demo-skill

A tiny skill used by the skill isolation example.

Quality

26%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

41%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 a deliberately minimal test fixture: perfectly token-efficient and appropriately self-contained, but it contains no actionable guidance, no workflow, and no structure — it states what the text is for without instructing anything. As a real skill it would leave Claude with nothing to execute.

Suggestions

Add a concrete instruction or check the skill is supposed to perform (e.g. 'Grep the coordinator's system prompt for this body text; report a leak if any line matches'), replacing the purely descriptive prose.

Add at least one section header (e.g. '## Leak check procedure') so the minimal content is organized per the small-skill structure guideline.

If the skill is meant to be invoked rather than loaded as a fixture, add the specific trigger condition or command to run when a leak is detected.

Dimension	Reasoning	Score
Conciseness	The body is three short sentences with zero padding and no explanation of concepts Claude already knows — 'This is a minimal skill' plus a single conditional statement about leak detection. Every token is minimal, matching the anchor 'Lean and efficient; assumes Claude's competence; every token earns its place'.	5 / 5
Actionability	The body provides no concrete guidance whatsoever — no commands, no code, no steps; it only describes what the text is for ('If this body shows up in the coordinator's system prompt, it indicates a skill state leak'). This matches anchor 1 'Entirely vague or abstract; no concrete code or commands; only describes rather than instructs'.	1 / 5
Workflow Clarity	No steps or sequence of any kind are present, matching anchor 1 'Steps missing or incoherent; no sequence'. The simple-skill exception (score 5 for a single unambiguous action) does not apply because the body states no action at all, and there is no validation concern since no operation is described.	1 / 5
Progressive Disclosure	The skill is under 50 lines, self-contained, and has no bundle files (no references/, scripts/, or assets/ exist), so nothing needs external placement — matching the guideline for small skills. It scores 4 rather than 5 because there are no section headers at all, leaving a minor organization gap against the 'well-organized sections' bar.	4 / 5
	Total	11 / 20 Passed

Description

12%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 a placeholder meta-label rather than a functional skill description: it names no capabilities, no user-facing triggers, and no use conditions. It would never be selected by a user's request because nothing in it maps to anything a user would say. It needs a concrete capability statement and an explicit 'Use when...' clause.

Suggestions

Replace the meta-description with a concrete capability statement, e.g. 'Detects skill state leaks across agents by checking whether a skill body appears in the coordinator's system prompt.'

Add an explicit trigger clause such as 'Use when testing skill isolation, debugging agent state leaks, or verifying skill body confinement across agents.'

Include natural trigger keywords users would actually say (skill isolation, state leak, system prompt contamination) so the skill is discoverable and distinguishable from generic debugging skills.

Dimension	Reasoning	Score
Specificity	The description 'A tiny skill used by the skill isolation example' names no concrete actions or even a functional domain — pure abstract language matching the anchor 'Entirely vague; no concrete actions; pure abstract language'. It cannot score 2 because it doesn't even minimally name a domain like 'Processes PDF files' does.	1 / 5
Completeness	There is a vague 'what' ('a tiny skill used by the skill isolation example') and no 'when' guidance at all, matching anchor 2 'Has a vague what and no when'. Not 3 because even the 'what' describes the artifact's role rather than any capability, and the missing-'Use when' rule would cap it at 3 regardless.	2 / 5
Trigger Term Quality	There are no natural keywords or phrases a user would say when needing this skill; the text contains only meta-commentary about the skill's role in an example. This matches the anchor 'No natural keywords; only technical jargon or entirely generic language'.	1 / 5
Distinctiveness Conflict Risk	The description has no distinct triggers and no capability statement, giving it no niche; it sits between anchor 1 ('entirely generic; would conflict with virtually any skill') and anchor 2 ('very broad; high overlap risk'). It is not 1 because it makes no broad domain claim (like 'code and documents') that would actively collide with other skills — it is merely contentless.	2 / 5
	Total	6 / 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: trpc-group/trpc-agent-go
Path: examples/skillisolation/skills/demo-skill/SKILL.md
Commit: 9bb1c42

Reviewed: 5 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.