ask

Ask Claude, Codex, or Gemini via local CLI and capture a reusable artifact

Quality

60%

Does it follow best practices?

Impact

Pending

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 provides a basic understanding of the skill's purpose but is too terse and lacks critical guidance for skill selection. It names specific AI models which helps with distinctiveness, but the absence of explicit trigger conditions and limited action specificity significantly weaken its utility for Claude's skill selection process.

Suggestions

Add a 'Use when...' clause specifying trigger scenarios like 'Use when the user wants to query Claude, Codex, or Gemini from the command line, compare model responses, or save AI outputs as reusable files.'

Expand the action list to be more specific about what 'capture a reusable artifact' means - e.g., 'save responses to files, compare outputs across models, batch query multiple LLMs'

Include additional natural trigger terms users might say: 'LLM', 'command line', 'terminal', 'API', 'model comparison', 'AI query'

Dimension	Reasoning	Score
Specificity	Names the domain (CLI interaction with AI models) and mentions two actions ('Ask' and 'capture a reusable artifact'), but lacks comprehensive detail about what specific operations are supported or what artifacts are produced.	2 / 3
Completeness	Describes what it does at a basic level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes specific model names (Claude, Codex, Gemini) and 'CLI' which users might say, but misses common variations like 'LLM', 'AI assistant', 'command line', 'terminal', or 'query'.	2 / 3
Distinctiveness Conflict Risk	The specific model names (Claude, Codex, Gemini) and 'local CLI' provide some distinctiveness, but 'artifact' is vague and could overlap with other skills that generate or capture outputs.	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 efficiently documents CLI routing functionality. It excels at actionability with concrete examples and maintains excellent token efficiency. The only weakness is the implicit workflow - the relationship between verifying CLI availability and running commands could be more explicitly sequenced.

Suggestions

Consider restructuring Requirements and Usage into a numbered workflow: 1. Verify CLI availability, 2. Run the ask command, 3. Find output in artifacts path

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient, providing only essential information without explaining concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context.	3 / 3
Actionability	Provides concrete, copy-paste ready commands for usage, routing, and verification. The examples are specific and executable, showing real-world use cases with actual command syntax.	3 / 3
Workflow Clarity	The workflow is implicit rather than explicit - it shows usage but doesn't clearly sequence the steps (verify CLI availability → run command → check artifact). For a skill involving external CLI tools, explicit verification-before-execution guidance would strengthen this.	2 / 3
Progressive Disclosure	For a simple, single-purpose skill under 50 lines, the content is well-organized with clear sections (Usage, Routing, Requirements, Artifacts). No external references needed given the scope.	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: 48ffaac

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.