trading-experiment
claudeAutonomous crypto strategy research via backtesting. Claude designs experiments, writes strategy code, runs backtests, analyzes results, and iterates.
1 skill · 3 agents
Deterministic state machine for autonomous multi-agent development. One orchestrator dispatches coder/reviewer agents in worktrees with queue-based task management.
Plugin swarm from marketplace OnSpotify-Plugins in dapmeupfam/OnSpotify-Plugins. Commands read from the repo's manifest — 19 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
pushUse to add a new task to an existing swarm queue. Triggers on "add a task to the swarm", "push to the queue", "queue another task", or /swarm:push.
runUse to start an autonomous multi-agent development swarm from a plan or task list. Triggers on "run the swarm", "execute this plan with agents", "build this autonomously", "start the swarm", or /swarm:run.
statusUse to check the current state of a running or completed swarm. Triggers on "swarm status", "check the queue", "how is the swarm doing", "show swarm progress", or /swarm:status.
teamUse to create, list, or manage swarm teams/workflows through conversation. Triggers on "create a swarm team", "new team", "new workflow", "custom pipeline", "set up a team for", "swarm team for", "list teams", "show teams", or /swarm:team.
coderUse this agent to implement a single development task in an isolated git worktree. Spawned by the orchestrator agent — not invoked directly by users.
orchestratorUse this agent to manage the swarm task queue and dispatch agents through a configurable pipeline. Never writes code directly. Reads the queue and team config, assigns work, merges results.
reviewerUse this agent to review code changes made by a coder agent. Spawned by the orchestrator — not invoked directly by users. Read-only, cannot modify code.
bash ${CLAUDE_PLUGIN_ROOT}/scripts/guard-write.sh
Autonomous crypto strategy research via backtesting. Claude designs experiments, writes strategy code, runs backtests, analyzes results, and iterates.
1 skill · 3 agents
Spawn Kimi CLI as a general-purpose sub-agent for Claude Code — define the task at spawn time, just like Claude Code's native Agent tool
1 command · 1 agent
Build visually stunning, production-grade websites with exceptional design quality and advanced layout techniques
1 skill
Skill for building with @chenglou/pretext — a pure TypeScript text measurement & layout engine that bypasses DOM reflows
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.