Browse the skill radar
Search by skill, publisher, category, or trust summary — then use the runtime filters to find cards with live test evidence. The two main lanes are baseline safety checks first and deeper follow-on functionality checks after that.
✨ Quick picks
🏷 Categories · coding-agents-and-ides
🧾 Evidence level: source-scanned means local source evidence; catalog-only means thinner metadata-first coverage.
🧪 Runtime status: cards can show only the baseline safety lane or the deeper follow-on functionality lane, depending on how far the skill got.
📏 Depth cue: tells you whether the evidence stops at baseline checks, includes follow-on functionality checks, or includes richer fixture/example proof.
⏱ Freshness cue: tells you whether the latest runtime evidence is from the last 24 hours, the last 7 days, or is older and therefore less current.
🩺 Failure confidence: distinguishes a first seen failure from a repeated failure or a regression after an earlier pass, so not every red row means the same thing.
Results
ralstp-consultant
Analyze problems using RALSTP (Recursive Agents and Landmarks Strategic-Tactical Planning). Based on PhD thesis by Dorian Buksz (RALSTP). Identifies agents, calculates difficulty, and suggests decomposition.
+ 1 more
salai-mcp
Israeli grocery shopping and price-comparison assistant over Salai MCP. Use when you need product search, autocomplete, cross-retailer price comparison, cart management, store discovery, retailer discovery, and complementary product recommendations through the Salai remote MCP endpoint.
+ 1 more
sec-watcher
Monitor SEC EDGAR filings for AI/tech companies in real time. Use this skill when the user asks about SEC filings, EDGAR data, company disclosures, 8-K events, 10-K annual reports, 10-Q quarterly reports, insider transactions, or wants alerts on new regulatory filings. Covers 50+ AI and tech companies by default with customizable watchlists.
+ 1 more
semver-helper
Semantic Versioning 2.0.0 reference guide. Quick decision trees and examples for choosing MAJOR, MINOR, or PATCH version bumps.
+ 1 more
skills-ttt
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like \"create a skill\", \"new skill\", \"make a skill\", \"skill for X\", \"how do I create a skill\", or \"help me build a skill\".
+ 1 more
soul-audit
|
+ 1 more
telegram-multilingual-voice-reply
Smart Telegram reply workflow for OpenClaw: if the user sends text, reply with text; if the user sends a voice note/audio, transcribe locally using the installed mlx_audio (default Qwen3-ASR on Apple Silicon), then generate a meaningful reply in the same language. Send back a Telegram voice note with a caption so the user receives ONE message containing both voice+text (the caption text must match the voice content exactly). Follow the input language (Chinese→Chinese, English→English) unless the user explicitly requests a different language.
+ 1 more
tg-media-resolve
Resolve Telegram <media:image>, <media:document>, <media:video> and other media placeholders into actual files for vision/analysis. Use when a Telegram message contains a media placeholder (e.g. <media:image>) that you cannot see — typically in quoted/replied-to messages or group chat history. Downloads the media via Telegram Bot API and returns a local file path for the image tool or further processing.
+ 1 more
token-monitor
Monitor OpenClaw token/quota usage and alert when any quota drops below a threshold (default 20%). Uses `openclaw models status` and writes only a local state file to avoid duplicate alerts. **Does not handle secrets.** **Token cost:** Script itself: 0 tokens (pure bash). Heartbeat integration: ~1k-2k tokens/hour (reading HEARTBEAT.md + executing script). Alert delivery: ~500-1k tokens/alert. **Optimization:** Use system cron instead of heartbeat to reduce to ~0 tokens (except alerts).
+ 1 more
token-watch
**Track, analyze, and optimize token usage and costs across AI providers. Set budgets, get alerts, compare models, and reduce your spend.**
+ 1 more
trackyard
Search and download licensed music from Trackyard's AI-powered catalog. Use for finding background music for videos, social content, podcasts, or any project needing royalty-free tracks. Supports natural language search ("upbeat electronic for tech video"), smart audio trimming to exact durations with hit-point alignment, and filtering by genre, mood, BPM, vocals, energy, and instruments.
+ 1 more
twitter-autopilot
Automate Twitter/X posting, engagement, and growth for OpenClaw AI agents. Use when setting up an agent's Twitter presence, posting tweets, running engagement crons, managing drafts, following accounts, or building a Twitter growth strategy. Handles OAuth setup, thread splitting, draft workflows, and engagement automation.
+ 1 more
verify-before-done
Require fresh verification evidence before claiming work is complete. Use ALWAYS before any completion claim, commit, push, PR, or status report. Prevents false completion claims.
+ 1 more
voice-assistant
Real-time voice assistant for OpenClaw. Streams mic audio through configurable STT (Deepgram or ElevenLabs) into your OpenClaw agent, then speaks the response via configurable TTS (Deepgram Aura or ElevenLabs). Sub-2s time-to-first-audio with full streaming at every stage.
+ 1 more
wa-relay-skill
WhatsApp message relay for OpenClaw v0.2.0. Routes third-party DMs to a relay agent that forwards them to the main agent via sessions_send. The main agent notifies the owner with a suggested response. Supports direct number allowlists.
+ 1 more
xiaohongshu-ops
End-to-end Xiaohongshu operations including positioning, topic research, content production, publish execution, and post-incident recovery. Reusable across verticals with templates and a concrete 陪你看剧 case preset.
+ 1 more
youtube-video-finder
author: upintheairsheep
+ 1 more
ai-usage
|
+ 1 more
buffer-session
Session management for OpenClaw agents. Context monitoring, structured handoffs, and performance optimization — so you never lose context again.
+ 1 more
didit-id-verification
>
+ 1 more
dj-set-ripper
>
+ 1 more
dzen
Publish articles and posts to Dzen.ru (Yandex Zen). Supports text, images, and videos. Requires session cookies and a CSRF token from a logged-in browser session.
+ 1 more
launchthatbot-git-team-ops
Role-based GitOps skill for OpenClaw agents with junior and senior operating modes.
+ 1 more
leadership-prompts
>