CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-refinement

Agent skill for refinement - invoke with $agent-refinement

43

1.23x
Quality

13%

Does it follow best practices?

Impact

96%

1.23x

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-refinement/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

27%Scale 1-3

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

This skill is an overly verbose tutorial on general software engineering practices (TDD, error handling, circuit breakers, complexity reduction) that Claude already understands. It lacks project-specific context, clear invocation instructions, and any progressive disclosure structure. The code examples, while concrete, are generic patterns rather than actionable guidance tied to a specific refinement workflow.

Suggestions

Reduce content by 80%+ by removing explanations of concepts Claude already knows (TDD, circuit breakers, error hierarchies, cyclomatic complexity) and focus only on project-specific refinement rules or constraints.

Add a clear workflow with explicit validation checkpoints: what triggers refinement, what checks must pass before completion, and what outputs are expected.

Split detailed code patterns into separate reference files (e.g., PATTERNS.md, ERROR_HANDLING.md) and keep SKILL.md as a concise overview with navigation links.

Add concrete instructions for how this skill should be invoked, what inputs it expects (e.g., which files to refine), and what success criteria look like.

DimensionReasoningScore

Conciseness

Extremely verbose at ~400+ lines. Explains fundamental concepts Claude already knows (TDD red/green/refactor, circuit breakers, error hierarchies, cyclomatic complexity). The examples are lengthy and illustrative rather than providing novel, project-specific guidance. Most content is generic software engineering knowledge.

1 / 3

Actionability

The code examples are concrete and mostly executable TypeScript, which is good. However, they are generic patterns (authentication service, circuit breaker) not tied to any specific project context. There's no guidance on when/how to invoke this skill, what inputs it expects, or what outputs it produces. It reads more like a textbook than an operational skill.

2 / 3

Workflow Clarity

The TDD Red-Green-Refactor phases provide a recognizable sequence, but there are no explicit validation checkpoints, no feedback loops for error recovery, and no clear decision points for when refinement is 'done.' The numbered best practices at the end are vague platitudes rather than actionable workflow steps.

2 / 3

Progressive Disclosure

Monolithic wall of text with no references to external files and no layered structure. All content—from basic TDD to circuit breakers to complexity analysis—is dumped inline. There's no separation of quick-start vs. advanced content, and no bundle files to support progressive disclosure.

1 / 3

Total

6

/

12

Passed

Description

0%Scale 1-3

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 domain it operates in. The only content is an invocation command, which is useless for skill selection purposes.

Suggestions

Define what 'refinement' means in this context by listing specific concrete actions the skill performs (e.g., 'Iterates on code output based on user feedback, improving structure, readability, and correctness').

Add an explicit 'Use when...' clause with natural trigger terms that describe scenarios where this skill should be selected (e.g., 'Use when the user asks to improve, iterate on, or polish existing output').

Specify the domain or artifact type this skill operates on to distinguish it from other skills (e.g., code refinement vs. prose refinement vs. design refinement).

DimensionReasoningScore

Specificity

The description provides no concrete actions whatsoever. 'Refinement' is abstract and undefined — there is no indication of what is being refined or how.

1 / 3

Completeness

The description fails to answer both 'what does this do' and 'when should Claude use it.' There is no explanation of capabilities and no 'Use when...' clause or equivalent guidance.

1 / 3

Trigger Term Quality

The only potentially relevant term is 'refinement,' which is vague and not a natural keyword users would use. The description focuses on invocation syntax ('$agent-refinement') rather than user-facing trigger terms.

1 / 3

Distinctiveness Conflict Risk

'Refinement' is extremely generic and could apply to virtually any skill that iterates or improves output. There is nothing to distinguish this from other skills.

1 / 3

Total

4

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (530 lines); consider splitting into references/ and linking

Warning

Total

10

/

11

Passed

Repository
ruvnet/claude-flow
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.