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 known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-workflow/SKILL.md

Quality

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 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 countless other skills. It reads more like a command invocation hint than a skill description.

Suggestions

Replace the entire description with concrete actions the skill performs, e.g., 'Orchestrates multi-step task pipelines, manages sequential agent handoffs, and tracks workflow state' or whatever the skill actually does.

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs to automate a sequence of tasks, create a pipeline, or coordinate multiple steps in a process.'

Remove the invocation instruction ('invoke with $agent-workflow') from the description—this is meta-information that doesn't help Claude decide when to select the skill, and instead use that space to describe the skill's unique niche and capabilities.

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 find a specific skill. 'Agent' and 'invoke' are technical/meta terms, not user-facing trigger terms.	1 / 3
Distinctiveness Conflict Risk	'Workflow' is an extremely broad term that could apply to virtually any automation, orchestration, or process skill. This description would conflict with many other skills and provides no distinguishing characteristics.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

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 feature catalog rather than actionable instructions. It spends most of its tokens listing generic software engineering concepts (error handling, scalability, monitoring) that Claude already understands, while providing minimal concrete guidance on how to actually use the MCP tools effectively. The code examples are the only redeeming element but lack response formats, error handling patterns, and validation steps.

Suggestions

Remove the persona framing and generic concept lists (quality standards, workflow patterns, advanced features) — replace with concrete examples showing input/output for each MCP tool call including expected response formats

Add explicit validation and error handling workflows: what does a failed workflow_execute response look like, and what concrete steps should Claude take to recover?

Replace the abstract 'workflow design approach' with a concrete step-by-step sequence Claude should follow when a user asks to create a workflow, including validation checkpoints

Either create bundle files for detailed API reference and examples, or trim the content to under 50 lines focusing only on the MCP tool signatures and one complete end-to-end example

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', 'advanced features', and 'workflow patterns' 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.	1 / 3
Actionability	The JavaScript code examples showing MCP tool calls are somewhat concrete and provide specific function signatures with parameters, which is useful. However, the examples are illustrative rather than fully executable (no error handling shown, no response format documented), and the vast majority of the content is abstract description rather than concrete guidance.	2 / 3
Workflow Clarity	The 'workflow design approach' is a generic 6-step process (requirements analysis, architecture, etc.) that describes abstract phases rather than concrete steps Claude should follow. There are no validation checkpoints, no feedback loops for error recovery, and no clear sequence for what to do when things fail despite mentioning 'error handling' repeatedly.	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

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
Commit: 9d4a9ea

Reviewed: 6 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.