Menu

Individual skill

model-council

0upvotes

Not available

Perplexity/skills/model-council/SKILL.md

Read pinned source

Source commit a2d33761e49b98f6ec1b48f12143264eb9b4ff4f

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Instructions only
Last checked
Nov 10, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

Standard SKILL.md format has not been attested at this commit. No installation command is available; inspect the source.

Repository context

Repository stars (not skill ratings)
71,152
Repository last updated
Nov 9, 2026
License
CC0-1.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Declared tags are partial or unavailable.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt
`<skill>`

skill: model-council  
workspace_path: `/home/user/workspace/skills/model-council`

# Model Council

The user invoked **Model Council**. Run their query independently across several frontier models in parallel, then synthesize one **model-forward** answer organized around where the models agree, disagree, and diverge. The synthesis — not the individual answers — is the product.

Read `text-models.md` in this skill for the canonical `spawn_agent` model identifiers and `multi-model-comparison.md` for the synthesis format.

## Phase 1 — Decide the council (model selection)

**Use only models `spawn_agent` accepts.** Do not offer other catalog models. If the user names one, say it is unavailable and apply the completion rule below. If a provider's catalog default is not accepted, use that provider's newest accepted model, or skip the provider if none is. Treat a launch rejection as a drop-out.  
Use the first matching rule below. Never ask the user which models to use; do not call `request_user_input` for model selection.
Back to top