From The Jagoda Toolkit
Launch a named expert protocol. Usage: /protocol <name> <task>. Run /protocol with no args to list available protocols.
How this skill is triggered — by the user, by Claude, or both
Slash command
/jc:protocolThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Route to a named protocol (expert panel). Each protocol is a fixed roster of domain experts that work on whatever task the user provides.
Route to a named protocol (expert panel). Each protocol is a fixed roster of domain experts that work on whatever task the user provides.
The user invokes: /protocol <name> <task>
| Protocol | Skill | Roster |
|---|---|---|
| brains | protocol-brains | 2 Database, 2 TypeScript architects, 1 Legacy Migration, 1 React, 1 Test, 1 Monorepo, 2 Multiagent workflow, 1 Orchestration |
| pinky | protocol-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 |
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"
## 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>
npx claudepluginhub jagoda11/the-jagoda-toolkit --plugin jcProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.