agent-workflow-automation
Agent skill for workflow-automation - invoke with $agent-workflow-automation
36
3%
Does it follow best practices?
Impact
95%
6.33xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-workflow-automation/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 description is essentially a placeholder that restates the skill name without providing any meaningful information about capabilities, use cases, or trigger conditions. It fails on every dimension: no concrete actions, no natural trigger terms, no completeness, and no distinctiveness. Claude would have no basis for selecting this skill appropriately from a list of available skills.
Suggestions
Replace the generic label with specific concrete actions the skill performs, e.g., 'Automates multi-step workflows by chaining API calls, scheduling tasks, and managing conditional logic.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to automate a sequence of steps, create a pipeline, schedule recurring tasks, or chain multiple actions together.'
Remove the invocation instruction ('invoke with $agent-workflow-automation') from the description—it wastes space and doesn't help Claude decide when to select the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Workflow-automation' is abstract and vague—it doesn't describe what specific tasks or operations the skill 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 beyond the skill name itself. | 1 / 3 |
Trigger Term Quality | The only keyword is 'workflow-automation,' which is generic jargon. There are no natural terms a user would say, such as specific workflow types, automation targets, or task names. | 1 / 3 |
Distinctiveness Conflict Risk | 'Workflow-automation' is extremely generic and could overlap with virtually any skill that automates tasks, processes, or pipelines. There are no distinct triggers to differentiate it. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an extremely verbose, largely fictional document that references non-existent tools and packages. It reads like aspirational marketing material rather than actionable automation guidance. The code examples are not executable, the MCP tool invocations use invalid syntax, and there are no real validation steps or clear workflows despite the CI/CD focus.
Suggestions
Replace all fictional tool references (ruv-swarm, ruvnet/swarm-action) with actual executable commands using the declared MCP tools and standard GitHub Actions patterns
Reduce content by 70%+ - pick 2-3 core workflows and make them fully executable with real tool invocations, removing all speculative features
Add explicit validation checkpoints to workflows (e.g., verify workflow YAML syntax before committing, check run status after dispatch)
Show correct MCP tool invocation syntax with realistic parameters instead of pseudo-JSON notation
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 400+ lines with massive amounts of repetitive content. Many sections show variations of the same pattern (spawn agents, run npx commands). Explains concepts Claude already knows, and includes speculative/aspirational features (predictive failures, self-healing CI) with no real executable substance. The content could be reduced by 70%+ without losing actionable information. | 1 / 3 |
Actionability | Almost entirely references a fictional tool 'ruv-swarm' and fictional MCP tool invocations with made-up syntax (e.g., mcp__claude-flow__swarm_init with JSON-like arguments that aren't valid). None of the code is executable - the npx commands reference non-existent packages, the GitHub Actions workflows use fictional actions (ruvnet/swarm-action@v1), and the JavaScript examples use non-existent APIs. This is aspirational documentation, not actionable guidance. | 1 / 3 |
Workflow Clarity | Despite describing CI/CD workflows, there are no clear step-by-step processes with validation checkpoints. The content jumps between disconnected code snippets without explaining when or how to use them. No verification steps, no error recovery guidance, and no clear sequencing for the multi-step operations described. The 'Best Practices' section is a bullet list of vague advice. | 1 / 3 |
Progressive Disclosure | The content has some structural organization with headers and sections, and includes references to related files (swarm-pr.md, swarm-issue.md, sync-coordinator.md) at the end. However, the main file is a monolithic wall of content that should have been split into separate reference files. The sheer volume of inline content undermines the structure. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
90%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 (640 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ruvnet/ruflo
- Commit
398f7c2
- 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.