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

Advisory

Suggest reviewing before use

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a broad, example-rich catalog of GitHub Actions/swarm automation patterns that is actionable in places but undermined by repetitive padding, pseudocode blocks, missing validation checkpoints, and broken external references. It would benefit from consolidation, executable-only examples, and moving templates into real referenced files.

Suggestions

Consolidate the repetitive 'npx ruv-swarm actions' command examples into a single parameterized reference table to cut length and redundancy.

Replace the pseudocode 'mcp__claude-flow__* { ... }' blocks with real executable syntax, or explicitly label them as illustrative pseudocode.

Add validation checkpoints to the deployment, self-healing, and auto-retry workflows, and either create the referenced swarm-pr.md/swarm-issue.md/sync-coordinator.md files or remove the broken 'See also' links.

Dimension	Reasoning	Score
Conciseness	The ~600-line body is mostly command/YAML examples rather than conceptual padding Claude already knows, but it is highly repetitive — dozens of near-identical 'npx ruv-swarm actions X --flag --flag' blocks and re-listed best-practice bullets that could be consolidated.	2 / 3
Actionability	Many YAML workflows and bash commands are concrete and copy-paste ready, but a large portion is pseudocode (the 'mcp__claude-flow__* { ... }' blocks are not valid bash or JS), and several standalone bash blocks embed unresolvable GitHub expressions like '${{ github.sha }}' outside a workflow context.	2 / 3
Workflow Clarity	The document is organized into clear sections and a few examples show sequencing (self-healing, progressive deployment), but it is a feature catalog rather than a sequenced workflow, and none of the batch/destructive operations (deployment, self-heal, auto-retry) include validation checkpoints, which caps this dimension at 2.	2 / 3
Progressive Disclosure	Sections are reasonably organized and there are one-level 'See also' references at the end, but the body is a monolithic ~600 lines of templates that belong in separate files, and the three referenced files (swarm-pr.md, swarm-issue.md, sync-coordinator.md) do not actually exist, so navigation is not reliable.	2 / 3
	Total	8 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is auto-generated boilerplate that fails to convey concrete capabilities, natural trigger terms, or usage conditions, making it indistinguishable from many other automation skills. It needs to be rewritten to name specific actions (e.g., creating/optimizing GitHub Actions workflows) and explicit 'Use when...' triggers.

Suggestions

Rewrite the description to list concrete actions, e.g., 'Create, optimize, and debug GitHub Actions CI/CD workflows with multi-agent swarm coordination.'

Add an explicit trigger clause: 'Use when the user asks to set up or improve GitHub Actions workflows, CI/CD pipelines, or workflow automation.'

Replace the invocation token ('$agent-workflow-automation') with natural language a user would actually say, and use third-person voice.

Dimension	Reasoning	Score
Specificity	The description "Agent skill for workflow-automation - invoke with $agent-workflow-automation" names no concrete actions; it is generic boilerplate ("Agent skill for...") rather than listing capabilities like creating or optimizing CI/CD pipelines.	1 / 3
Completeness	It states only a weak "what" (an agent skill for workflow-automation) and provides no "when" guidance at all — there is no "Use when..." clause or equivalent trigger, which per the guidelines caps completeness at 2, and the weak "what" pulls it to 1.	1 / 3
Trigger Term Quality	The only keywords are the generic compound "workflow-automation" and the invocation token "$agent-workflow-automation"; natural terms a user would actually say (e.g., "GitHub Actions", "CI/CD", "workflows") are absent, so it reads as jargon/invocation syntax rather than natural triggers.	1 / 3
Distinctiveness Conflict Risk	"workflow-automation" is very generic and would overlap with numerous CI/CD, devops, and automation skills; nothing in the description carves out a distinct niche or trigger set.	1 / 3
	Total	4 / 12 Passed

Validation

87%

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 — 14 / 16 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
relative_links	Relative link issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: ruvnet/claude-flow
Commit: 03d4f84

Reviewed: 2 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.