agent-workflow
Agent skill for workflow - invoke with $agent-workflow
39
7%
Does it follow best practices?
Impact
95%
2.43xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-workflow/SKILL.mdQuality
Discovery
0%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 essentially no useful information for skill selection. It fails on every dimension: it names no concrete actions, includes no natural trigger terms, answers neither 'what' nor 'when', and is so generic it would conflict with many other skills. It reads more like a label than a description.
Suggestions
Describe the specific actions this skill performs (e.g., 'Creates, manages, and automates multi-step workflows including task sequencing, conditional branching, and parallel execution').
Add an explicit 'Use when...' clause with natural trigger terms that users would actually say (e.g., 'Use when the user asks to automate a process, create a pipeline, orchestrate tasks, or set up a multi-step workflow').
Remove the invocation instruction ('invoke with $agent-workflow') from the description and replace it with capability and context information that helps Claude distinguish this skill from others.
| 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 | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause and no description of capabilities. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'workflow', which is extremely generic. There are no natural keywords a user would say to trigger this skill. 'invoke with $agent-workflow' is an invocation instruction, not a trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | 'Workflow' is an extremely broad term that could overlap with virtually any process-oriented skill. There is nothing distinctive about this description to differentiate it from other skills. | 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 heavily padded with generic software engineering concepts and vague descriptions that Claude already knows. While it provides some useful MCP tool call signatures, the content lacks concrete executable workflows, validation checkpoints, and structured progressive disclosure. The majority of the content describes what the agent should be rather than providing actionable instructions for how to accomplish specific tasks.
Suggestions
Remove the verbose role description, quality standards, and advanced features lists—replace with a concise quick-start section showing a complete workflow creation-to-execution example with actual tool calls and expected responses.
Add explicit validation checkpoints: after workflow_create, check the response for errors; after workflow_execute, poll workflow_status and handle failure states with concrete retry logic.
Replace the abstract 'workflow design approach' with a concrete step-by-step sequence showing how to go from user request to running workflow, including specific decision points and error handling.
Split workflow patterns (CI/CD, ETL, etc.) into separate reference files or provide one complete end-to-end example instead of listing six abstract pattern names.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive lists of concepts Claude already knows (error handling, scalability, fault tolerance). The 'quality standards', 'advanced features', 'workflow patterns', and 'workflow design approach' sections are padded with generic software engineering principles that don't add actionable value. | 1 / 3 |
Actionability | The JavaScript code examples showing MCP tool calls are somewhat concrete and provide specific function signatures with parameters. However, they are illustrative rather than executable in a real context—there's no guidance on what actual values to use, how to handle responses, or what the return types look like. | 2 / 3 |
Workflow Clarity | The 6-step 'workflow design approach' is abstract and reads like a generic methodology description rather than a concrete sequence with validation checkpoints. There are no verification steps, no feedback loops for error recovery, and no clear guidance on what to do when a workflow step fails. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files and no clear separation between quick-start material and advanced content. Everything is dumped into a single document with bullet-point lists that could be better organized or split. | 1 / 3 |
Total | 5 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/claude-flow
- Commit
f547cec
- 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.