agent-test-long-runner

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

0.98x

Quality

15%

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

Quality

Content

30%

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-organized and appropriately short for a self-contained skill, but it is almost entirely generic guidance with no concrete, executable instructions or a real workflow. It reads as a template placeholder rather than operational guidance.

Suggestions

Replace abstract capability bullets with concrete, actionable instructions (specific commands, tools, or step-by-step procedures) so Claude knows exactly what to do.

Provide a real sequenced workflow with validation checkpoints for the long-running tasks the skill claims to handle, rather than behavioral platitudes.

Remove the duplicate spurious YAML frontmatter block in the body (the second 'name/description/category' block) and the filler closing line to tighten token usage.

Dimension	Reasoning	Score
Conciseness	The body is brief and does not explain concepts Claude already knows, but it is padded with generic platitudes ("Take Your Time: Don't rush - quality over speed", "Remember: You have plenty of time to do thorough, high-quality work!") that could be tightened; it is not a 1 because it avoids concept re-explanation, and not a 3 because the filler does not earn its place.	2 / 3
Actionability	There is no executable code, no commands, and no concrete examples; items like "Complex Analysis: Deep dive into codebases" and "Document Everything" describe rather than instruct, matching the score-1 anchor. The instruction-only guidance is not actionable, so the absence-of-code exemption does not apply.	1 / 3
Workflow Clarity	The numbered "Instructions" list (Take Your Time, Be Thorough, Communicate Progress) is a set of behavioral attitudes, not a sequenced multi-step workflow, and there are no validation checkpoints for the long-running tasks it claims to handle; it does not reach a 2 because there is no real task sequence.	1 / 3
Progressive Disclosure	The skill is under 50 lines, self-contained with no external bundle files, and organized into clearly headed sections (Capabilities, Instructions, Output Format, Example Use Cases) with no nested references, satisfying the simple-skill allowance for a score of 3.	3 / 3
	Total	7 / 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.

This is a generic placeholder description that fails to convey any concrete capability, trigger, or use-case guidance. It reads as an auto-generated wrapper rather than a meaningful skill description.

Suggestions

Replace the description with concrete actions the skill performs (e.g., 'Runs long-duration test suites, monitors execution, and aggregates pass/fail results').

Add an explicit 'Use when...' trigger clause with natural terms a user would actually say (e.g., 'Use when running test jobs expected to take 30+ minutes or when monitoring long test suites').

Write in third person and remove the internal invoke-syntax ("$agent-test-long-runner") which is not a natural user trigger term.

Dimension	Reasoning	Score
Specificity	The description states only "Agent skill for test-long-runner - invoke with $agent-test-long-runner", naming no concrete actions or capabilities whatsoever; it is vague and abstract rather than listing specific actions like the score-1 anchor 'Helps with documents'.	1 / 3
Completeness	It answers neither 'what does this do' (no capability described beyond 'agent skill') nor 'when should Claude use it' (no 'Use when...' clause or trigger); both halves are missing, the weakest anchor. It is not a 2 because there is no concrete 'what' to speak of.	1 / 3
Trigger Term Quality	The only terms are internal jargon ("test-long-runner", "$agent-test-long-runner") that a user would never naturally say when they need this skill; there are no natural user-facing keywords, matching the score-1 anchor for technical jargon / no natural keywords.	1 / 3
Distinctiveness Conflict Risk	The text is a generic auto-generated placeholder ("Agent skill for test-long-runner") with no description of a distinct niche and no distinct triggers, so it would conflict with other generic agent skills; it does not establish the clear niche of the score-2/3 anchors.	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/ruflo
Path: .agents/skills/agent-test-long-runner/SKILL.md
Commit: 26c35b5

Reviewed: about 5 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.