agent-workflow

Agent skill for workflow - invoke with $agent-workflow

2.43x

Quality

Does it follow best practices?

Impact

95%

2.43x

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-workflow/SKILL.md

Quality

Content

14%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 primarily a persona description and capability listing rather than actionable instructions. It spends most of its tokens describing what the agent is and what it can do in abstract terms, rather than providing concrete, executable guidance for how to accomplish specific tasks. The MCP tool call examples are the only concrete element, but they lack context on when to use each, what responses look like, and how to handle errors.

Suggestions

Remove the persona description and generic capability lists; replace with a concise quick-start section showing a complete workflow creation-to-execution sequence with expected outputs.

Add explicit validation and error-handling workflows: show what to check after workflow_execute, how to interpret workflow_status responses, and what to do when steps fail.

Replace the abstract 'workflow design approach' with concrete decision trees or checklists (e.g., 'If the workflow has independent steps, use parallel execution by setting...').

Cut the 'workflow patterns', 'quality standards', and 'advanced features' bullet lists entirely — these describe generic concepts Claude already knows and add no actionable value.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive explanations of concepts Claude already knows (what CI/CD is, what ETL pipelines are, what error handling means). The 'quality standards', 'workflow patterns', and 'advanced features' sections are padded lists of generic software engineering concepts that don't add actionable value. The persona framing ('You are a Flow Nexus Workflow Agent') wastes tokens on identity description.	1 / 3
Actionability	The JavaScript code examples showing MCP tool calls are somewhat concrete and provide specific function signatures with parameter examples. However, the examples are illustrative rather than executable in a real context, and the bulk of the content is abstract descriptions ('Design step sequences, dependencies, and parallel execution paths') rather than concrete instructions for what to actually do.	2 / 3
Workflow Clarity	The 'workflow design approach' lists 6 high-level steps but they are vague and abstract (e.g., 'Understand the automation objectives and constraints'). There are no validation checkpoints, no error recovery sequences, no feedback loops. For a skill involving workflow orchestration with potentially destructive or complex multi-step operations, the absence of concrete validation steps is a significant gap.	1 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files, no clear navigation structure, and no separation of overview from detailed content. Everything is dumped into a single file with no progressive disclosure strategy, and there are no bundle files to support it.	1 / 3
	Total	5 / 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 is an extremely weak description that provides almost no useful information. It fails on every dimension: it names no concrete actions, includes no natural trigger terms, lacks both 'what' and 'when' guidance, and is so generic it would be indistinguishable from many other skills. It reads more like a label than a description.

Suggestions

Replace the vague 'workflow' reference with specific concrete actions the skill performs (e.g., 'Creates, manages, and automates multi-step workflows including task sequencing, conditional branching, and status tracking').

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 automate a process, create a pipeline, orchestrate tasks, or manage sequential steps').

Remove the invocation syntax ('invoke with $agent-workflow') from the description—this is implementation detail, not selection guidance—and instead use that space to clearly define the skill's unique niche.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Agent skill for workflow' is entirely vague—it doesn't describe what the skill does, what domain it operates in, or what actions it performs.	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 trigger guidance.	1 / 3
Trigger Term Quality	The only potentially relevant term is 'workflow,' which is extremely generic and not a natural keyword a user would use to invoke a specific skill. 'Agent' and '$agent-workflow' are technical jargon, not user-facing trigger terms.	1 / 3
Distinctiveness Conflict Risk	'Workflow' is an extremely broad term that could overlap with virtually any task-oriented skill. There is nothing distinctive about this description that would help Claude differentiate it from other 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Path: .agents/skills/agent-workflow/SKILL.md
Commit: 913f9ea

Reviewed: 3 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.