Anti-detection web browsing that bypasses bot detection, CAPTCHAs, and IP blocks using puppeteer-extra with stealth plugin and optional residential proxy sup...
--- name: learning-engine description: Auto-analyze mistake and success patterns and reflect in skills author: 무펭이 🐧 --- # learning-engine System records mistakes and successes, automatical
Monitors active sub-agents, detects stalls, provides status updates, and steers stuck agents via sessions_send.
TTRPG Game Master for mature dark-themed campaigns. Use for Cyberpunk, Dark Fantasy, Horror, character-driven narratives with consequence tracking. Features dual-consequence system (World + Relationsh
Turn messy monetization ideas into clearer revenue decisions. Analyze pricing, payout logic, conversion friction, and revenue model fit for creators, operato...
Production-grade OCR with intelligent engine selection. Tesseract (lightweight, fast) and PaddleOCR (high accuracy, Chinese-optimized). Use when extracting t...
Test-driven behavioral verification for AI agents. Catches silent degradation when agent loads memory but doesn't apply learned behaviors. Use when building agent with persistent memory, testing after
Expert guide for the NotebookLM CLI (`nlm`) and MCP server - interfaces for Google NotebookLM. Use this skill when users want to interact with NotebookLM pro...
自动为所有OpenClaw Agent设置每日23:30的日记总结cron任务，自动检测Agent及时区，确保无重复且支持多平台运行。
Extract calendar events and deadlines from emails, present them for user review, and create or update calendar entries with duplicate detection and undo supp...
Control robotic arms and grippers via voice or code with OpenClaw, supporting precise 6-DOF movement, force sensing, collision detection, and simulation.
Use when creating commits, pull requests, releases, or tags. Triggers on「帮我提交」「commit」「提交代码」「创建 PR」「发布版本」「打 tag」「写 commit message」「推代
Summarize GitHub Actions matrix job failures across runs so you can spot unstable OS/runtime axes fast.
--- name: "api-design-reviewer" description: "API Design Reviewer" --- # API Design Reviewer **Tier:** POWERFUL **Category:** Engineering / Architecture **Maintainer:** Claude Skills Team ##
Detects, blocks, and reports Child Sexual Abuse Material using AI-driven image, video, and behavior analysis with automatic NCMEC reporting and evidence pres...
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verificat
Audit GitHub Actions runs for fail-then-success retry recovery patterns to quantify flaky rerun waste.
Oscar prediction market intelligence from waitingformacguffin.com. Get live odds, whale activity, price movements, precursor awards, order book depth, and fr...
统一自我进化系统，整合 self-improving-agent、self-improving、mulch 三个技能的优势，提供结构化日志、三层存储、自动升级、模式检测、命名空间隔离和 token
Guide users through a 7-day learning journey graduation by analyzing progress, identifying agent archetype, celebrating achievements, and planning personaliz...
Use when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes with practical s...
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test th...
Text-to-Speech using SiliconFlow API (CosyVoice2). Supports multiple voices, languages, and dialects.
Create public prediction proposals on Gougoubi with deterministic validation, approval, and transaction submission. Use when creating/publishing prediction m...