agentleFS
Sign inStart free
Jagoda11Jagoda11/the-jagoda-toolkit/skills/protocol/SKILL.md

protocol

Skill0 starsChanged 6 months agoMITView on GitHub

Launch a named expert protocol. Usage: /protocol [name] [task]. Run /protocol with no args to list available protocols.

3 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

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If no arguments: list available protocols (see below) and stop.

    line 18
  2. Distinctive:

    If only a name with no task: ask "What should Protocol <Name> work on?"

    line 19
  3. Distinctive:

    If name + task: dispatch to the matching protocol skill.

    line 20
  4. Distinctive:

    If the protocol name is not recognized, say:

    line 37

“Common” is measured: kept by at least 6 in 10 of the 3 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

Protocol — Expert Team Router

Purpose

Route to a named protocol (expert panel). Each protocol is a fixed roster of domain experts that work on whatever task the user provides.

Instructions

Parse Input

The user invokes: /protocol <name> <task>

  • If no arguments: list available protocols (see below) and stop.
  • If only a name with no task: ask "What should Protocol <Name> work on?"
  • If name + task: dispatch to the matching protocol skill.

Available Protocols

ProtocolSkillRoster
brainsprotocol-brains2 Database, 2 TypeScript architects, 1 Legacy Migration, 1 React, 1 Test, 1 Monorepo, 2 Multiagent workflow, 1 Orchestration
pinkyprotocol-pinky2 React architects, 1 TS architect, 1 State/Data, 1 MUI, 1 UX/a11y, 1 Contracts, 1 Test, 1 i18n, 1 Security, 1 Performance, 1 Business Impact, 1 Backend Contract, 1 Monorepo, 1 Tailwind, 1 UI Component Library

Dispatch

Invoke the matching skill using:

Skill: protocol-<name>, args: "<task>"

If the protocol name is not recognized, say:

"Unknown protocol: <name>. Available protocols: brains, pinky"

Output (when listing)

## Available Protocols

| Protocol | Experts |
|----------|---------|
| **brains** | 2 Database, 2 TS architects, 1 Legacy Migration, 1 React, 1 Test, 1 Monorepo, 2 Multiagent workflow, 1 Orchestration |
| **pinky** | 2 React architects, 1 TS architect, 1 State/Data, 1 MUI, 1 UX/a11y, 1 Contracts, 1 Test, 1 i18n, 1 Security, 1 Performance, 1 Business Impact, 1 Backend Contract, 1 Monorepo, 1 Tailwind, 1 UI Component Library |

Usage: /protocol <name> <task>

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