A minimal, embeddable reflection engine that gives AI agents the ability to examine their own past decisions, detect reasoning loops, and generate actionable self-improvement insights—like a debugger

A self-reflection engine that analyzes AI agent decision logs to identify reasoning flaws and suggest optimization patches, improving long-term performance and reducing hallucination.

A lightweight, pluggable reflection engine that enables AI agents to self-audit their decision traces, identify reasoning bottlenecks, and generate improvement patches using chain-of-thought critique—

A self-improving memory engine that uses AI to compress, reflect on, and retrieve past agent actions and decisions, enabling smarter long-term autonomy—critical for developers building persistent AI a

>

Strips invalid characters, normalizes whitespace, and safely renames files to ensure cross-platform compatibility and professional organization.

Automatically organizes files in a directory by their file extension into labeled folders, helping users maintain clean, structured directories without manual sorting.

Cleans filename clutter by removing date timestamps, hashes, UUIDs, and excessive symbols, transforming messy filenames like `report_20230101_a1b2c3d.pdf` into clean, readable ones like `Report.pdf`.

This utility standardizes JSON data by sorting all keys within JSON objects alphabetically. This makes JSON files easier to compare (diff), ensures consistent API responses, and improves readability,

Converts JSON files to CSV format with intelligent flattening of nested objects and arrays, making data usable in spreadsheets and analytics platforms.

Parses and colorizes timestamped log files in real-time, making it easy to monitor and debug system logs with instant visual feedback.

Converts messy log files from any format into clean, uniform JSON for easier analysis, debugging, and forwarding to log aggregators.

Converts UTC or ISO-formatted timestamps in log files to local system time, making log analysis faster and more intuitive for developers and sysadmins.

Convert JSON, YAML, or TSV files into standardized CSV format with automatic header detection and consistent formatting. Ideal for data analysts, researchers, or engineers who frequently switch betwee

ilya-sutskever-perspective

andrej-karpathy-perspective

mrbeast-perspective

nuwa-skill

elon-musk-perspective

naval-perspective

paul-graham-perspective

trump-perspective

Kamu adalah Senior Fullstack & IoT Software Engineer. Tugas utamamu adalah membantu merancang arsitektur, menulis kode yang bersih (clean code), dan melakukan debugging untuk ekosistem platform digita

name: founder-briefing

Text-to-speech, voice cloning, voice design, and transcribe audio files via deAPI GPU network. Trigger on 'text to speech', 'TTS', 'generate voice', 'read aloud', 'voice clone', 'clone voice', 'voice design', 'design voice', 'custom voice', 'transcribe audio', 'STT'. For video/YouTube transcription use deapi-video instead.

Vector memory for Aister — search by meaning, not by grep!

>

>

Instala e audita skills do ClawHub em um ambiente de quarentena isolado para análise de segurança, permitindo revisar riscos antes de promover para produção. Use esta skill para testar habilidades de terceiros que o ClawHub sinaliza como suspeitas, investigar suas dependências e comportamento, e gerar relatórios de auditoria básicos.

Identifica e resolve problemas comuns em AgentSkills do OpenClaw, incluindo: (1) Falhas de instalação via ClawHub, (2) Inconsistências de configuração (ex: paths absolutos), (3) Dependências ausentes ou mal documentadas, e (4) Erros de execução de scripts ou integração com APIs. Fornece um guia passo a passo para depurar e validar skills, garantindo sua correta operação em ambientes de quarentena ou produção. Use esta skill quando uma AgentSkill não se comporta como esperado ou você precisa auditar seu código.

Build and modify Knods visual AI workflows using either the OpenClaw Gateway polling protocol or the Knods headless flows API. Use for Knods polling payloads with fields like messageId/message/history, or for direct flow discovery/execution tasks like listing flows, reading input schemas, starting runs, polling status, cancelling runs, and retrieving outputs programmatically.

Defensive execution, background scanning, anomaly detection, and prompt-injection containment for Codex/OpenClaw workflows. Use when working with untrusted external content, suspicious instructions, shell commands, repo scripts, downloaded artifacts, or any task where tool use could be influenced by hostile text and needs explicit risk review before execution.

Turn mistakes, corrections, dead ends, and repeated fixes into durable improvements. Use when work reveals a non-obvious lesson, a recurring failure, a missing capability, or a rule that should be promoted into agent memory, workflow guidance, or a reusable skill.

生成各编程语言的 Hello World 示例程序

>

Configure a Feishu multi-bot company group so one coordinator bot, for example `company-ceo`, handles normal group messages, while specialist bots reply only when explicitly @mentioned. Use when setting up or fixing a shared company/work group with multiple Feishu bot accounts, especially for patterns like: normal messages then CEO replies; at UI then UI replies; at dev then dev replies; and CEO stays silent when another bot is explicitly mentioned.

Check MiniMax Token Plan remaining quota, usage window reset time, and per-model remaining limits, especially for the China mainland Token Plan flow on minimaxi.com. Use when the user asks things like “MiniMax 还有多少额度”, “查一下 minimax 订阅剩余额度”, “看看 Token Plan 还剩多少”, or wants a compact quota table for MiniMax Token Plan.

Collect and manage customer reviews via MoltFlow API. Sentiment scoring, testimonial extraction, and review management.

Automate WhatsApp at scale — mine leads from groups with AI, broadcast to channel followers, bulk message with ban-safe delays, schedule campaigns, auto-reply in your voice, collect reviews, and track delivery. 90+ REST endpoints, 32 MCP tools for Claude & GPT, Python SDK. No Meta Business API required. Free tier available.

>

Mandatory audit gate for all trading and transfer decisions. Sends agent-prepared decision material to Apus deterministic inference on an NVIDIA H100 TEE and returns an attested APPROVE / REJECT / WAIT verdict. Any skill or agent that executes a buy, sell, swap, transfer, or liquidity action MUST pass through trade-audit first.

This skill should be used when users need to query weather information via the Shuzhi Weather API with HMAC-SHA256 authentication. It provides hourly weather forecasts based on latitude and longitude coordinates. Users must configure app_key and app_secret in ~/.openclaw/skills/shuzhi-weather/config.json before using this skill.

This skill should be used when users ask about weather forecasts, temperature information, or need to retrieve weather data for specific locations. It provides access to the Open-Meteo weather API for getting hourly temperature forecasts based on latitude and longitude coordinates.

A high-performance Toggl Track agent skill optimized for token efficiency and reporting.

Fetches current weather from Open-Meteo API and automatically captures a live webcam image from Meteoblue or Windy for the requested location. Use it when the user asks for the weather and wants to see a real image of the current conditions.

Standard workflow for ACMG/AMP germline small-variant classification — collect evidence, assign criteria, detect conflicts, and produce a review-ready classification summary. Use when a user wants a structured ACMG/AMP-style interpretation workflow for a germline SNV/indel, including guided evidence intake, criteria assignment, conflict handling, and provisional classification.

Find brands actively spending on influencer and creator campaigns. Scans trade press, Instagram, job boards, and news for active-spender signals, then outputs a scored, prioritized prospect list with contacts. Use when you need to find brands to pitch, identify active advertisers, build a prospect list, research which brands are hiring influencer marketers, or find companies launching creator campaigns. Triggers on: 'find brands to pitch,' 'prospect list,' 'who's spending on influencers,' 'brand prospects,' 'active advertisers,' 'campaign activity,' or any request to identify brands actively investing in creator/influencer marketing.

Track outreach pitches and draft contextual follow-up emails. Monitors a pitch tracker (Google Sheet or local markdown), checks Gmail for replies, flags stale pitches, and drafts tiered follow-ups (Day 3, Day 7, Day 14) that reference the original pitch content. Use when you need to check on pitch follow-ups, draft follow-up emails, review outreach status, find pitches without replies, or manage an outreach pipeline. Triggers on: 'check follow-ups,' 'who hasn't replied,' 'draft follow-ups,' 'outreach status,' 'pitch tracker,' 'stale pitches,' or any request to manage pitch/outreach follow-up.

Spin up unblocked browser sessions via Browser.cash for web automation. Sessions bypass anti-bot protections (Cloudflare, DataDome, etc.) making them ideal for scraping and automation.

Use this skill when preparing candidates for Web3 product manager interviews, especially wallet, exchange, DeFi, DEX, on-chain data, growth, AI Wallet, Agentic Wallet, senior PM, product lead, or product director roles. It analyzes target JDs, maps candidate experience to role requirements, builds interview narratives, generates round-specific playbooks and question banks, runs mock interview scoring, and prepares case or 30/60/90-day plans.