probe-skill

Verify that the compiled Companion can load a skill and execute its packaged shell resource.

Quality

67%

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 ./experiments/pi-bun/skills/probe-skill/SKILL.md

Quality

Content

88%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 extremely lean and gives a concrete executable command with a clear single-step workflow, appropriate for a small probe skill. The only gaps are a relative-path qualifier on the command and the absence of any section structure.

Dimension	Reasoning	Score
Conciseness	Three lean lines with no padding or explanation of concepts Claude already knows; every token earns its place, matching the lean-and-efficient anchor.	5 / 5
Actionability	Provides a concrete executable command (`sh scripts/check.sh`) and a clear instruction to report output, but the "relative to this skill's base directory" qualifier leaves a minor gap versus a fully copy-paste-ready absolute invocation.	4 / 5
Workflow Clarity	This is a simple single-purpose skill whose single action (run check.sh, report output) is unambiguous and non-destructive, so the simple-skill exception justifies a 5.	5 / 5
Progressive Disclosure	Under 50 lines with a single one-level reference to a real bundle file (scripts/check.sh, verified present), but there are no section headers to organize the content, keeping it just below 5.	4 / 5
	Total	18 / 20 Passed

Description

46%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 states a clear purpose with two concrete actions but omits any explicit "Use when..." trigger guidance and relies on technical jargon rather than natural user keywords. It is fairly distinct but would benefit from natural trigger phrasing.

Suggestions

Add an explicit "Use when..." clause naming the situations that should trigger this skill, to lift completeness above 3.

Replace jargon ("compiled Companion", "packaged shell resource") with natural terms a user would actually say when they need this skill.

List a couple more concrete actions or expected outcomes to broaden coverage toward the specificity anchor.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("load a skill" and "execute its packaged shell resource"), but coverage is not comprehensive, matching the 1-2 concrete actions anchor; not a 4 because no additional specific actions are listed.	3 / 5
Completeness	There is a clear "what" (verify the Companion loads a skill and executes its shell resource) but no "Use when..." clause, so per the missing-trigger guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Phrases like "compiled Companion" and "packaged shell resource" are technical jargon; a user would not naturally say these, missing the natural trigger phrases users actually say.	2 / 5
Distinctiveness Conflict Risk	The scope (compiled Companion probe, packaged shell resource) is a distinct niche with low conflict risk; not a 5 because the wording lacks explicit distinct trigger phrases.	4 / 5
	Total	12 / 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: The-Vibe-Company/companion
Path: experiments/pi-bun/skills/probe-skill/SKILL.md
Commit: c950f6f

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.