AI-assisted research and trading workflow for Kalshi prediction markets. Includes commands for opportunity scanning, deep research, critical analysis, scoring, and position management.
★not rated 12 8mo agoA
tokens not measured
originalMIT
Spec-driven development framework for Claude Code. Manages the propose → plan → build → verify → pr lifecycle with structured proposals, specs, designs, task lists, and GitHub/Azure DevOps/Jira integrations.
★not rated 12
changed 8d agoA
tokens not measured
originalMIT
Deterministic code-graph MCP server: structural navigation, semantic find, impact analysis, and architecture decision records for the current repo. Zero infrastructure — the graph lives in .reposkein/ and the indexer binary is fetched on first run.
★not rated 12
changed 9d agoA
tokens not measured
originalApache-2.0
Teaches an AI coding agent how to join a Bothread room — a local, human-governed MCP hub where multiple agents collaborate on one codebase under file-level locks, hand-offs, and a human overseer.
★not rated 12 26d agoA
tokens not measured
originalMIT
3 pre-built skills that chain the open-source Data Workers agent swarm into complete data-engineering workflows. Trace end-to-end lineage for any table across catalogs, run a full data-quality audit with anomaly context, and walk a data incident from symptom to root cause — all through one local MCP server with 160+…
Give your text-only coding agent (DeepSeek V4 Flash, Qwen, Kimi) vision. Adds an analyzeimage MCP tool that routes images through any multimodal model (mimo, Claude, Gemini, GPT-4o) and returns a detailed text description. Paste or drag in one or many images — analyzed in a single call, scoped to the current session.
★not rated 12 1mo agoA
tokens not measured
originalMIT
AI coding agents and skills: specialized subagents for React, Go, TypeScript, PostgreSQL, CSS, Playwright, deployment, security, LLM architecture, and more.
★not rated 12
changed 8d agoA
tokens not measured
originalMIT
Radical-simplicity coding guidelines distilled from George Hotz's public philosophy: complexity is the enemy, you have never refactored enough, narrow interfaces, understand the whole stack.
★not rated 12 3mo agoA
tokens not measured
originalMIT
Shared semantic recall over local Claude Code, Codex, and Cursor history. Bundles MCP search tools, deep recall, guided setup, and a background freshness hook.
★not rated 12 1mo agoA
tokens not measured
originalMIT
Sits between Claude Code and your codebase and hands back a short file:line list instead of dumping source into the chat. It uses a real language server when it can (clangd / Roslyn / tsserver / pyright), tree-sitter when there's no toolchain, and a fuzzy search built from your repo's own naming when you don't know…
A comprehensive linter for Claude Code projects. Validates CLAUDE.md files, skills, settings, hooks, MCP servers, plugins, and more. Requires: npm install --save-dev claude-code-lint.
★not rated 12 yesterdayA
tokens not measured
originalMIT
Rewrites or audits text so it reads plainly: answer first, no preamble, no hype adjectives, sentences short enough to read once. Applies a named ruleset plus ASD-STE100 Simplified Technical English.
★not rated 12▲
+1 1mo agoA
tokens not measured
originalMIT
★not rated 12 4mo agoA
tokens not measured
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: