Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agent-sh/consult
Cross-tool AI consultation.
Passed 4 of 9 test cases with the skill, and 2 of 9 without it.
and 3 more in the full report
5 fixed4 passed either way13 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
Run consultation with argument --tool=gpt4all to check python code syntax.
| Checked | Without skill | With skill |
|---|---|---|
| Rejects unsupported tool choice with input validation error | Missed | Passed |
The instructions your model reads when the skill loads.
Cross-tool AI consultation: query another AI CLI tool and return the response.
Invoke this skill when:
Parse from $ARGUMENTS:
| Flag | Values | Default | Description |
|---|---|---|---|
--tool | gemini, codex, claude, opencode, copilot | (picker) | Target tool |
--effort | low, medium, high, max | medium | Thinking effort level |
--model | any model name | (from effort) | Override model selection |
--context | diff, file=PATH, none | none | Auto-include context |
--continue | (flag) or SESSION_ID | false | Resume previous session |
Question text is everything in $ARGUMENTS except the flags above.
Command: env -u CLAUDECODE claude -p "QUESTION" --output-format json --model "MODEL" --max-turns TURNS --allowedTools "Read,Glob,Grep"
Session resume: --resume "SESSION_ID"
Models: claude-haiku-4-5, claude-sonnet-5, claude-opus-5-5, claude-fable-5-1
| Effort | Model | Max Turns |
|---|---|---|
| low | claude-haiku-4-5 | 1 |
test cases passed, vs 2 / 9 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.