agent-implementer-sparc-coder

Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder

1.09x

Quality

—

Does it follow best practices?

Impact

69%

1.09x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

50%

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

The content provides a reasonable structure and useful implementation patterns, but is undermined by '$'-corrupted, non-executable code examples, padding with well-known concepts, and a monolithic layout with no progressive disclosure. Workflow sequencing exists but lacks validation feedback loops for batch operations.

Suggestions

Fix the malformed code examples by replacing '$' with real path separators ('/') and removing '/ // Implementation' placeholders so examples are copy-paste ready and executable.

Trim sections that re-explain concepts Claude already knows (TDD principles, DRY/YAGNI/KISS/SOLID) and keep only skill-specific guidance.

Add explicit validation/feedback loops to the TDD workflow (e.g. 'if tests fail, read errors, fix implementation, re-run') and split large reference material (code patterns, error handling) into referenced bundle files.

Dimension	Reasoning	Score
Conciseness	The body includes useful pattern content but pads it with concepts Claude already knows (TDD Red/Green/Refactor, DRY/YAGNI/KISS/SOLID), matching the score-2 anchor of mostly efficient with some unnecessary explanation rather than the lean score-3 anchor.	2 / 3
Actionability	Concrete code patterns are present but non-executable: '$' replaces path separators (e.g. 'src$auth$service.js', '$auth$login') and 'function$class', and blocks contain '// Implementation' / '// Setup with mocks' placeholders, matching the score-2 pseudocode/missing-details anchor.	2 / 3
Workflow Clarity	The Red-Green-Refactor phases give a sequence with 'Bash("npm test")' checks, but the parallel/batch write operations lack explicit validation feedback loops and error-recovery steps, so per the batch-operations guideline workflow_clarity is capped at 2.	2 / 3
Progressive Disclosure	The single ~260-line file is organized into sections but is monolithic with no bundle files, external references, or navigation signals, matching the score-2 anchor of content that should be split but is inline.	2 / 3
	Total	8 / 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 description is boilerplate that labels the skill rather than describing its capabilities or when to invoke it, offering no concrete actions or natural trigger terms. It fails to distinguish the skill from other generic agent skills.

Suggestions

Replace the boilerplate with concrete capabilities, e.g. 'Transforms specifications into tested code using TDD (Red-Green-Refactor), generating unit/integration tests and implementation files in parallel.'

Add an explicit 'Use when...' trigger clause with natural terms users would say, e.g. 'Use when implementing a spec or design into code, writing tests, or refactoring for TDD coverage.'

Drop the technical invocation token from the description and use third-person action voice ('Implements', 'Generates') to improve distinctiveness and specificity.

Dimension	Reasoning	Score
Specificity	The description only states 'Agent skill for implementer-sparc-coder', naming a domain but listing no concrete actions, matching the score-1 anchor 'Vague or no actions; abstract language' rather than score 2 which requires naming some actions.	1 / 3
Completeness	It gives neither a real 'what does this do' statement (only a label) nor any 'when to use it' guidance, so both what and when are weak/missing as in the score-1 anchor.	1 / 3
Trigger Term Quality	The only trigger is the technical invocation token '$agent-implementer-sparc-coder'; there are no natural keywords a user would say, matching the score-1 anchor for technical jargon with no natural terms.	1 / 3
Distinctiveness Conflict Risk	'Agent skill for implementer-sparc-coder' is generic boilerplate that would conflict with many other agent skills, matching the score-1 anchor 'Very generic; would conflict with many skills'.	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
Commit: 03d4f84

Reviewed: 2 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.