demo-skill

A tiny skill used by the skill isolation example.

Quality

33%

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 maximally concise but contains no actionable instruction or workflow — it functions as a leak-detection canary rather than guidance for performing a task. Its only real strength is token efficiency.

Suggestions

If the skill is meant to do more than act as a canary, add a concrete step or command for detecting the leak (e.g., a check to run or a signal to look for).

Add a short section header (e.g., '## Purpose') so the flat body has clear structure and earns the progressive-disclosure top score.

State explicitly when the body appearing in the coordinator prompt should be reported and how, turning the note into an actionable workflow with a validation/reporting checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is two short sentences with no padding and no explanation of concepts Claude already knows, matching 'Lean and efficient; every token earns its place'. It is not a 4 because there are no instances of over-explanation to trim.	5 / 5
Actionability	"This is a minimal skill" and the leak-detection note describe a state rather than giving any executable guidance, code, or commands, matching 'Entirely vague or abstract; only describes rather than instructs'. It is not a 2 because there are not even high-level hints toward a concrete task.	1 / 5
Workflow Clarity	There is no sequence of steps and no validation checkpoint; the body is a single declarative diagnostic statement, matching 'Steps missing or incoherent; no sequence'. The simple-skill exception does not apply because no actionable single step is defined.	1 / 5
Progressive Disclosure	The 4-line body has no bundle files and needs no external references, with content appropriately placed for a body this small. It falls short of a 5 because the flat prose lacks section headers or clear organizational structure.	4 / 5
	Total	11 / 20 Passed

Description

25%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 as an example for skill isolation but provides no concrete capabilities, no natural trigger terms, and no usage guidance, making it unlikely to be selected for the right task. It reads as a label rather than a discovery description.

Suggestions

Replace the example-purpose framing with the concrete action the skill performs (e.g., 'Detects skill state leaks across agents by checking whether a body appears in the coordinator system prompt').

Add a 'Use when ...' trigger clause naming the natural phrases a user would say (e.g., 'Use when testing skill isolation or debugging cross-agent context leakage').

Include domain-specific keywords like 'skill isolation', 'context leak', and 'coordinator prompt' so the description is distinguishable from generic demo skills.

Dimension	Reasoning	Score
Specificity	The phrase "tiny skill used by the skill isolation example" names a domain (skill isolation) but states no concrete actions, matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 1 because a domain is named, and not a 3 because no concrete capabilities are enumerated.	2 / 5
Completeness	It gives a vague 'what' (a tiny example skill) and no 'when to use' trigger, matching 'Has a vague what and no when'. It is not a 1 because something is stated, and capped below 3 by the missing explicit 'Use when...' clause.	2 / 5
Trigger Term Quality	"skill isolation example" is meta-jargon a user would not naturally say when needing this skill, offering only one generic-ish keyword. It sits above the no-keyword anchor (1) but below the 'some relevant keywords' anchor (3) because the natural user-facing trigger phrases are entirely missing.	2 / 5
Distinctiveness Conflict Risk	"tiny skill used by the skill isolation example" is very broad and would overlap with any demo or test skill, matching 'Very broad; high overlap risk'. It is slightly more specific than the fully-generic anchor (1) but lacks the niche triggers needed for a 3.	2 / 5
	Total	8 / 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: 9f7e561

Reviewed: ~17 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.