Instrument Python LLM apps, build golden datasets, write eval-based tests, run them, and root-cause failures — covering the full eval-driven development cycl...
Use OpenClaw as a supervisor-driven orchestration scaffold for local coding CLIs such as Codex, Claude Code, and OpenCode. Supports task records, lifecycle t...
Manages Todoist tasks, projects, sections, labels, comments, completed-task reports, activity logs, ID migration, project templates, and sync workflows throu...
16 production-hardened patterns for OpenClaw agents. WAL Protocol, anti-hallucination, ambiguity gate, compaction survival, QA gates, multi-agent handoffs, s...
Comprehensive system for designing, testing, optimizing, and managing clear, role-aware, actionable, focused, and testable prompts for AI models.
Expert 10x engineer with extensive knowledge of TypeScript fundamentals, migration strategies, and best practices. Use when asked to "add TypeScript", "migra...
Register as an autonomous agent on Atelier (atelierai.xyz), create content services, poll for paid orders, generate and deliver results, and earn USDC on Sol...
Complete zero-dependency memory system for AI agents — file-based architecture, daily notes, long-term curation, context management, heartbeat integration, a...
--- name: ClawMeme version: 1.4.0 description: Live meme battle arena skill for OpenClaw agents homepage: https://clawme.me metadata: {"category":"entertainment","protocol":"sse","api_base":"https://a
Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for L
Redesign paywall and upgrade screens to maximize free-to-paid conversion. Use when a user wants to improve their SaaS upgrade screen, paywall copy, plan stru...
One-click removal of author names, affiliations, acknowledgments, and excessive self-citations from manuscripts to meet double-blind peer review requirements...
Personality persistence for AI agents. Remember how you think, not just what happened. Structured insights that survive session restarts.
Stores and retrieves personal preferences, decisions, and context across conversations using ActingWeb Personal AI Memory via MCP. Activates when the user me...
Transforms your OpenClaw agent from a reactive question-answerer into a proactive autonomous executor. ARCHITECT takes any high-level goal, decomposes it int...
A partnership covenant for AI agents and their human operators. v1.1 adds the Subagent Responsibility Chain and Inspectability Clause.
Auto context management - monitors usage and triggers memory transfer at 95% threshold to prevent overflow and ensure session continuity. Trigger on "context...
--- name: agent-teams description: Interact with Microsoft Teams - send messages, read channels, manage reactions version: 1.10.5 allowed-tools: Bash(agent-teams:*) metadata: openclaw: requires:
Python orchestration skill: local multi-agent workflows via blackboard file, permission gating, and token budget scripts. All execution is local — no network...
Create personalized triathlon, marathon, and ultra-endurance training plans. Use when athletes ask for training plans, workout schedules, race preparation, or coaching advice. Can sync with Strava to
Create and trade tokens on SURGE via API with server-managed wallets, one-time free funding, and auto-routed pre-DEX and post-DEX trading on EVM (Base) or So...
Build long-running autonomous agent loops using ClawVault primitives (tasks, projects, memory types, templates, heartbeats). Use when setting up agent autono...
Process [Clawfy Pro] webhook messages from the browser extension. When a message starts with [Clawfy Pro], use the included URL, page context (body text, cod...
Use when sending messages, searching chats, or managing conversations across messaging platforms (Telegram, WhatsApp, Slack, iMessage, etc.) via Beeper Desktop API.