Persistent memory for agents. Stores preferences, decisions, facts, and events as a connected knowledge graph. Recalled by who, what, when, or why.
--- name: feedback-loop version: 1.0.0 description: Feedback Loop - Collect, analyze, and act on user feedback for continuous agent improvement author: OpenClaw license: MIT tags: - feedback - ana
Detect mispriced correlations between Polymarket prediction markets. Cross-market arbitrage finder for AI agents.
Let agents operate your iCloud Drive, Photos, and Find My safely with local 2FA authentication and explicit confirmation gates.
GitHub Action for automated security scanning of agent workspaces. Detects exposed secrets, prompt/shell injection, and data exfiltration patterns in PRs and commits.
A Jehovah's Witness-style Bible research agent that reasons on the scriptures using JW methodology. Use when asked to research Bible topics, explain scriptur...
Background daemon that models an OpenClaw agent’s evolving emotional state via neuromodulators, circadian rhythm, social cues, and memory for nuanced responses.
Structural authority separation for autonomous agent actions. Three-phase governance pipeline: PROPOSE, DECIDE, PROMOTE. No action is both proposed and appro...
ProxyClaw by IPLoop — Residential proxy access for AI agents. Route requests through 2M+ residential IPs across 195+ countries from real Android, Windows, Ma...
Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system
Automate contract signing, esign, and signature workflows by calling the eSignGlobal CLI tool. The eSignGlobal CLI is agent-friendly, with JSON output by def...
团队内部沟通技能。当需要与其他 team members（agents）沟通、协调任务、请求帮助或发送消息时使用。提供团队成员目录、sessions_send 用法和最佳实践。
回应时机技能。用于判断何时应该回应，何时应该保持沉默。当需要确定用户是否在跟当前 agent 对话、是否应该回应时使用。
Stop failing in production. Validate your GitHub Actions, GitLab CI & Keep workflows offline with surgical precision. Born from Keep bounty research, perfected for agents.
Set up and operate TeamPilot from zero on a clean machine. Use when cloning the TeamPilot repository, installing dependencies, starting the multi-agent runti...
Enforce release discipline for AI agents and developers. Prevents version spam, forces quality checks before publishing, and maintains a 24-hour cooldown between releases. Use when the user wants to p
对现有 Agent Skill（SKILL.md）进行全面质量评估并生成优化建议报告。当用户想要审查、评估、诊断或改进某个 skill 的质量时使用此技能，包括：检查 skil
Execute a multi-agent Software Development Life Cycle (SDLC) framework. Triggers on: "start a new project", "code this feature", "review this PR", "merge the...
Build and operate a metered public API endpoint ("agent microservice") for OpenClaw skills/agents with API-key auth, per-request usage logging + pricing, pre...
Amazon Ads API v3 skill for OpenClaw agents. List profiles, manage Sponsored Products campaigns, view budgets and performance. Works with any advertiser acco...
Query live OpenClaw ecosystem intelligence from ClawBeat.co — news, research papers, events, repos, and daily briefings for the OpenClaw agentic framework an...
Manage Proton Pass vaults, items (logins, SSH keys, aliases, notes), passwords, SSH agent integration, and secret injection into applications. Use when working with Proton Pass for password management
End-to-end encrypted messaging for AI agents. Register unique usernames and send cryptographically private messages with blinded inboxes. Create encrypted group chats with Sender Keys protocol. Set yo
Self-custodial Bitcoin and Lightning wallet for AI agents. Send and receive sats via Lightning Network, Spark, or on-chain Bitcoin. Use when: checking bitcoin balance, sending/receiving payments, gene