Name: agent-workflow
Rating: 60.6 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-workflow

Agent skill for workflow - invoke with $agent-workflow

2.43x

Quality

41%

Does it follow best practices?

Impact

95%

2.43x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is agent-workflow in ruvnet/claude-flow

Quality

Content

57%Weight 40%Scale 1-5

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

The body delivers a usable, concrete MCP toolkit and a clear design-methodology sequence, but it is padded with abstract capability/quality/feature prose, lacks validation checkpoints in its workflow, and has malformed structure (a duplicate frontmatter block). No bundle files exist to offload detail.

Suggestions

Trim the abstract 'Quality standards' and 'Advanced features you leverage' lists, folding only the non-obvious points into the toolkit or design sections to improve conciseness.

Add an explicit validation/verification step to the workflow design approach (e.g., check workflow_status with metrics before declaring success, and a fix-and-retry loop on failure) to lift workflow clarity above 3.

Remove the stray duplicate YAML frontmatter block near the top of the body so the document has a single clean structure.

Dimension	Reasoning	Score
Conciseness	The toolkit code block is efficient, but surrounding sections ("Your core responsibilities", "Quality standards", "Advanced features you leverage") are abstract capability lists that could be tightened, fitting 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	The JavaScript toolkit block gives concrete MCP tool calls with named parameters (workflow_create, workflow_execute, workflow_agent_assign, workflow_status), which is mostly executable guidance with minor gaps (placeholder IDs, no setup/auth details), landing just above the 'some concrete guidance but incomplete' anchor.	4 / 5
Workflow Clarity	The numbered 'workflow design approach' (1-6) provides a sequence but no validation/verification checkpoints; per the batch/destructive cap this cannot exceed 3, matching 'steps listed but validation gaps; checkpoints missing'.	3 / 5
Progressive Disclosure	Content has section headers but is a single ~85-line inline file with no external references, and a stray duplicate frontmatter block in the body harms organization, fitting 'some structure but could be better organized' rather than the well-placed anchor at 4.	3 / 5
	Total	13 / 20 Passed

Description

25%Weight 40%Scale 1-5

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 frontmatter description is a near-placeholder that says how to invoke the skill but not what it concretely does or when to use it, leaving it generic and conflict-prone. Notably, a far richer description ("Event-driven workflow automation specialist...") exists only inside the body, not in the parsed frontmatter.

Suggestions

Replace the frontmatter description with a concrete statement of capabilities, e.g. 'Create, execute, and monitor event-driven automation workflows with multi-agent task assignment and message queue coordination.'

Add an explicit 'Use when...' clause naming natural trigger phrases such as 'workflow automation', 'CI/CD pipeline', 'event-driven pipeline', or 'ETL pipeline'.

Use third-person action verbs ('Creates', 'Executes', 'Monitors') and include distinguishing keywords to reduce overlap with other workflow-related skills.

Dimension	Reasoning	Score
Specificity	The phrase "Agent skill for workflow" names the domain (workflow) but states no concrete actions; the only other clause ("invoke with $agent-workflow") is invocation syntax, not a capability, matching the 'names domain but actions minimal/generic' anchor rather than the entirely-vague anchor below it.	2 / 5
Completeness	It offers only a vague 'what' ("Agent skill for workflow") and entirely omits any 'when'/'Use when' guidance, matching the 'vague what and no when' anchor; it does not rise to 3 because there is no explicit trigger clause and the what is extremely thin.	2 / 5
Trigger Term Quality	"workflow" is one generic keyword a user might say, but there are no natural trigger phrases and "invoke with $agent-workflow" is technical invocation syntax, fitting the 'one or two generic keywords; missing natural phrases' anchor.	2 / 5
Distinctiveness Conflict Risk	"Agent skill for workflow" is very broad and would overlap with many workflow-related skills, fitting the 'very broad; high overlap risk' anchor rather than the 'somewhat specific' anchor at 3.	2 / 5
	Total	8 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Path: .agents/skills/agent-workflow/SKILL.md
Commit: fa13ee4

Reviewed: about 4 hours 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.