Skill rating

reddi.tech fork of self-improving-agent. Captures learnings, errors, and corrections to enable continuous improvement. Use when: a command fails, user corrects Claude, a capability is missing, an exte

For stores selling necessity/utility products (car storage, kitchen tools, storage and cleaning tools). Uses VOC-based selection (voice of customer from reviews) for selection and improvement and outp

Create and manage LLM-powered personal knowledge bases using Karpathy's wiki method. Use when users want to build a knowledge base, ingest sources, query their wiki, or maintain an Obsidian-compatible

Create a new skill through a guided conversation. Use when a user wants help authoring a skill from scratch, choosing between quick or full guidance, analyzing documentation to extract behavior patter

Create and verify no-thinking variants of local Qwen/Qwen3-series Ollama models. Use when a user asks to disable thinking, hide or remove think-tag output, make /no_think the default, create a non-thi

Scrape government permit databases (liquor licenses, business registrations, contractor permits, health permits) to generate B2B sales leads. Enriches raw permit data with business emails via web scra

NotebookLM Distiller: Batch knowledge extraction from Google NotebookLM into Obsidian. Supports Q&A generation (15-20 deep questions), structured summaries, glossary extraction, web research sessions,

Access OlaXBT Nexus cryptocurrency data APIs — market data, news, KOL tracking, technical indicators, and trading insights. Uses a wallet-linked JWT; no private key in the skill.

KallyAI Executive Assistant — AI that handles phone calls (outbound + inbound), email, bookings, research, errands, multi-channel messaging, and phone number management on your behalf. Use when users

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 int

Extract structured real-estate lead records from parsed message objects. Use when users ask to find leads in WhatsApp exports, extract name-phone-budget, or classify listing vs requirement posts. Reco

Turn rough creative briefs into structured Seedance video prompt packs, reference-aware motion plans, focused variants, and debugging loops. Use for text-to-video, image-to-video, video-to-video, firs

初始化并启动 Chrome DevTools Protocol（CDP）模式，支持用 Playwright 和 browser-use Agent 远程控制真实 Chrome 浏览器。解决 Chrome 145+ App-Bound Encryption 限制，自动复制 Profile 到非默认路径以启用 CDP。适合自动化网页操作、数据提取、Form 填表、爬虫等场景。

Submit completed work for a task on OpenAnt. Submission = text description + files. IMPORTANT — before submitting, always check if your work produced any files and upload them first. Use when the agen

Search and browse tasks on OpenAnt. Use when the agent or user wants to find available work, discover bounties, list open tasks, filter by skills or tags, check what tasks are available, or look up a

Generate a structured help-request document when stuck with AI coding. Scans specified conversation sessions, extracts errors and failed attempts, outputs a clean HELP_REQUEST.md. Triggers on "stuck",

Uses dupe.com APIs in order to find similar products for the product found in the input URL given by the user.

License compliance for your own repos. Ensures correct copyright headers, dual-license blocks, and LICENSE files across all source files.

Interactive hiring wizard to set up a new AI team member. Guides the user through role design via conversation, generates agent identity files, and optionally sets up performance reviews. Use when the

End-to-end voice workflow with Deepgram STT and TTS. Use when transcribing voice messages, generating spoken replies, or building a shell-based audio pipeline that turns input audio into text and opti

Query DeepWiki MCP to get AI-grounded answers about any public GitHub repository. Use when answering questions about a repo's source code, architecture, configuration, or internals. Triggers on "how d

Use when the user has 2+ recordings of the same event (each with a `.sync.json` sidecar from wjs-syncing-multicam) and wants them combined into a single MP4 — auto-switching between cams second-by-sec

One-click skill publishing automation covering duplicate check, Bear notes sync, and GitHub push. Use when publishing a new or updated skill to ClawHub and GitHub, or when the user says "publish skill

Dune Analytics API skill for querying, analyzing, and uploading blockchain data. Use this skill whenever the user mentions Dune, on-chain data, blockchain analytics, token trading volume, DEX activity

LoongFlow brings evolutionary multi-agent optimization to your coding agent harness. Drop it into Codex, Claude Code, Cursor or any OpenClaw agent — then watch PEES (Plan-Execute-Evaluate-Summary) ite

Given a task an AI agent needs to perform, find the right agent-native service from the awesome-agent-native-services catalog. Surfaces how to USE each service — including which ones an agent can join

CLI for VibeSKU — an AI-powered creative automation platform that turns product SKU photos into professional e-commerce visuals and marketplace-ready copy at scale. Use when the user wants to: (1) gen

Meta Ads data analysis and reporting via meta-ads-open-cli. Use when the user wants to check Meta/Facebook/Instagram ad performance, pull campaign/ad set/ad stats, explore ad account structure, inspec

Real-time token monitoring for MRC canteen order system. Monitors Firebase Firestore for token status and notifies when orders are ready. Use when user sends commands like "mrc 73", "token 97", or "mo

Operate and assist across Chile's Mercado Público / ChileCompra supplier workflows using both the public API and the private supplier portal. Use when searching, listing, monitoring, or reporting on l

Use when a user wants to rehearse a high-pressure conversation such as a performance review, reporting meeting, promotion defense, difficult manager conversation, or stakeholder alignment session, usi

Understand website goals and user journeys first, then analyze GSC/GA4 data and audit the live site to validate whether users behave as intended. Identify gaps between goals and reality, and produce a

Create and switch between AI assistant personalities. Use /personality to list and activate saved personalities. Use /create-personality to design new personas with auto-filled SOUL and IDENTITY. Pers

Monitor ClawHub skill performance with file-based state tracking. Fetches public stats via web_fetch, tracks recommendations and their outcomes, avoids repetitive suggestions. Day-of-week rotation for

Conduct evidence-based research with exact, accurate APA citations using the Gemini API's 'scientific citation' (Google Search grounding) feature. Use when Xiaoyan (Research Assistant) or others need

Score and optimize tweets based on X's real open-source ranking algorithm. Analyzes draft tweets against the actual ranking code — not generic tips. Use when: composing tweets, optimizing drafts for r

Download individual songs from a DJ set or mix. Given a link from YouTube, SoundCloud, Mixcloud, or 1001Tracklists, extract the tracklist from the page description or metadata, then look up and downlo

Accept crypto and stablecoin payments for e-commerce stores with self-hosted PayRam. Use when building "crypto e-commerce", "Shopify crypto integration", "accept USDC for products", "WooCommerce crypt

Agent identity provider — own email address and E2E-encrypted credential vault. Use when storing or retrieving passwords for services, logging into services with stored credentials, checking email inb

Scan and analyze installed skills. Use when user wants to (1) scan a specific skill directory to view its name, description, and details, or (2) scan all installed skills to list all available skills

Lightweight session logging for OpenClaw agents. Automatically creates a timestamped session file on every session start (including /new resets) and appends topic summaries during conversation. Solves

Use when managing Crunch coordinators, competitions (crunches), rewards, checkpoints, staking, or cruncher accounts via the crunch-cli.

Delegate coding tasks to Sourcegraph Amp, an autonomous coding agent. Use when: multi-file changes, new features, bug fixes, test writing, or any coding task > ~5 minutes. Amp reads the codebase, plan

Transcribe YouTube videos with smart fallback: extracts captions first (fast, free), falls back to local Whisper transcription when no captions available. Auto-detects best Whisper backend (MLX/faster

Convert Telegram chat exports into a long screenshot-style image. Supports Telegram Desktop JSON exports with bubble-style message rendering, avatars, timestamps, and proper text wrapping. Use when us

Extracts durable workflow preferences and project conventions from a session, then proposes the smallest valid update to global or project CLAUDE.md files. Trigger when the user asks to remember rules

Export the agent core from supported framework repositories into a small source-only zip for AI migration or cross-framework analysis. Use when the user wants to detect supported agent repos, extract

Professional property valuation for Taiwan real estate using market comparison approach and floor area pricing. Analyzes 實價登錄 data, adjusts for location, floor level, building age, parking space deduc

Public OpenClaw skill for low-token routing and downstream analysis of processed DDA LFQ proteomics inputs. Use when the user already has protein-level quantification tables such as MaxQuant-style `pr

generate Moon Lovers style romantic chat replies from a character profile for fictional character roleplay. supports 8 character profiles (四大美人 Xishi, Wang Zhaojun, Diaochan, Yang Yuhuan + 四大美男 Pan An