agent-workflow

Agent skill for workflow - invoke with $agent-workflow

2.43x

Quality

36%

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

Quality

Content

72%

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

The body delivers strong actionability via concrete MCP tool examples and is well-organized for a simple skill, but it is padded with restated-capability bullet lists and lacks validation/feedback checkpoints in its workflow steps.

Suggestions

Trim the 'Quality standards' and 'Advanced features you leverage' lists, which restate capabilities Claude already infers from the toolkit section.

Add explicit validation/retry checkpoints to the 6-step workflow approach (e.g., validate workflow status after execute, retry failed steps) to support error-prone automation operations.

Resolve the malformed duplicate frontmatter block (the second '---' with flow-nexus-workflow) which is invalid markdown and clutters the body.

Dimension	Reasoning	Score
Conciseness	The MCP toolkit code block is concrete, but surrounding 'Quality standards', 'Advanced features you leverage', and capability lists restate concepts Claude already knows and could be trimmed; not a level 3 lean body.	2 / 3
Actionability	The toolkit provides fully executable, copy-paste-ready MCP tool calls with real parameters (workflow_create, workflow_execute, workflow_agent_assign, workflow_status), meeting the highest anchor.	3 / 3
Workflow Clarity	The 6-step design approach is sequenced, but there are no validation checkpoints or feedback loops for risky automation/batch execution, which caps workflow clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	This is a simple single-purpose skill with well-organized sections and no external references needed, so it meets the simple-skill allowance for a 3 without separate files.	3 / 3
	Total	10 / 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 frontmatter description is a bare placeholder with no concrete capabilities, natural trigger terms, or use-conditions, making it indistinguishable from any generic workflow skill. It needs a complete rewrite stating specific actions and explicit 'use when' triggers.

Suggestions

Replace the placeholder with concrete actions, e.g. 'Creates, executes, and monitors event-driven automation workflows with message-queue processing and agent coordination.'

Add an explicit 'Use when...' clause listing natural triggers users would say, such as 'Use when designing CI/CD pipelines, ETL/data processing, or event-driven automation workflows.'

Drop the invocation syntax ('$agent-workflow') from the description and focus on capability + trigger language to reduce conflict with other skills.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for workflow - invoke with $agent-workflow' names no concrete actions, only the abstract concept of a workflow agent, matching the vague-language anchor.	1 / 3
Completeness	It states neither clearly what the skill does (only 'workflow' vaguely) nor when to use it, with no 'Use when...' clause; both what and when are weak or missing.	1 / 3
Trigger Term Quality	The only trigger cue is the technical invocation syntax '$agent-workflow'; there are no natural keywords a user would actually say, so it stays at the lowest level.	1 / 3
Distinctiveness Conflict Risk	'Agent skill for workflow' is extremely generic and would overlap with many skills, offering no distinctive niche to prevent wrong-skill triggering.	1 / 3
	Total	4 / 12 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/claude-flow
Path: .agents/skills/agent-workflow/SKILL.md
Commit: 26c35b5

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.