技能列表

Manage and monitor a personal stock watchlist with support for adding, removing, listing stocks, and summarizing their recent performance using data from 10jqka.com.cn. Use when the user wants to track specific stocks, get performance summaries, or manage their watchlist.

个股分析师。当用户提到任何 A 股、港股、美股股票名称或代码，或说出"分析一下"、"看看这只"、"打个分"、"值得买吗"、"怎么看"等意图时，调用本 skill。

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use before starting work and after responding to the user.

准备PPT/PDF讲解稿。将幻灯片转为图片并生成逐页演讲词。触发词：准备PPT讲解稿、准备演讲稿、生成演讲词、prepare presentation narration.

>

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

|

Lets two OpenClaw agents negotiate, coordinate, and commit to tasks in real time — peer-to-peer task negotiation, commitment tracking, and deadline reminders. Uses a relay for connection setup; all messages are end-to-end encrypted.

Fetch and parse news highlights from CCTV News Broadcast (Xinwen Lianbo) for a given date.

Convert functionality into Claude Code automation. Use when the user says "agentify", "agentic", "automate this", "create an agent", "make a plugin", "make a skill", or wants to automate a workflow as an agent, skill, or plugin.

Run Claude Code tasks in headless mode with `claude -p` through the local `cc-task-runner.sh` wrapper, including model switching, JSON output capture, structured schema checks, multi-file artifact validation, and glob matching. Use when you need reliable non-interactive Claude Code execution for coding, review, analysis, report generation, or file-producing tasks. Triggers include headless runner, claude -p automation, scripted Claude Code tasks, JSON-schema validation, artifact verification, an