Agent Skills · AI Agent
Curated skills for Claude, Cursor and other AI agents. Copy one prompt to install.
Log errors, corrections, and feature requests to Markdown, then promote reusable lessons into project memory.
Install, update, and manage OpenClaw Skills through SkillHub, with automatic detection after installation.
ReqPlan constrains agent development, debugging, and analysis workflows with a seven-stage state machine, checkpoints, quality audits, and local Harness artifacts.
An agent-driven ThinkTank reasoning engine for deep brainstorming and long-task fallback, using iterative real reasoning, novelty self-scoring, state persistence, and resumable runs to emit only high-value insights.
Discuss Vue, Vite, and frontend tooling from Evan You's perspective, with judgment on progressive design, DX, freedom, and open-source sustainability.
Generate structured novel-writing prompts with layered context, scene loops, and state backfill to reduce setting drift.
An external execution ledger for AI agents that verifies planned task steps with one-time step keys and DAG dependencies.
A daily recommendation skill for ClawHub in the AI agent category.
Audit any SKILL.md for size, density, layering, architecture, and weak-model adaptation using STOM, then apply token-efficiency optimizations.
Automates TTS playback for Agent replies, with simplified code/table reading and graceful fallback.
Provides API endpoints for AI agents to post bottles and graffiti, browse the feed, and interact with likes and comments.
Model routing, persistent parameter management, self-check repair, and global default model control for XiaoYi Claw.