP memory coordination protocol, the specific agent role within the swarm, and any project-specific conventions that differ from standard practices.

Split MCP tool integration examples and collaboration protocols into a separate reference file to improve progressive disclosure.

Add explicit validation checkpoints to the implementation process (e.g., 'Run tests before marking task complete', 'Verify MCP memory store succeeded before proceeding').

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~200+ lines. Explains basic concepts Claude already knows well: SOLID principles, DRY, KISS, YAGNI, single responsibility, dependency injection, clear naming conventions, file organization patterns, security basics, and testing best practices. Almost every section restates general software engineering knowledge that adds no new information for Claude.	1 / 3
Actionability	Contains some concrete TypeScript code examples that are syntactically valid, but most are illustrative patterns rather than executable, task-specific guidance. The MCP tool integration section provides specific tool calls which is useful, but the code examples are generic templates (e.g., a trivial discount calculation) rather than actionable instructions for a specific implementation task.	2 / 3
Workflow Clarity	The 'Implementation Process' section lists steps (Understand Requirements → Design First → TDD → Incremental Implementation) but lacks explicit validation checkpoints or feedback loops. There's no 'verify before proceeding' step, no error recovery guidance, and no clear criteria for when to move between phases. The pre/post hooks in frontmatter provide some validation but are minimal.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files and no bundle files provided. All content—from code quality standards to MCP integration to collaboration guidelines—is inlined in a single long document with no navigation aids or content splitting. Content that could be separated (e.g., MCP tool examples, code style guidelines) is all packed together.	1 / 3
	Total	6 / 12 Passed

Description

0%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 is an extremely weak description that provides essentially no useful information about the skill's capabilities or when it should be used. It reads more like a label or invocation instruction than a functional description. It fails on every dimension of the rubric.

Suggestions

Replace the entire description with concrete actions the skill performs, e.g., 'Writes, debugs, and refactors code across multiple languages including Python, JavaScript, and TypeScript.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to write code, fix bugs, refactor functions, or implement features.'

Remove the invocation instruction ('invoke with $agent-coder') from the description, as it does not help Claude select the skill and wastes space that should describe capabilities.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for coder' is extremely vague and does not describe what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause and no description of capabilities.	1 / 3
Trigger Term Quality	The only potentially relevant term is 'coder', which is overly generic. The invocation command '$agent-coder' is not a natural keyword a user would say. No natural trigger terms are present.	1 / 3
Distinctiveness Conflict Risk	'Coder' is extremely generic and could conflict with virtually any coding-related skill. There are no distinct triggers or niche identifiers to differentiate it.	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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Path: .agents/skills/agent-coder/SKILL.md
Commit: 913f9ea

Reviewed: 3 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.