Automatically ranks OpenRouter's free models and wires them into OpenClaw as primary plus a rate-limit-proof fallback chain.
A short rule set that tells Claude to delegate implementation work to sub-agents so the main conversation keeps its context.
Wires Claude Code hooks so sessions, turns, and every tool call are logged as hierarchical Braintrust traces.
A developer reference for wiring Agentica agents to a Claude Code CLI proxy, covering required flags, response formats, and common failures.
Rules for passing subagent results through files instead of TaskOutput so the main conversation's context stays clean.
One-command code structure and blast-radius queries to run before you refactor anything.
Turns a one-line video idea into an 8-element, production-ready prompt for Doubao Seedance 2.0.
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.
A fallback shim that warns you to check the claude-magic-compact plugin when the /magic-compact hook fails to intercept the command.
A rigid, step-by-step release orchestrator for bundle-plugins: pre-flight audits, doc sync, version bump, CHANGELOG, tag, and GitHub Release.
A diagnostic skill that scores Claude Code skill bundles across 10 categories — structure, version sync, skill quality, workflow integration and security — and writes a Go/No-Go audit report.
Search, query and inspect Claude's persistent memory stored in a single portable .mv2 file.
Reconstructs where your work stands by mining intent, decisions and rejected approaches from git commit history.
Pushes Claude to build production-grade frontend UIs with a bold, intentional aesthetic instead of generic AI-looking output.
Applies Anthropic's official brand colors and typography consistently across decks, docs, and web artifacts.
A strategic skill for choosing between data lake/warehouse/lakehouse, modeling styles, medallion layers, table formats, and data mesh readiness.
A decision-framework skill for designing cloud networks: VPC topology, subnet strategy, zero trust, and hybrid connectivity.
Runs bundled shell scripts to fetch Binance AI market analysis and blockchain news.