Name: agent-test-long-runner
Rating: 48.8 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-test-long-runner

Agent skill for test-long-runner - invoke with $agent-test-long-runner

0.98x

Quality

21%

Does it follow best practices?

Impact

96%

0.98x

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-test-long-runner/SKILL.md

The canonical home for this skill is agent-test-long-runner in ruvnet/claude-flow

Quality

Content

25%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 content is well-sectioned but almost entirely generic motivational guidance with no concrete code, commands, or operational workflow. It tells Claude to be thorough and take its time rather than conferring any skill-specific, executable knowledge.

Suggestions

Add concrete, executable guidance — at least one worked example (e.g. a sample analysis plan or a report skeleton) instead of abstract directives like 'Deep dive into codebases'.

Replace the attitudinal Instructions list with an operational workflow with explicit checkpoints (e.g. scope -> analyze -> draft -> self-review -> deliver), so the steps are actionable rather than motivational.

Remove the stray duplicate YAML frontmatter block at the top of the body; keep a single frontmatter and let the body begin with the '# Test Long-Running Agent' heading.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic attitudinal directives Claude already knows ("Take Your Time: Don't rush - quality over speed", "Be Thorough", "Document Everything") and buzzword-heavy capability labels, fitting the noticeably-verbose/padded anchor; it avoids a 1 because it does not explain technical concepts Claude knows, it just over-directs.	2 / 5
Actionability	There is no code, no command, and no concrete executable step — only abstract directives like "Deep dive into codebases" and "Provide detailed, well-structured responses", matching the entirely-vague/no-executable-guidance anchor exactly.	1 / 5
Workflow Clarity	The numbered Instructions list is a rough sequence but every step is an attitudinal directive with no operational detail or checkpoints ("Iterate", "Communicate Progress"), matching the rough-sequence-many-gaps anchor; it is above 1 because a numbered sequence does exist.	2 / 5
Progressive Disclosure	The body is under 50 lines with no need for external references and is organized into clear sections (Capabilities, Instructions, Output Format, Example Use Cases), fitting the good-structure anchor; it is capped below 5 by the malformed duplicate frontmatter block left at the top of the body.	4 / 5
	Total	9 / 20 Passed

Description

17%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 description is auto-generated boilerplate that names the skill slug and its invocation command but states no concrete capabilities or trigger conditions. It fails to tell a user or Claude what the skill does or when to use it.

Suggestions

Replace the boilerplate with a concrete statement of what the agent does, e.g. 'Runs long-running (30+ minute) analysis, research, and reporting tasks that require sustained multi-step work.'

Add an explicit 'Use when...' trigger clause naming natural phrases a user would say, such as 'Use when a task needs deep, extended analysis or comprehensive documentation that exceeds a quick single-pass response.'

Drop the 'invoke with $agent-test-long-runner' invocation syntax from the description; it is not a trigger term and crowds out capability information.

Dimension	Reasoning	Score
Specificity	The description only names the domain ("Agent skill for test-long-runner") and an invocation directive ("invoke with $agent-test-long-runner") with no concrete capability actions, matching the anchor that names a domain but gives minimal/generic actions; it is not a 1 because it does name a specific domain rather than being fully abstract.	2 / 5
Completeness	It offers only a vague "what" ("Agent skill for test-long-runner") and no real "when" — "invoke with $agent-test-long-runner" is invocation syntax, not a trigger condition, so it fits the vague-what-and-no-when anchor; it is above 1 because a domain is at least named.	2 / 5
Trigger Term Quality	The only terms are the slug "test-long-runner" and the invocation syntax "$agent-test-long-runner" / "invoke with", which is technical invocation jargon rather than natural phrases a user would say, matching the no-natural-keywords anchor; it does not reach 2 because there are no generic-but-natural keywords either.	1 / 5
Distinctiveness Conflict Risk	The text is boilerplate template ("Agent skill for X - invoke with $X") that would apply identically to any skill, giving high overlap risk; only the embedded slug lends mild distinctiveness, so it stays at 2 rather than 3.	2 / 5
	Total	7 / 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-test-long-runner/SKILL.md
Commit: fa13ee4

Reviewed: about 8 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.