agent-workflow
Agent skill for workflow - invoke with $agent-workflow
42
11%
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 could conflict with any number of other skills. It reads more like a placeholder than a functional description.
Suggestions
Replace the entire description with specific actions the skill performs, e.g., 'Creates, manages, and automates multi-step workflows including task sequencing, dependency tracking, and parallel execution.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to automate a sequence of tasks, build a pipeline, orchestrate steps, or manage task dependencies.'
Remove the invocation instruction ('invoke with $agent-workflow') from the description, as it does not help Claude decide when to select the skill and wastes space that should describe capabilities.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for workflow' is entirely vague and abstract, with no indication of what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause and no description of capabilities. | 1 / 3 |
Trigger Term Quality | The only keyword is 'workflow', which is extremely generic. There are no natural terms a user would say to trigger this skill. '$agent-workflow' is a technical invocation command, not a natural language trigger. | 1 / 3 |
Distinctiveness Conflict Risk | 'Workflow' is an extremely generic term that could overlap with virtually any task-oriented skill. There is nothing distinctive about this description. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
22%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 persona descriptions that Claude already knows, while lacking the concrete, executable guidance needed for effective workflow automation. The MCP tool examples are a strength but are undermined by the absence of real workflow sequences, validation steps, expected outputs, and error handling procedures. The skill reads more like a marketing description of capabilities than an actionable instruction set.
Suggestions
Remove the verbose persona description, quality standards, workflow patterns list, and advanced features list—these are generic concepts Claude already knows. Focus only on tool-specific knowledge.
Add concrete end-to-end workflow examples showing how to chain tool calls together, including expected output from each step and how to use that output in subsequent calls.
Add explicit validation and error handling steps: what does workflow_status return on failure? What should Claude do when a step fails? Include a feedback loop (check status -> handle error -> retry).
Replace the abstract 'workflow design approach' with a concrete numbered procedure using actual tool calls, e.g., '1. Create workflow with workflow_create 2. Verify creation succeeded by checking response 3. Execute with workflow_execute 4. Poll workflow_status until complete'.
| 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 add no actionable value. The persona description ('You are a Flow Nexus Workflow Agent...') wastes tokens on role-playing setup. | 1 / 3 |
Actionability | The JavaScript code block provides concrete MCP tool calls with example parameters, which is useful. However, the examples are incomplete—there's no guidance on expected outputs, error responses, or how to chain the tools together in practice. The 'workflow design approach' is a vague numbered list of abstract steps rather than executable guidance. | 2 / 3 |
Workflow Clarity | The 6-step 'workflow design approach' is entirely abstract ('Understand the automation objectives', 'Design step sequences') with no concrete validation checkpoints, no error recovery procedures, and no feedback loops. For a skill involving multi-step workflow orchestration, the absence of any concrete sequencing or validation steps is a significant gap. | 1 / 3 |
Progressive Disclosure | The content has some structural organization with headers and sections, but it's a monolithic file with no references to external documentation. Content like the full list of workflow patterns and advanced features could be split into separate reference files. However, given no bundle files exist, the inline approach is the only option, though it results in bloat. | 2 / 3 |
Total | 6 / 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
2b9e2de
- 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.