CtrlK
BlogDocsLog inGet started
Tessl Logo

portable-skill

A stable standalone Codex fixture Skill.

41

Quality

40%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tests/fixtures/portability/codex-mini/skills/portable-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

58%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 is appropriately concise and well-structured for a simple skill, but it provides only high-level direction with no concrete, executable guidance or defined steps. It tells Claude what to do in the abstract without showing how.

Suggestions

Add a concrete example of the inspection, such as a specific command or the exact file(s)/tools to use, so the guidance is executable rather than a hint.

Spell out the inspection steps explicitly (what to look at, in what order) so the single-task workflow is unambiguous rather than implied.

Clarify what 'inspect' should produce (e.g., a summary, a list of findings) so the action has a defined outcome.

DimensionReasoningScore

Conciseness

The body is a single lean line with no padding or over-explanation of concepts Claude already knows, so every token earns its place.

5 / 5

Actionability

'Use QwenPaw's ordinary file tools to inspect the current project' is a high-level hint with no concrete commands, code, or specific steps to execute.

2 / 5

Workflow Clarity

The single vague instruction ('inspect the current project') gives only a rough direction with no defined steps or checkpoints; there are no concrete sub-steps to follow.

2 / 5

Progressive Disclosure

This is a simple skill under 50 lines with no bundle files; the single well-organized line needs no external references or further structure.

5 / 5

Total

14

/

20

Passed

Description

21%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 identifies the skill's domain but gives no concrete actions or trigger guidance, relying on meta/test jargon rather than natural user phrasing. It answers neither 'what does it do' nor 'when should Claude use it' in a usable way.

Suggestions

Replace meta language ('stable standalone Codex fixture Skill') with concrete verbs describing what the skill actually does (e.g., 'Inspects...', 'Analyzes...').

Add an explicit trigger clause: 'Use when ...' naming the natural phrases a user would say when they need this skill.

Include synonyms or file/keyword variations users are likely to mention so the skill is discoverable and distinct from neighboring skills.

DimensionReasoningScore

Specificity

The phrase 'A stable standalone Codex fixture Skill' names the domain but lists no concrete actions, matching the anchor where actions are minimal or generic.

2 / 5

Completeness

It offers only a vague 'what' (a fixture skill) and entirely lacks a 'when'/'Use when...' trigger clause, matching the anchor for a vague what with no when.

2 / 5

Trigger Term Quality

It uses technical/meta jargon ('Codex fixture Skill') with no natural keywords a user would actually say, matching the anchor for only technical jargon with no natural triggers.

1 / 5

Distinctiveness Conflict Risk

'Codex fixture Skill' is somewhat specific but the generic 'stable standalone ... Skill' framing still risks overlap with similar fixture/test skills.

3 / 5

Total

8

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agentscope-ai/QwenPaw
Reviewed

Table of Contents

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.