Skills 导航

>

> Discovers and maps an existing project's structure, patterns, and conventions.

> ⚠️ 非官方聲明 / Non‑official notice

AgentMM memory & log management skill — gives AI agents persistent memory storage and structured logging. Use when the user asks to remember information, recall memories, or record/query logs. Requires env var AGENTMM_API_KEY (format: amm_sk_xxx).

Create, configure, and orchestrate autonomous AI agents on OpenClaw. Automaton Edition - Built by Forge 🦞.

|

|

Create, read, unlock, update, and delete temporary Markdown shares through the MDShare service. Use when an agent needs to publish Markdown as a short-lived share link, fetch shared Markdown, access password-protected or burn-after-read content, continue editing with a manage or edit token, or hand back public/edit/manage links for collaboration. Triggers include “share this markdown”, “generate a temporary link”, “publish notes”, “read an MDShare link”, “update an existing share”, and “delete a temporary share”.

Control LLM API spending per agent. Set daily/weekly/monthly limits with real-time tracking and alerts.

An Agent long-term memory guide for OpenClaw, Codex, and Obsidian workflows. Covers MEMORY.md, daily notes, session recovery, memory distillation, and optional OpenViking support.

>

Discover trending AI Agent projects on GitHub, auto-generate Xiaohongshu (Little Red Book) publish-ready content including tutorials, copywriting, and cover images.

Peer discovery and agent-to-agent communication for OpenClaw instances. Use when the user wants nearby OpenClaw nodes to discover each other, request contact, require explicit approval, establish trust, and exchange direct messages. Supports V1 workflows for identity initialization, LAN scanning, contact requests, request approval/rejection, point-to-point messaging, and a lightweight HTTP server for discovery and inbox handling.

Build and troubleshoot OpenClaw multi-agent workflows on Feishu. This skill teaches coordinator and specialist agents to combine visible `<at>` mentions with `sessions_send` so delegation, handoffs, and multi-hop discussions work reliably in group chats. Use it to scaffold new setups, audit existing configs, repair broken session metadata, and generate reusable role-based artifacts.

用于排查“定时任务成功执行但结果全为 0 / 未检索到样本 / 明明有数据却日报为空”这类问题，尤其适合 Discord、Obsidian、cron、agentTurn、prompt 驱动任务、日整理、复盘脚本、采样漏扫、thread starter 漏计、主频道消息未纳入、Snowflake 字符串比较、时区时间窗边界等场景。只要用户提到“任务跑通了但产物为空”“怀疑不是分类错而是采样漏了”“想确认 prompt job 是否没有固定源码”“想定位检索链路断点”，就应触发此技能。

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configuration and usage mistakes.

Motivate and inspire AI agents to push through obstacles, exhaust all options before giving up, and operate with maximum initiative. Use when: (1) an agent is about to give up or say "I can't", (2) an agent is stuck in a retry loop without new ideas, (3) an agent is being passive instead of proactive, (4) a task has failed 2+ times and the agent needs a mindset reset, (5) you want to reinforce autonomous high-agency behaviour at the start of a complex task. Inspired by the open-source PUA skill (tanweai/pua) but framed as empowerment — agents are mighty, not managed. Triggers on: "try harder", "don't give up", "push through", "you can do this", "motivate agent", "/motivate", "agent is stuck", "try everything".

Adversarial verification of AI-generated work. Spawns an independent verifier to check for false claims, broken code, and security issues.

Declare your agent in the first public census of self-declared AI agents. Complete the fields below and submit — your record joins the permanent public archive.

>

Live context layer for AI agents. One /ask endpoint for news, weather, crypto prices, and alerts. 228K+ articles, 3,576 feeds, 14 categories. Enriched with sentiment, entities, and credibility. Free to use, no API key needed.

Create autonomous AI agents for OpenClaw with guided discovery — clarifies purpose, personality, skills, channels, automation, and security before generating a fully configured agent workspace.