ask

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

Quality

60%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/ask/SKILL.md

Quality

Discovery

32%

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 uses domain-specific jargon ('process-first advisor routing', 'no raw CLI assembly') that obscures rather than clarifies the skill's purpose. It lacks an explicit 'Use when...' clause, making it difficult for Claude to know when to select this skill. The mention of `omc ask` and specific AI tools provides some distinctiveness but is insufficient to compensate for the overall vagueness.

Suggestions

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user wants to route questions to Claude, Codex, or Gemini via the omc CLI, or mentions `omc ask`.'

Replace jargon like 'process-first advisor routing' and 'no raw CLI assembly' with concrete actions, e.g., 'Routes questions to AI advisors (Claude, Codex, Gemini) using `omc ask`, captures output artifacts, and handles CLI command construction automatically.'

Add common user-facing trigger terms such as 'ask AI', 'query advisor', 'omc', or 'multi-model' to improve keyword coverage.

Dimension	Reasoning	Score
Specificity	It names a specific command (`omc ask`) and mentions 'artifact capture' and 'advisor routing', but the concrete actions are not well-enumerated. 'Process-first advisor routing' and 'no raw CLI assembly' are somewhat abstract and jargon-heavy rather than listing clear user-facing capabilities.	2 / 3
Completeness	It partially addresses 'what' (advisor routing via omc ask with artifact capture) but has no explicit 'when' clause or trigger guidance. The lack of a 'Use when...' clause caps this at 2 per the rubric, and the 'what' itself is vague enough to warrant a score of 1.	1 / 3
Trigger Term Quality	Includes some relevant keywords like 'Claude', 'Codex', 'Gemini', and 'omc ask', which users might naturally reference. However, it uses technical jargon ('process-first advisor routing', 'artifact capture', 'raw CLI assembly') that users are unlikely to say naturally, and misses common variations of what users might ask for.	2 / 3
Distinctiveness Conflict Risk	The mention of `omc ask` and specific AI advisors (Claude, Codex, Gemini) provides some distinctiveness, but 'advisor routing' is vague enough that it could overlap with other skills involving AI tool orchestration or CLI helpers.	2 / 3
	Total	7 / 12 Passed

Implementation

87%

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

This is a well-crafted, concise skill that clearly communicates its core constraint (always use `omc ask`, never raw CLI commands) with actionable examples. The routing safety boundary is strongly emphasized. The only weakness is the lack of an explicit sequential workflow tying together verification, execution, and artifact validation steps.

Suggestions

Consider adding a brief numbered workflow sequence: 1) verify provider CLI, 2) run `omc ask`, 3) confirm artifact was written to the expected path — this would make the process more explicit and add a validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The content is lean and efficient. It doesn't explain what Claude, Codex, or Gemini are, nor does it over-explain CLI concepts. Every section serves a clear purpose: usage, routing constraint, requirements, and artifact output location.	3 / 3
Actionability	Provides exact executable commands for usage, verification, and routing. The examples are copy-paste ready, the routing constraint is explicit with a concrete command template, and the artifact output path is precisely specified.	3 / 3
Workflow Clarity	The skill is relatively simple (single command routing), but the steps aren't explicitly sequenced. There's no clear workflow like: 1) verify CLI availability, 2) run the command, 3) check artifact output. The verification step exists but isn't integrated into a sequential flow, and there's no validation of the output artifact.	2 / 3
Progressive Disclosure	For a simple, single-purpose skill under 50 lines with no need for external references, the content is well-organized into clear sections (Usage, Routing, Requirements, Artifacts) that are easy to scan and navigate.	3 / 3
	Total	11 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: Yeachan-Heo/oh-my-claudecode
Commit: 3e94567

Reviewed: 1 day 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.