agent-refinement

Agent skill for refinement - invoke with $agent-refinement

Install with Tessl CLI

npx tessl i github:ruvnet/claude-flow --skill agent-refinement

What are skills?

Review — 13%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Discovery

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 concrete actions, no natural trigger terms, no guidance on when to use it, and is so generic that it would be impossible for Claude to reliably select this skill from a pool of alternatives. The description reads more like a placeholder than a functional skill description.

Suggestions

Specify what is being refined (e.g., 'Refines code quality', 'Refines document structure', 'Refines agent responses') with concrete actions like 'improves clarity, fixes errors, optimizes performance'

Add a 'Use when...' clause with explicit triggers such as 'Use when the user asks to improve, polish, iterate on, or refine existing content'

Include natural keywords users would actually say, such as 'improve', 'polish', 'iterate', 'make better', 'clean up', along with the specific domain (code, text, etc.)

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for refinement' is completely abstract with 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 'Use when...' clause and no explanation of capabilities.	1 / 3
Trigger Term Quality	The only trigger term is '$agent-refinement' which is a technical command, not a natural keyword users would say. 'Refinement' is too vague to serve as a useful trigger.	1 / 3
Distinctiveness Conflict Risk	'Refinement' is extremely generic and could apply to code refinement, document refinement, image refinement, or any iterative improvement task. This would conflict with many other skills.	1 / 3
	Total	4 / 12 Passed

Implementation

27%

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

This skill is excessively verbose, teaching Claude generic software engineering patterns (TDD, circuit breakers, error hierarchies) that it already knows well. The content reads like a tutorial rather than project-specific guidance. It would be far more effective as a brief overview pointing to when/how to apply refinement in this specific project context.

Suggestions

Reduce content to project-specific refinement guidance (e.g., 'Run npm test before committing', 'Use existing ErrorHandler in src/errors/') rather than teaching generic patterns

Split into separate files: SKILL.md overview, TDD.md, PERFORMANCE.md, ERROR_HANDLING.md with clear navigation links

Add explicit validation checkpoints: 'Run tests after each refactor step - do not proceed if tests fail'

Replace generic code examples with references to actual project files or patterns already established in the codebase

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive code examples that explain concepts Claude already knows (TDD phases, error handling patterns, circuit breakers). The 400+ lines could be condensed to ~50 lines of project-specific guidance.	1 / 3
Actionability	Contains executable TypeScript code examples, but they are generic patterns rather than project-specific guidance. The examples are illustrative rather than copy-paste ready for a specific codebase.	2 / 3
Workflow Clarity	The TDD Red-Green-Refactor phases are clearly sequenced, but validation checkpoints are implicit. No explicit 'verify tests pass before proceeding' steps or error recovery guidance for when refinement fails.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files. All content is inline despite being lengthy enough to warrant splitting into separate files for TDD, performance, error handling, etc.	1 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (530 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Reviewed: about 13 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.