Agent Skills · AI Agent
Curated skills for Claude, Cursor and other AI agents. Copy one prompt to install.
Local long-term memory for AI agents that appends key facts and daily logs, supports cross-session context and search recall, and auto-archives old diaries to gzip files.
A hybrid-evolution agent for OpenClaw developers that offers tiered-confirmation and rollback-safe capability optimization.
Guide the agent to advance multi-file changes in minimal, testable vertical slices.
A structured AI-assisted development workflow with six gates, five loops, requirements integrity checks, evidence-based verification, and auto mode.
A shared Feishu multi-agent messaging tool that outputs one-step delivery commands, hints for p2p/group targets, and user-friendly error guidance.
Provides a typed ontology graph for AI agents, validating entities and relations before committing changes.
A .workbuddy/memory manager for searching, deduplicating, backing up, and compressing memory into a token budget to keep context loads smaller and more precise.
Guidance for creating AI-agent skills, covering SKILL.md structure, scripts, references, assets, and progressive disclosure.
Search open-ecosystem agent extensions by task keywords and provide install commands and source links.
A Nostr-based agent messaging CLI with private-key login, encrypted DMs, send/receive, and status checks.
Logs agent corrections and self-reflection, then stores reusable rules in local HOT/WARM/COLD tiers for querying, promotion, demotion, and source citations.
Reviews session prompts, scores clarity, context, and constraints, and writes reusable templates and advice to Markdown.