agent-implementer-sparc-coder
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder
33
6%
Does it follow best practices?
Impact
69%
1.09xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-implementer-sparc-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 is an extremely weak description that provides virtually no useful information for skill selection. It only contains an invocation command and a generic label ('agent skill'), failing to describe any capabilities, use cases, or trigger conditions. This would be nearly impossible for Claude to correctly select from a pool of available skills.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Implements code following the SPARC methodology by breaking tasks into specification, pseudocode, architecture, refinement, and completion phases.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks for code implementation, building features, writing functions, or developing software components.'
Include domain-specific keywords users would naturally say, such as 'code implementation', 'write code', 'build feature', 'develop', 'programming', or whatever specific actions this skill performs.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It only states it's an 'agent skill' with an invocation command, providing no information about what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides an invocation command with no explanation of purpose or trigger conditions. | 1 / 3 |
Trigger Term Quality | There are no natural keywords a user would say. 'implementer-sparc-coder' is internal jargon/a tool name, not something a user would naturally request. No domain terms, file types, or action words are present. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish from any other agent skill. The name 'sparc-coder' hints at coding but provides no specifics to differentiate it from other coding-related skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
12%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 verbose collection of general software engineering best practices that Claude already knows, presented in a descriptive rather than actionable format. The pseudocode workflow notation isn't executable, the code examples are generic templates with placeholder comments, and the content includes extensive padding about well-known concepts (SOLID, DRY, YAGNI, basic error handling). The skill would benefit from being reduced to only project-specific conventions and concrete, executable instructions.
Suggestions
Remove all general software engineering knowledge Claude already knows (TDD explanation, SOLID/DRY/YAGNI/KISS definitions, basic error handling patterns, JSDoc syntax) and focus only on project-specific conventions or non-obvious instructions.
Replace pseudocode workflow notation (Write(), MultiEdit(), Bash()) with actual executable commands or tool invocations that Claude can directly use.
Cut the content by 70-80% to focus on what's unique to this project's implementation approach, with concrete file paths, actual project structure, and real examples from the codebase.
Add references to external files for detailed patterns (e.g., 'See PATTERNS.md for code templates') rather than inlining everything in one monolithic document.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and padded with concepts Claude already knows well: TDD red/green/refactor, SOLID principles, DRY, YAGNI, KISS, basic error handling patterns, dependency injection, JSDoc syntax, retry with exponential backoff, etc. Most of this is general software engineering knowledge that adds no new information. The hooks in the frontmatter also add unnecessary ceremony. | 1 / 3 |
Actionability | Despite containing code snippets, the guidance is largely abstract and descriptive rather than executable. The 'workflow' uses pseudocode notation (Write(), MultiEdit(), Bash()) that isn't real syntax. Code patterns are generic templates with placeholder comments like '// Implementation' and '// Arrange, Act, Assert' rather than concrete, copy-paste-ready examples. The skill describes what to do conceptually but doesn't give specific, actionable instructions. | 1 / 3 |
Workflow Clarity | The three-phase TDD workflow (Red → Green → Refactor) provides a clear sequence, and each phase includes a verification step (run tests). However, there are no explicit validation checkpoints for error recovery, no guidance on what to do when tests don't pass as expected, and the pseudocode notation makes the actual steps ambiguous. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files. Everything from code patterns to optimization strategies to documentation standards is inlined in a single file, much of which could be separated or omitted entirely. There's no navigation structure or signposting to help find relevant sections quickly. | 1 / 3 |
Total | 5 / 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
0d9f9b1
- 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.