greeter

A friendly greeter skill

2.17x

Quality

64%

Does it follow best practices?

Impact

100%

2.17x

Average score across 3 eval scenarios

Securityby

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

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 an exemplary minimal instruction: an exact trigger, an exact response, and no wasted tokens. It fully compensates for the vague description by carrying the trigger and behavior specification itself. Its only soft spot is the leak of implementation provenance ('skills-example extension') in the user-facing reply, which is cosmetic rather than structural.

Dimension	Reasoning	Score
Conciseness	The body is three lean lines with zero padding and no explanation of concepts Claude already knows — every token earns its place (anchor 5: 'Lean and efficient; assumes Claude's competence').	5 / 5
Actionability	It specifies an exact trigger condition ('When the user says "hello" or asks for a greeting') and an exact verbatim reply string — fully executable, copy-paste-ready instruction for the single common case (anchor 5). As an instruction-only skill with concrete, specific guidance, absence of code is not penalized.	5 / 5
Workflow Clarity	This is a simple single-purpose skill whose single action is completely unambiguous: condition → exact response. Per the simple-skills scoring note, workflow clarity can score 5 without an explicit multi-step workflow, and no destructive or batch operations are involved.	5 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references, and nothing in the body belongs in a separate file; content is appropriately all-inline. Per the scoring notes, progressive disclosure can score 5 for such skills.	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 domain label rather than a capability description: it names no concrete actions, includes no trigger guidance, and offers no natural keywords beyond the skill's own name. It resembles the bad_overall_examples ('Helps with documents') in structure. The content body ironically contains the material (trigger: 'hello' or 'asks for a greeting'; action: exact reply text) that a good description would surface.

Suggestions

State concrete capabilities in third person, e.g. 'Replies with a friendly greeting message when the user says hello or asks to be greeted.'

Add an explicit trigger clause: 'Use when the user says "hello", asks for a greeting, or wants a welcome message.'

Include natural keyword variations users would say (greeting, say hi, hello, welcome) to improve trigger matching and distinctiveness.

Dimension	Reasoning	Score
Specificity	"A friendly greeter skill" names the domain but provides no concrete action verbs, matching anchor 2 ('Names the domain but actions are minimal or generic'). It falls short of anchor 3 because no specific capability like 'replies with a greeting' is actually stated.	2 / 5
Completeness	The 'what' is only vaguely implied (a greeter skill presumably greets) and the 'when' is completely missing — anchor 2 ('Has a vague what and no when'). The missing 'Use when...' clause also caps completeness at 3 per judging guidelines, and this is below even that.	2 / 5
Trigger Term Quality	The only keywords are 'friendly' and 'greeter'; natural phrases a user would actually say ('say hello', 'greet me', 'welcome message') are entirely absent. This matches anchor 2 ('One or two generic keywords; missing the natural phrases users say') rather than anchor 3, which requires some relevant keywords beyond the bare domain name.	2 / 5
Distinctiveness Conflict Risk	Greeting is a fairly distinct niche, so it does not conflict with virtually any skill (rules out 1-2), but the extreme vagueness leaves overlap risk with general conversational or social-interaction skills. Anchor 3 ('Somewhat specific but could still overlap with similar skills') fits best; it lacks the explicit trigger scoping needed for anchor 4.	3 / 5
	Total	9 / 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: google-gemini/gemini-cli
Path: packages/cli/src/commands/extensions/examples/skills/skills/greeter/SKILL.md
Commit: 361b0bb

Reviewed: 6 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.