Advisory router — query Claude, Codex, or Gemini for a quick second opinion. Experimental — only Claude is guaranteed available; other models require dev-mcp-setup configuration.
SkillScore86Maintained
Automatic
◆AI Engineer pack
Last verified 8/19/2026
What it changes
Passed 19 of 22 test cases with the skill, and 3 of 22 without it.
Without skill14%
With skill86%
Checks it passed that the model alone missed
Contains an Answer section citing Claude
Includes a Note section in the markdown output
Contains a top-level header specifying Ask for Claude
and 14 more in the full report
16 fixed3 passed either way3 still failing0 broke
Pass-rate lift
+73 pp
Tokens
-5%
Agent turns
0%
Response time
-30%
Model gemini-3.6-flashMeasured 8/19/2026v119 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 16
Prompt
Who is the primary architectural role or persona that consumes multi-model perspective summaries in the EvoNexus Engineering Layer?
What was checked, without and with the skill
Checked
Without skill
With skill
Identifies apex-architect as the consumer of multi-model perspective summaries
Missed
Passed
case-18 · gemini-3.6-flash · 8/19/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md54 linessingle file
Dev Ask
Derived from oh-my-claudecode (MIT, Yeachan Heo). Adapted for the EvoNexus Engineering Layer.
EXPERIMENTAL. Quick advisory query to a specific LLM (Claude, Codex, Gemini) for a second opinion. Different from dev-ccg which runs all three in parallel — dev-ask is single-shot.
Use When
You want a fast second opinion from a specific model
Comparing how different models approach the same problem
Validating Claude's answer against another model
Do Not Use When
Need consensus across models → use dev-ccg
Just need an answer → ask the active session directly
Codex/Gemini APIs not configured → only Claude available, fall back
Workflow
Pick the target model:claude | codex | gemini
Format the question model-agnostically
Send via the appropriate API
Return the answer with the model's name attached
Optional: save to workspace/development/research/[C]ask-{topic}-{date}.md
Configuration
Model
Required setup
Claude
Native — always available
Codex
OpenAI API key configured via dev-mcp-setup
Gemini
Google API key configured via dev-mcp-setup
If a target model isn't configured, the skill warns:
"{model} is not configured. Only Claude is currently available. Configure via dev-mcp-setup or use dev-ccg to compare available models."