Name: agent-workflow-automation
Rating: 36.6 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-workflow-automation

Agent skill for workflow-automation - invoke with $agent-workflow-automation

6.33x

Quality

Does it follow best practices?

Impact

95%

6.33x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-workflow-automation/SKILL.md

Quality

Content

7%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 an extremely verbose, largely non-actionable document that references fictional tools and APIs throughout. It reads more like a marketing brochure for a hypothetical 'ruv-swarm' product than an actionable skill for Claude. The content is padded with repetitive YAML/bash examples that all follow the same pattern and none of which are executable against real tools.

Suggestions

Replace all fictional tool references (ruv-swarm, ruvnet/swarm-action) with actual executable commands using the MCP tools listed in the frontmatter, or real GitHub Actions CLI commands

Reduce content by 70-80% - consolidate the dozens of similar 'npx ruv-swarm actions <verb>' examples into a concise reference table and keep only 2-3 fully worked examples

Add explicit validation checkpoints and error handling to workflows, especially for destructive operations like deployments and automated PR/issue creation

Move detailed workflow templates and integration examples into separate bundle files, keeping SKILL.md as a concise overview with clear references

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines with massive amounts of repetitive examples. Many sections show variations of the same pattern (npx ruv-swarm actions <command> with flags). Explains concepts Claude already knows, and includes speculative/non-existent tools (ruv-swarm) with extensive boilerplate YAML that adds little instructional value.	1 / 3
Actionability	Despite containing many code blocks, none are truly executable - they reference a non-existent tool (ruv-swarm/npx ruv-swarm), fictional GitHub Actions (ruvnet/swarm-action@v1), and MCP tool calls with invented syntax (mcp__claude-flow__swarm_init { topology: 'mesh' }). The code is essentially pseudocode dressed up as real commands, with no verifiable or copy-paste-ready content.	1 / 3
Workflow Clarity	While many multi-step processes are shown, there are no validation checkpoints, no error recovery feedback loops, and no verification steps. The workflows are presented as aspirational sequences without any mechanism to confirm success or handle failures. The 'Self-Healing CI/CD' section ironically lacks any actual self-healing logic.	1 / 3
Progressive Disclosure	The content has section headers providing some organization, and references three related files at the bottom (swarm-pr.md, swarm-issue.md, sync-coordinator.md). However, the massive monolithic body contains far too much content that should be split into separate reference files. No bundle files are provided to verify the references exist.	2 / 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 description is essentially a label rather than a functional description. It provides no concrete actions, no trigger guidance, and no distinguishing details. It would be nearly impossible for Claude to correctly select this skill from a pool of available skills based on this description alone.

Suggestions

Replace the generic label with specific concrete actions the skill performs, e.g., 'Creates automated workflows, schedules recurring tasks, chains multi-step processes, and triggers actions based on events.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to automate tasks, create pipelines, set up triggers, or build multi-step workflows.'

Specify the domain or tools involved (e.g., CI/CD pipelines, task scheduling, API integrations) to make the skill clearly distinguishable from other automation-related skills.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'Workflow-automation' is abstract and vague — it doesn't describe what the skill actually does (e.g., create workflows, schedule tasks, trigger events).	1 / 3
Completeness	The description fails to answer both 'what does this do' and 'when should Claude use it.' There is no 'Use when...' clause and no meaningful explanation of capabilities.	1 / 3
Trigger Term Quality	The only keyword is 'workflow-automation,' which is a hyphenated compound that users are unlikely to naturally say. There are no natural trigger terms like 'automate tasks,' 'schedule,' 'pipeline,' or specific workflow tool names.	1 / 3
Distinctiveness Conflict Risk	'Workflow-automation' is extremely generic and could overlap with virtually any automation-related skill. There are no distinct triggers or niche identifiers to differentiate it from other skills.	1 / 3
	Total	4 / 12 Passed

Validation

90%

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 — 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/claude-flow
Path: .agents/skills/agent-workflow-automation/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.