技能列表

Call fal.ai model APIs for image generation (text-to-image and image-to-image). Use when a user asks to integrate fal, construct requests, run jobs, handle auth, or return image URLs from fal model APIs.

发送文件到消息平台。触发词：发送文件、发送文档、发送截图、传文件、发文件。支持飞书等平台，内容优先级：生成的文档 > 本地文件 > 截图。

CLI for crypto portfolio tracking, market data, and CEX history. Use when the user asks about crypto prices, wallet balances, portfolio values, Coinbase/Binance holdings, or Polymarket predictions.

Generate images using Alibaba Cloud Bailian Qwen-Image and Z-Image models (通义千图文生图 + 人像照片模型)

|

Tactical negotiation framework based on Chris Voss's "Never Split the Difference." Use when preparing for negotiations, during live negotiation scenarios, analyzing counterpart behavior, crafting responses to difficult conversations, handling objections, salary/contract negotiations, or when asked about negotiation techniques like mirroring, labeling, calibrated questions, or the Ackerman method.

Convert Self-Improving Agent learnings into a structured ExpertPack. Migrates the .learnings/ directory (LEARNINGS.md, ERRORS.md, FEATURE_REQUESTS.md) and any promoted content from workspace files into ExpertPack's portable format with multi-layer retrieval, context tiers, and EK measurement. Output is Obsidian-compatible — includes YAML frontmatter on all content files and can be opened as an Obsidian vault. Use when: upgrading from Self-Improving Agent to ExpertPack, backing up agent learnings

Email API for AI agents. Send and receive emails programmatically via ClawMail.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Use https://tx.steer.fun to have a user execute a wallet action (send a transaction or sign a message) with their own wallet via a shareable URL. Use when an agent needs the user to approve/execute a JSON-RPC request (e.g. eth_sendTransaction, personal_sign, eth_signTypedData_v4, wallet_sendCalls) and return the result (tx hash/signature) back to the agent, optionally via redirect_url.

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when (1) a command, tool, API, or operation fails; (2) the user corrects you or rejects your work; (3) you realize your knowledge is outdated or incorrect; (4) you discover a better approach; (5) the user explicitly installs or references the skill for the current task.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.