agent-coder
Agent skill for coder - invoke with $agent-coder
40
13%
Does it follow best practices?
Impact
79%
1.12xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-coder/SKILL.mdQuality
Discovery
0%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 no information about what the skill does, when it should be used, or what distinguishes it from other skills. It reads more like an invocation instruction than a functional description.
Suggestions
Replace the entire description with concrete actions the skill performs (e.g., 'Writes, debugs, and refactors code across multiple languages, runs tests, and implements features from specifications').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks to write code, fix bugs, implement features, refactor functions, or work with source files').
Remove the invocation syntax ('invoke with $agent-coder') from the description field, as it does not help Claude select the right skill and wastes space that should describe capabilities.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for coder' is entirely vague and does not describe what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'coder', which is overly generic. There are no natural keywords a user would say when needing a specific coding task performed. The invocation syntax '$agent-coder' is not a natural trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | 'Coder' is extremely generic and would conflict with virtually any coding-related skill. There is nothing to distinguish this from other programming or 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 a generic software engineering best practices document that teaches Claude things it already knows (SOLID principles, DRY, error handling patterns, security basics, testing guidelines). It's extremely verbose at ~150+ lines while providing little project-specific or novel guidance. The MCP tool integration section is the most valuable unique content but is buried in generic advice.
Suggestions
Remove all generic software engineering advice (SOLID, DRY, KISS, YAGNI, naming conventions, security basics, testing best practices) - Claude already knows these. Focus only on project-specific patterns and tool integration.
Extract MCP tool integration examples and code style guidelines into separate reference files (e.g., MCP_TOOLS.md, CODE_STYLE.md) and link from a concise overview.
Add explicit validation checkpoints to the implementation workflow, e.g., 'Run linter after implementation', 'Verify tests pass before marking complete', with concrete commands.
Reduce the skill to ~30-40 lines focusing on: (1) how this agent coordinates with other agents via MCP memory, (2) the specific implementation workflow with validation gates, and (3) links to detailed references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose - explains basic concepts Claude already knows (SOLID, DRY, KISS, YAGNI, single responsibility, dependency injection, error handling patterns, file organization conventions, security basics like 'never hardcode secrets'). Most of this is generic software engineering knowledge that wastes tokens. | 1 / 3 |
Actionability | Contains some concrete TypeScript code examples and MCP tool invocations, but much of the guidance is generic advice rather than project-specific executable instructions. The code examples are illustrative patterns rather than copy-paste-ready solutions for specific tasks. | 2 / 3 |
Workflow Clarity | The 'Implementation Process' section lists steps (understand requirements, design first, TDD, incremental implementation) but lacks validation checkpoints, error recovery loops, or concrete verification steps. For a coding agent that modifies files, there's no explicit validate-before-commit workflow. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline including lengthy code style guidelines, best practices, file organization, documentation patterns, and MCP tool examples that could be split into separate reference files. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
100%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
01070ed
- Reviewed
Table of Contents
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.