Tessl • The management layer for AI agent skills

The content is a model of minimal, fully actionable instruction: one sentence that specifies the exact response token and the exclusion constraint, leaving no room for misinterpretation. As a simple single-task skill under 50 lines with no bundle files, it satisfies every content dimension at the top anchor. Nothing needs to change.

Dimension	Reasoning	Score
Conciseness	The body is a single sentence — "reply with exactly QA-SAMPLE-SKILL-OK and no other text" — with zero padding and no explanation of concepts Claude already knows, matching 'Lean and efficient; every token earns its place'.	5 / 5
Actionability	The instruction specifies the exact literal output string and the constraint ('no other text'), which is fully executable, copy-paste-ready guidance with no ambiguity, matching the top anchor for an instruction-only skill.	5 / 5
Workflow Clarity	This is a simple single-purpose skill whose one action is completely unambiguous; per the rubric's simple-skill guideline, workflow clarity scores 5 when the single action is unambiguous, and no destructive or batch operations require validation checkpoints.	5 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references (none exist in the bundle), and inlines nothing that belongs in a separate file, so per the simple-skill guideline progressive disclosure scores 5.	5 / 5
	Total	20 / 20 Passed

Description

61%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 has an explicit, natural 'Use when' trigger clause built around the skill's own name, making it highly distinctive and conflict-free. However, it fails to describe any concrete capability — 'A QA sample skill' says what the skill is, not what it does — and the trigger coverage is a single term with no variations. It is functional but minimally informative.

Suggestions

State the concrete action in the description, e.g. 'Replies with a fixed QA token to verify skill invocation' instead of the vague 'A QA sample skill'.

Add natural trigger variations and synonyms (e.g. 'test the sample skill', 'verify skill-sample is loaded') so the description matches more than one phrasing a user might say.

Combine what and when in the pattern of the good examples: one sentence of concrete capability followed by an explicit 'Use when...' clause with concrete trigger phrases.

Dimension	Reasoning	Score
Specificity	"A QA sample skill" names the domain but states no concrete actions or capabilities, matching the anchor 'Names the domain but actions are minimal or generic'. It is above anchor 1 because it identifies a specific purpose rather than being pure abstraction, but below anchor 3 because no concrete actions are listed.	2 / 5
Completeness	Both elements are present: a what ("A QA sample skill") and an explicit when ("Use when the user asks to use skill-sample"), meeting anchor 4's 'Has both what and when'. It falls short of anchor 5 because the what is vague — it does not state what the skill actually does.	4 / 5
Trigger Term Quality	The trigger "when the user asks to use skill-sample" is a natural phrase a user would say, but it is a single term with no variations or synonyms, fitting 'Some relevant keywords but missing common variations'. It is not score 4 since there is no broader keyword coverage, and not score 2 since the keyword is specific rather than generic.	3 / 5
Distinctiveness Conflict Risk	The only trigger is the skill's own name ("skill-sample"), giving it a clear niche with a distinct trigger and minimal conflict risk with any other skill, which matches anchor 5 exactly.	5 / 5
	Total	14 / 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: CherryHQ/cherry-studio
Path: tests/e2e/regression/fixtures/skill-sample/SKILL.md
Revision: 1dad629

Reviewed: 9 days ago

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.

skill-sample

Table of Contents

Is this your skill?