hello

Greet the user when they explicitly try the hello-codewhale example.

Quality

83%

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

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 content is an exemplary compact, single-purpose skill: concise, fully actionable, unambiguous in its single step, and appropriately self-contained with no need for progressive disclosure. Nothing is padded or missing for what the skill does.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: a single instruction plus constraints with no padding or explanation of concepts Claude already knows, matching the anchor for every token earning its place.	5 / 5
Actionability	It gives fully executable guidance for an instruction-only skill — the exact required text `hello-codewhale:hello` and explicit output constraints — which per the rubric's instruction-only note is not penalized for lacking code; it is unambiguous about what to produce.	5 / 5
Workflow Clarity	This is a simple single-action skill under 50 lines with no destructive or batch operations, so the simple-skill exception applies and the single action is unambiguous, satisfying the 5 anchor.	5 / 5
Progressive Disclosure	At under 50 lines with no need for external references (no references/scripts/assets bundles present), the content is self-contained and well-organized into instruction plus constraints, meeting the anchor for compact skills that need no file splitting.	5 / 5
	Total	20 / 20 Passed

Description

66%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 cleanly states what the skill does and when to use it with a distinct, low-conflict trigger, though its action list and keyword coverage are thin. It is a solid, concise description for a narrow example skill rather than a comprehensive one.

Suggestions

Broaden trigger-term coverage by adding natural phrasings a user might actually say (e.g., "Use when the user invokes the hello-codewhale example or asks for a sample greeting").

Make the "what" slightly more concrete by noting the greeting form expected (e.g., one short localized greeting), moving completeness toward a 5.

Dimension	Reasoning	Score
Specificity	Names the domain (greeting) and one concrete action ("Greet the user"), matching the anchor for 1-2 concrete actions without being comprehensive; it is not as multi-action as a 4 or as abstract as a 1.	3 / 5
Completeness	Answers both what ("Greet the user") and when ("when they explicitly try the hello-codewhale example"), but the "what" is terse and lacks a richer trigger list, so it sits at 4 rather than a fully explicit 5 and well above a 3 lacking a clear when.	4 / 5
Trigger Term Quality	Includes the relevant trigger phrase "when they explicitly try the hello-codewhale example", but offers only that single niche term with no common variations or synonyms, fitting the anchor for partial keyword coverage.	3 / 5
Distinctiveness Conflict Risk	The trigger "hello-codewhale example" is a highly specific niche phrase with minimal overlap risk against any other skill, matching the anchor for a clear niche with distinct triggers.	5 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Hmbown/Codewhale
Path: docs/examples/plugins/hello-codewhale/skills/hello/SKILL.md
Commit: 21282f1

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.