CtrlK
BlogDocsLog inGet started
Tessl Logo

greeter

A friendly greeter skill

76

2.17x
Quality

64%

Does it follow best practices?

Impact

100%

2.17x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/cli/src/commands/extensions/examples/skills/skills/greeter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%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 minimal, fully-actionable instruction for a trivial skill: a clear trigger and an exact reply, with no padding and no unnecessary references. It appropriately matches the simple-skill exceptions in the rubric.

DimensionReasoningScore

Conciseness

Two lean lines assume Claude's competence and contain only the trigger condition and exact reply, matching 'Lean and efficient; assumes Claude's competence; every token earns its place'. It is not a 4 because there is no over-explanation to trim.

5 / 5

Actionability

It gives an exact copy-paste reply ("Greetings from the skills-example extension! 👋") with a concrete trigger, matching 'Fully executable; copy-paste ready'. It is not a 4 because there are no gaps in the instruction.

5 / 5

Workflow Clarity

This is a simple single-purpose skill whose single action is unambiguous (trigger -> fixed reply), so the simple-skill exception applies and it scores 5; no destructive or batch operation is present. It is not a 4 because the action is fully unambiguous.

5 / 5

Progressive Disclosure

The skill is under 50 lines, single-task, with no need for external references, so well-organized inline content suffices for a 5 per the rubric's simple-skill guidance; no nested references exist. It is not a 4 because nothing is misplaced or buried.

5 / 5

Total

20

/

20

Passed

Description

28%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 single vague label with no concrete actions, no explicit trigger guidance, and no 'Use when...' clause, capping completeness and specificity low. It names a real niche but does not differentiate it.

Suggestions

Add concrete actions, e.g. 'Replies with a friendly greeting when greeted' or list greeting variants.

Add an explicit 'Use when the user says hello, asks for a greeting, or wants a welcome message' clause to raise completeness and trigger quality.

Use third-person action voice ('Greets the user...') instead of the noun-phrase label to improve specificity.

DimensionReasoningScore

Specificity

"A friendly greeter skill" names the domain (greeter) but states no concrete actions, matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 1 because it does name a concrete domain, and not a 3 because it lists no actions.

2 / 5

Completeness

It gives a vague 'what' (a greeter skill) with no 'when' clause, matching 'Has a vague what and no when'; the missing 'Use when...' guidance caps completeness at 3 and this falls below that. It is not a 3 because the 'what' itself is vague.

2 / 5

Trigger Term Quality

The only keyword is 'greeter'/'greeting'; the natural phrases a user would actually say ('hello', 'say hi') are absent, fitting 'One or two generic keywords; missing the natural phrases users say'. It is not a 3 since coverage is thinner than 'Works with PDF files'.

2 / 5

Distinctiveness Conflict Risk

Greeting is a somewhat specific niche with low overlap risk, but the description is so generic it could still overlap with general conversational skills, fitting 'Somewhat specific but could still overlap'. It is not a 4 because no distinct trigger phrases are given.

3 / 5

Total

9

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
google-gemini/gemini-cli
Reviewed

Table of Contents

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.