help

Route a "how do I use Codewhale" question to the installed help, config, and doctor surfaces instead of reciting a manual from memory. Explicit-only.

Quality

92%

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%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplary router skill body: concise, fully actionable with exact commands and doc paths, a clearly sequenced routing workflow with verification-style bounds, and well-organized sections appropriate for a sub-50-line single-purpose skill with no bundle files.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what Codewhale or slash commands are, and every line earns its place ('This skill is a router, not a manual ... it never restates documentation'), matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	It gives fully concrete, copy-ready guidance: exact slash commands ('/help', '/skills inspect', '/skill <name>'), 'codewhale-tui doctor', the tool 'read_file', and specific doc paths ('docs/CONFIGURATION.md', 'docs/PROVIDERS.md'), matching the 'fully executable commands; copy-paste ready' anchor even though this is an instruction-only skill.	3 / 3
Workflow Clarity	The routing table is an explicit ordered sequence ('Answer from the surface that owns the fact, in this order: 1..5'), and the Bounds section supplies verification checkpoints ('the surface wins', 'Prefer its output over inference', 'If nothing local answers it, say so and stop'), matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	No bundle files exist and the body is under 50 lines, so per the rubric's simple-skills note a well-organized set of sections (Invocation, When to use, Non-goals, Routing table, Working in a checkout, Bounds) suffices for a top score; the only referenced paths are docs inside a Codewhale checkout, not nested skill references.	3 / 3
	Total	12 / 12 Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states a concrete routing action to named surfaces with an explicit trigger and low conflict risk. Its main gap is trigger-term breadth: it captures the headline 'how do I use Codewhale' phrasing but not the everyday variations users would also say.

Suggestions

Broaden the trigger terms to cover natural variations, e.g. 'Use when the user asks what a command does, where a setting or keybinding lives, or how to use Codewhale itself.'

Consider mirroring a couple of the concrete surfaces (command, setting, keybinding) into the description so the trigger set matches what the body routes on.

Dimension	Reasoning	Score
Specificity	The description names concrete routing targets — 'the installed help, config, and doctor surfaces' — and an explicit action ('Route a ... question'), matching the anchor that lists multiple specific concrete actions rather than vague language.	3 / 3
Completeness	It answers both what ('Route ... to the installed help, config, and doctor surfaces') and when (a 'how do I use Codewhale' question), and the embedded trigger phrase counts as equivalent explicit trigger guidance, matching the 'clearly answers both what AND when' anchor.	3 / 3
Trigger Term Quality	It includes a natural trigger phrase ('a "how do I use Codewhale" question') plus keywords (Codewhale, help, config, doctor), but coverage of how users actually phrase such queries is narrow — it omits common variations like 'what does this command do', 'where is this setting', or 'how do I change a keybinding' that the body later raises.	2 / 3
Distinctiveness Conflict Risk	It carves a clear, narrow niche — Codewhale self-usage routing, marked 'Explicit-only' — that is unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	11 / 12 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: crates/tui/assets/skills/help/SKILL.md
Commit: e1049cf

Reviewed: about 13 hours 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.