CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-implementer-sparc-coder

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

44

1.09x
Quality

23%

Does it follow best practices?

Impact

69%

1.09x

Average score across 3 eval scenarios

SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

42%Weight 40%Scale 1-5

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

The content body reads as a generated agent spec: it presents a coherent TDD workflow and recognizable code patterns, but nearly all code is placeholder pseudocode with corrupted file paths (dollar signs where slashes belong), and much of the prose restates generic software-engineering knowledge Claude already has. A stray duplicated YAML frontmatter block at the top of the body further muddies the structure.

Suggestions

Fix the corrupted path separators throughout ('tests$unit$auth.test.js' → 'tests/unit/auth.test.js', 'src$auth$service.js' → 'src/auth/service.js', "'$auth$login'" → '/auth/login') so examples are executable.

Replace placeholder variables and '// Implementation' comments in the workflow and code patterns with complete, runnable snippets, and add an explicit fix-and-retest loop for when tests fail.

Cut the sections that restate knowledge Claude already has (DRY/YAGNI/KISS/SOLID lists, generic performance and documentation advice) and remove the duplicated YAML frontmatter block at the top of the body, keeping only SPARC-specific guidance.

DimensionReasoningScore

Conciseness

The body re-teaches concepts Claude already knows — TDD's red/green/refactor cycle, DRY/YAGNI/KISS/SOLID, 'choose efficient data structures', 'proper indexing', and README documentation advice — several padded sections across ~260 lines. It is not a 1 because the code patterns and error-handling sections do carry some skill-specific structure.

2 / 5

Actionability

The workflow phases are pseudocode with undefined variables (authTestSuite, authImplementation, optimizations), the code patterns are skeletons with '// Implementation' placeholders, and every path is corrupted ('tests$unit$auth.test.js', 'src$auth$service.js', "'$auth$login'") making nothing copy-paste executable. It is not a 2 because real, near-runnable snippets exist (the retryOperation function, the AuthService constructor) alongside the placeholders.

3 / 5

Workflow Clarity

The Red → Green → Refactor sequence is present with test-run checkpoints at each phase ('Bash("npm test") // Verify all fail'), but checkpoints are expressed in pseudocode and there is no fix-and-retry loop for failures. It is not a 4 because the steps cannot be executed as written due to corrupted paths and placeholder variables.

3 / 5

Progressive Disclosure

There are no bundle files at all, and the single-file body has clear section headers but opens with a stray second YAML frontmatter block and inlines material (performance optimization, documentation standards, generic best-practice lists) that belongs in separate references or should be cut. It is not a 2 because the section structure is real and navigable, and not a 4 because the duplicated metadata block and breadth of inline generic content leave organization gaps.

3 / 5

Total

11

/

20

Passed

Description

3%Weight 40%Scale 1-5

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 frontmatter description is pure boilerplate: it names the skill and how to invoke it, but says nothing about what the skill does or when to use it. It would almost never trigger correctly on user intent and is indistinguishable from any other agent-skill wrapper description.

Suggestions

Replace the description with concrete capabilities, e.g. 'Implements code from SPARC specifications using TDD: writes failing tests first, implements features in parallel, refactors for quality, maintains >80% test coverage.'

Add an explicit trigger clause such as 'Use when implementing a specification, writing or running tests for new features, or refactoring code delivered by the SPARC workflow.'

Include natural trigger terms users would actually say — 'implement', 'write tests', 'refactor', 'code the spec', 'TDD' — instead of only the '$agent-implementer-sparc-coder' invocation syntax.

DimensionReasoningScore

Specificity

The description states only 'Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder', which names no concrete action the skill performs; the sole content is an invocation instruction. It falls below anchor 2 ('Processes PDF files') because even a generic action verb describing what the skill does is absent.

1 / 5

Completeness

The 'what' is extremely vague (only the skill's own name) and the 'when' is entirely missing, matching the anchor 'Missing both what and when, or both are extremely vague'. The nested 'Transform specifications into working code with TDD practices' line in the body is not part of the frontmatter description being evaluated.

1 / 5

Trigger Term Quality

No natural keywords a user would say appear; the description contains only the technical identifier 'implementer-sparc-coder' and the '$agent-implementer-sparc-coder' invocation syntax, which is jargon rather than natural trigger language.

1 / 5

Distinctiveness Conflict Risk

The boilerplate 'Agent skill for X' pattern is very broad and would overlap with any similarly generated agent-skill description. It scores 2 rather than 1 because the embedded name 'implementer-sparc-coder' does hint at a distinct SPARC implementation niche.

2 / 5

Total

5

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
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.