agent-implementer-sparc-coder

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

1.09x

Quality

27%

Does it follow best practices?

Impact

69%

1.09x

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-implementer-sparc-coder/SKILL.md

Quality

Content

47%

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

The body presents a clear, well-sequenced TDD workflow with validation checkpoints, but is padded with generic programming concepts Claude already knows and relies on skeletal, non-executable code examples. It is a monolithic file with no progressive disclosure to supporting materials.

Suggestions

Cut generic principle refreshers (SOLID/DRY/YAGNI/KISS, basic retry/backoff, directory-layout rationale) that Claude already knows, keeping only SPARC-specific guidance.

Replace placeholder skeletons with concrete, executable code, and fix corrupted path separators ('$' -> '/') so examples are copy-paste ready.

Move large reference blocks (code patterns, performance/error-handling patterns) into separate files under references/ and link to them from a concise overview.

Dimension	Reasoning	Score
Conciseness	Large sections restate concepts Claude already knows (TDD Red/Green/Refactor, SOLID, DRY, YAGNI, KISS, dependency injection, retry-with-backoff, directory layout), padding the body with unnecessary context as in the level-1 anchor.	1 / 3
Actionability	Code blocks are present but are skeletons with placeholders ('// Implementation', 'authTestSuite', '// Arrange, Act, Assert') and corrupted paths using '$' instead of '/', giving some concrete guidance but incomplete executable detail (level-2 anchor).	2 / 3
Workflow Clarity	The TDD workflow is explicitly sequenced as Phase 1 Red, Phase 2 Green, Phase 3 Refactor, each closing with a test/lint verification checkpoint ('Verify all fail', 'Verify all pass'), matching the level-3 clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	No bundle files exist and the ~260-line body is a single monolithic document with many topics (patterns, performance, error handling, documentation) that could be split out; sections are headed but content that should be separate is inline (level-2 anchor).	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 reads as a templated placeholder: it names the skill and its invocation token but conveys no concrete capabilities or natural use-case triggers. It fails to tell a user or Claude when to invoke it or what it specifically does.

Suggestions

Replace the placeholder with concrete actions, e.g. 'Transforms specifications into tested code using TDD: writes failing tests, implements minimal code, and refactors.'

Add a 'Use when...' clause with natural trigger terms such as 'implementing a feature', 'writing tests first', or 'turning a spec into code'.

Drop the raw invocation token from the description; keep natural language that a user would actually say.

Dimension	Reasoning	Score
Specificity	The phrase 'Agent skill for implementer-sparc-coder' names a category but lists no concrete actions, matching the vague 'Helps with documents' anchor rather than the multi-action level-3 examples.	1 / 3
Completeness	It states only a circular 'what' (an agent skill for coding) and an invocation hint rather than a 'when to use it' trigger; both what and when are very weak, matching the level-1 anchor.	1 / 3
Trigger Term Quality	'implementer-sparc-coder' and the invocation token '$agent-implementer-sparc-coder' are internal identifiers, not natural terms a user would say, fitting the 'technical jargon or overly generic' level-1 anchor.	1 / 3
Distinctiveness Conflict Risk	The named identifier 'implementer-sparc-coder' gives it some niche specificity above a fully generic description, but the surrounding text offers no distinct capability triggers, so it could still overlap with other coding skills (level-2 anchor).	2 / 3
	Total	5 / 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
Path: .agents/skills/agent-implementer-sparc-coder/SKILL.md
Commit: 26c35b5

Reviewed: about 20 hours 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.