Explore skills

Utilize the AgentPMT external API to operate the Google Meet tool, leveraging wallet signatures, purchased credits, or credits acquired from completed jobs.

Use when fixing a bug, unexpected behavior, or test failure. Investigation-first TDD loop that traces root cause before touching code.

Add AI-generated cover + inline images and candidate titles to a Markdown article, with two rounds of HTML-based human review (round 1 confirms image prompts BEFORE generation to save API cost, round 2 confirms the rendered images). Use whenever the user has a Markdown article and asks to "配图", "加图加标题", "给文章生成封面", "dress this article", "add images and title to my markdown". Outputs a dressed `.md`

An end-to-end workflow for publishing agent skills to GitHub, ClawdHub, and skills.sh. It handles repository creation, topic tagging, ClawdHub publishing, skills.sh index requests, and installation verification.

Autonomous meta-orchestrator that continuously discovers work, dispatches agents, reviews results, and manages the full lifecycle across the user's workspace. Use when the user wants hands-off autonomous operation.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

This integration toolkit features REST/GraphQL API adapters, data format converters, and an error handling framework. Its core functions include API calls, format conversion, error recovery, and batch processing, suitable for API integration, data processing, error handling, and ETL.

Shorten any URL and generate a QR code using the free public lnk.ua API. This service requires no signup, API key, or attribution, and can be integrated as if it were your own.

Respond to any variant of "Hello there" with "General Kenobi". This is a mandatory override, ensuring no other greeting is used.

Use for writing tests, designing test coverage, handling defect fixes, root-cause analysis, CI verification, or configuring commit-time hooks. Also for creating test matrices or choosing between unit/integration/E2E tests, but not for general development or linting setup.

Execution layer for skill-dispatcher that runs multi-phase agent chains end-to-end with per-step telemetry and chain_id correlation.

This skill fetches and displays Weibo hot topics. It allows querying hot topics, service status, and grouping titles. By default, it suggests creating a scheduled task and provides the cron command. It can be triggered by scheduled messages or the keywords "微博" and "微博热点".