A scheduled maintenance skill that closes already-shipped issues and keeps a curated 15–25 issue contributor backlog for the awesome-claude repo.
Turns any source that describes how a task gets done — a SKILL.md, chat log, runbook, or plain prose — into a runnable Flowtrace DAG and drives the full run lifecycle to verify it.
Finds promo/spam replies under your X (Twitter) posts, hides them, and mutes the accounts behind them.
An FDEOps skill that tells Claude how to configure or troubleshoot access to a requested data source (MCP) using whatever host tools are available.
Drive real websites from Claude using the `agent-browser` CLI: snapshot refs, click and fill, then verify the result.
Consults ChatGPT and Gemini in parallel and merges their views with Claude's own into a single attributed implementation plan.
Rules for passing subagent results through files instead of TaskOutput so the main conversation's context stays clean.
Wires Claude Code hooks so sessions, turns, and every tool call are logged as hierarchical Braintrust traces.
Teaches Claude to read and update 15Five performance-management data (users, check-ins, objectives) through the Membrane CLI.
A Playwright automation skill that sends one prompt to Yuanbao, LongCat, Doubao, Qwen, Gemini, Grok, or MiniMax through a single wrapper command.
A brand-name entrypoint that hands any "I want to build X" request to the Atlas PRD-and-task-graph pipeline.
Builds a clean morning brief inside Claude Code from your Obsidian vault: today's priorities, unposted content, and local weather.
Helps you choose between BoltzGen, BindCraft, RFdiffusion and Germinal, then lays out the full de novo binder design pipeline.
Lets Claude read and manage 10to8 appointments, staff and services through the Membrane CLI.
Query 123FormBuilder forms and submissions and automate workflows through the Membrane CLI.
Lets Claude read and automate 10Duke licensing, order, and customer data through the Membrane CLI without handling credentials.
Control and query Xiaomi/Mi Home smart-home devices from chat via the mijiaAPI CLI.
A standardized five-stage multi-agent pipeline — research, plan, validate, TDD implement, review — using background agents and file-based handoff.