demo-skill

A tiny skill used by the skill isolation example.

Quality

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./examples/skillisolation/skills/demo-skill/SKILL.md

Quality

Content

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

This is not a functional skill — it is a test sentinel designed to detect skill state leaks across agents. It contains zero actionable content, no code, no workflow, and no structure. It fails on every dimension of the rubric.

Suggestions

If this is intended as a real skill, add concrete instructions or executable code for the task it should teach.

Add a clear workflow or at minimum a single unambiguous action step.

If this is purely a test fixture, it should not be evaluated as a skill — consider excluding it from quality assessments.

Dimension	Reasoning	Score
Conciseness	The content provides no actionable information whatsoever. It is essentially a test fixture/sentinel value rather than a real skill, so every token is wasted from a skill-teaching perspective.	1 / 3
Actionability	There are no concrete instructions, code, commands, or guidance of any kind. The content describes its own purpose as a leak-detection mechanism rather than instructing Claude on how to perform a task.	1 / 3
Workflow Clarity	No workflow, steps, or process are described. There is nothing for Claude to follow or execute.	1 / 3
Progressive Disclosure	No structure, sections, or references exist. The content is two sentences with no organization or navigation to supporting materials.	1 / 3
	Total	4 / 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 description is essentially a placeholder or meta-comment about the skill's origin rather than a functional description. It fails on every dimension: it specifies no actions, includes no user-facing trigger terms, answers neither 'what' nor 'when', and provides no distinguishing characteristics.

Suggestions

Replace the meta-comment with a concrete description of what the skill actually does, listing specific actions (e.g., 'Demonstrates X by performing Y and Z').

Add an explicit 'Use when...' clause with natural trigger terms that describe when Claude should select this skill.

Include domain-specific keywords that distinguish this skill from others and match terms users would naturally use in their requests.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. 'A tiny skill used by the skill isolation example' is entirely abstract and says nothing about what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only references its role as a test artifact, providing no functional or trigger information.	1 / 3
Trigger Term Quality	There are no natural keywords a user would say. 'Skill isolation example' is internal/meta jargon, not something a user would naturally request.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it provides no distinguishing characteristics. It could conflict with any other skill since there are no domain-specific or action-specific terms.	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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: trpc-group/trpc-agent-go
Commit: fc01b4b

Reviewed: 3 days 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.