ask

Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, or Cursor via `omc ask`, with artifact capture and no raw CLI assembly

Quality

73%

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 ./skills/ask/SKILL.md

Quality

Content

86%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 strong, highly actionable single-purpose skill: the execution path is unambiguous, provider verification is included, and outputs are concretely specified. Its only real flaws are minor — a stray template placeholder line and slight section-ordering noise.

Suggestions

Remove the dangling "Task: {{ARGUMENTS}}" line at the end of the Artifacts section, which reads as a leftover template placeholder.

Reorder so the Requirements/verification section appears before Routing, making the natural sequence (verify → route → artifact) explicit.

Trim the Antigravity platform note to the essential: which platforms are supported and that Windows users should use `omc ask gemini`.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — the routing rule, version checks, and artifact path each earn their tokens — but the dangling "Task: {{ARGUMENTS}}" line and the "Process-first" framing add nothing, and the Antigravity paragraph could be tightened slightly.	4 / 5
Actionability	Fully executable throughout: `omc ask {{ARGUMENTS}}` as the required path, five concrete invocation examples, per-provider verification commands, and the exact artifact path `.omc/artifacts/ask/<provider>-<slug>-<timestamp>.md`. Copy-paste ready with the common cases covered.	5 / 5
Workflow Clarity	The single action is unambiguous with an explicit do-not ("Do NOT manually construct raw provider CLI commands") and verification steps (`--version` checks), but the stray "Task: {{ARGUMENTS}}" line and Requirements being listed after Routing introduce minor sequence noise.	4 / 5
Progressive Disclosure	No bundle files exist and none are needed for a skill this size; the four well-organized sections (Usage, Routing, Requirements, Artifacts) keep all content appropriately inline with easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

61%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 clearly communicates what the skill does and names its providers, but it is written in process/design language rather than user-facing trigger terms, and it completely lacks a "when to use this" clause. Adding explicit trigger guidance would substantially improve it.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants a second opinion, wants to ask/delegate to another AI advisor (Claude, Codex, Gemini, Antigravity, Grok, or Cursor), or mentions `omc ask`".

Rewrite "Process-first" and "no raw CLI assembly" as concrete capability verbs, e.g. "Routes a prompt to the selected advisor CLI via `omc ask`, runs it, and saves the output as a markdown artifact".

Include natural synonyms such as "second opinion", "cross-model review", or "another AI's take" that a user would actually say when they need this skill.

Dimension	Reasoning	Score
Specificity	Names the domain (advisor routing) and a couple of concrete behaviors ("artifact capture", routing "via `omc ask`"), but phrases like "process-first" and "no raw CLI assembly" are design jargon rather than an enumeration of specific capabilities, so coverage is not comprehensive.	3 / 5
Completeness	The "what" is clear (route a prompt through an advisor CLI via `omc ask`, persist the result), but the "when" is entirely absent — there is no "Use when…" clause or equivalent trigger guidance, which caps completeness at 3.	3 / 5
Trigger Term Quality	Explicitly names all six providers ("Claude, Codex, Gemini, Antigravity, Grok, or Cursor") — natural terms a user would say when wanting this skill — but misses common variations like "second opinion", "cross-model", or "another AI".	4 / 5
Distinctiveness Conflict Risk	The provider-routing niche via `omc ask` is fairly distinct, but mentioning six generic provider names creates minor overlap risk with provider-specific skills since no trigger context separates it.	4 / 5
	Total	14 / 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: Yeachan-Heo/oh-my-claudecode
Path: skills/ask/SKILL.md
Commit: dc7ba1d

Reviewed: 3 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.