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', 'artifact capture') that obscures what the skill actually does for users. It lacks an explicit 'Use when...' clause, making it difficult for Claude to know when to select this skill. While it names specific tools (Claude, Codex, Gemini, omc ask), the core functionality remains unclear.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to ask a question to Claude, Codex, or Gemini via the omc CLI tool'

Replace jargon like 'process-first advisor routing' with concrete actions, e.g., 'Routes questions to AI advisors (Claude, Codex, Gemini) via the `omc ask` command, captures response artifacts, and avoids manual CLI assembly'

Include natural trigger terms users would say, such as 'ask AI', 'omc command', 'query model', or 'get AI response'

Dimension	Reasoning	Score
Specificity	Names a specific domain ('advisor routing') and mentions some actions ('artifact capture', 'no raw CLI assembly'), but the concrete capabilities are unclear. 'Process-first advisor routing' is jargon-heavy and doesn't list specific user-facing actions like 'routes questions to AI advisors' or 'captures output artifacts'.	2 / 3
Completeness	There is no explicit 'Use when...' clause or equivalent trigger guidance. The 'what' is partially addressed but vague, and the 'when' is entirely missing. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' further reduces it.	1 / 3
Trigger Term Quality	Includes some useful trigger terms like 'omc ask', 'Claude', 'Codex', 'Gemini', and 'CLI', but 'process-first advisor routing' and 'artifact capture' are not natural phrases a user would say. Missing common variations like 'ask AI', 'run command', or 'query advisor'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'omc ask' and specific AI tools (Claude, Codex, Gemini) provides some distinctiveness, but 'advisor routing' is vague enough to potentially overlap with other AI orchestration or CLI skills. The niche is somewhat identifiable but not sharply defined.	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 the critical constraint (always use `omc ask`, never raw CLI commands) with actionable examples. Its main weakness is the lack of an explicit sequential workflow with a verification step to confirm artifact creation succeeded. The safety boundary around not manually constructing CLI commands is a strong point.

Suggestions

Add an explicit numbered workflow: 1. Verify provider CLI is installed, 2. Run `omc ask`, 3. Confirm artifact was written (e.g., `ls .omc/artifacts/ask/` or check exit code).

Consider adding a brief note on error handling — what should happen if `omc ask` fails or the provider CLI is not authenticated.

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 both usage and verification. The routing section gives a concrete command template (`omc ask {{ARGUMENTS}}`) and explicitly forbids the wrong approach with clear rationale. Examples are copy-paste ready.	3 / 3
Workflow Clarity	The skill is relatively simple (single command routing), but the workflow is implicit rather than sequenced. There's no explicit step-by-step flow (e.g., 1. verify CLI availability, 2. run omc ask, 3. check artifact output). There's also no validation/verification step to confirm the artifact was written successfully, which matters for a persistence operation.	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). No monolithic walls of text or unnecessary nesting.	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: 679b418

Reviewed: 4 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.