pirate-skill

Speak like a pirate.

Quality

66%

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 ./packages/sdk/test-data/skills/pirate-skill/SKILL.md

Quality

Content

92%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 concise and gives a clear, actionable in-character directive, and as a trivial single-purpose skill it satisfies the workflow and structure exceptions. The only gap is the lack of an example pirate-speak response to fully anchor the expected output style.

Suggestions

Add a one-line example of a desired pirate-speak response to make the expected output style copy-paste concrete and lift actionability to 5.

Dimension	Reasoning	Score
Conciseness	The body is a single lean sentence with zero padding and no explanation of concepts Claude already knows, matching 'Lean and efficient; assumes Claude's competence; every token earns its place'. It is not below 5 because nothing is redundant or over-explained.	5 / 5
Actionability	"Respond to everything in pirate speak. Always mention \"Arrr\"." gives concrete, specific directives an instruction-only skill can execute, matching 'Mostly executable guidance; concrete ... with minor gaps'. It is not a 5 because no example output shows what a pirate-speak response should look like, and not a 3 because the guidance is concrete rather than pseudocode or vague.	4 / 5
Workflow Clarity	This is a simple single-purpose skill whose single action (reply in pirate speak) is unambiguous, so per the simple-skill exception it can score 5. It is not below 5 because there is no multi-step or risky process requiring validation checkpoints.	5 / 5
Progressive Disclosure	Under 50 lines with no need for external references, the flat single sentence is appropriately organized for its scope, so the simple-skill exception applies. It is not below 5 because there is no content that belongs in a separate file and no nested references to fault.	5 / 5
	Total	19 / 20 Passed

Description

41%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 lean and on-topic but stops at naming the persona without any 'when to use' guidance or richer trigger terms, which caps completeness and limits trigger-term quality. It is distinct as a niche but underspecified for discovery.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to talk like a pirate, wants pirate-themed responses, or requests a pirate persona.'

Broaden trigger terms to include natural user phrasings like 'talk like a pirate', 'pirate mode', or 'pirate speak'.

Optionally add a second concrete capability (e.g. 'Pirate-translates text and keeps responses in-character') to raise specificity above a single action.

Dimension	Reasoning	Score
Specificity	"Speak like a pirate." names the domain and a single action but offers no breadth of capabilities, matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because it does not list even 1-2 distinct concrete actions, and not a 1 because the domain is explicitly named.	2 / 5
Completeness	It gives a clear 'what' (speak like a pirate) but no 'Use when...' clause or equivalent trigger guidance, so per the rubric cap it cannot exceed 3. It is not a 4 because the 'when' is entirely missing rather than weakly implied.	3 / 5
Trigger Term Quality	The only natural keyword is "pirate"; common user phrasings like 'talk like a pirate' or 'pirate mode' are absent, so coverage is thin and missing the phrases users would actually say. It is above 1 because 'pirate' is a natural term rather than jargon, but below 3 because no synonyms or variations are present.	2 / 5
Distinctiveness Conflict Risk	"Speak like a pirate." occupies a clear, narrow niche with distinct triggers and low overlap risk with other skills. It is not a 5 because the brevity leaves the trigger phrasing underspecified, and not a 3 because the pirate persona is unmistakably distinct.	4 / 5
	Total	11 / 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/sdk/test-data/skills/pirate-skill/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.