agentleFS
Sign inStart free
blovett80blovett80/synero-mcp/skills/get-started/SKILL.md

get-started

Skill0 starsChanged 10 days agoMITView on GitHub

Use Synero to get a second opinion from several AI models (GPT, Claude, Gemini, Grok) on a question, with a consensus answer and where the models agree and disagree.

23 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 22 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the query_council tool when the user wants a second opinion, a cross-check, or a decision where one model's blind spot would be costly: …

    line 8
  2. Very specific:

    Leave preset unset for the balanced four-model council.

    line 11

“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Getting started with Synero

Use the query_council tool when the user wants a second opinion, a cross-check, or a decision where one model's blind spot would be costly: technical choices, code or architecture reviews, research and fact checks, plans and strategy.

  • Pass the user's question as prompt. Include any relevant context the user gave.
  • Leave preset unset for the balanced four-model council. Use solo for one quick answer, duel for two models, deep for the strongest (slower) models.
  • Set web_search: true for recent events or facts that may have changed.
  • To follow up on a previous answer, pass its queryId as parent_query_id.
  • A long run (deep, web search) may come back with status: "running" and a job_id after about two minutes. Call get_council_result with that job_id until the answer arrives. Never call query_council again for it: that starts and bills a second run.

Present the consensus answer first, then summarize where the models agreed and where they split, naming which model took which position. Link the result url so the user can open the full comparison on synero.ai.

Each call is billed to the user's Synero credits (new accounts get 3 free queries). Do not call it for trivial lookups the user did not ask to cross-check.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free