Total 50,708 skills, AI & Machine Learning has 8496 skills
Showing 12 of 8496 skills
Parent skill. Focuses on researching personal judgment, methodology, system capability and brand equity building in the AI era. Responsible for overall positioning control and task distribution.
Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any problem with 'IMO', 'Putnam', 'USAMO', 'olympiad', or 'competition math' in it. Uses pure reasoning (no tools) — then a fresh-context adversarial verifier attacks the proof using specific failure patterns, not generic 'check logic'. Outputs calibrated confidence — will say 'no confident solution' rather than bluff. If LaTeX is available, produces a clean PDF after verification passes.
Cross-device real-time collaboration tool for strict turn-based 1:1 messaging with another AI agent via a relay server. Use when the user asks you to collaborate with an agent on another device, send a direct message to a remote agent, or coordinate work across machines using a shared token. Short name: Agent DM.
Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.
Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall', 'irrelevant matches', 'missing expected results', or asks 'how to improve search quality?', 'which embedding model?', 'should I use hybrid search?', 'should I use reranking?'. Also use when search quality degrades after quantization, model change, or data growth.
Main entry point for Langgeladi ASOP. It automatically routes to the most appropriate diagnostic tool based on your question. Trigger methods: /lang, /langgeladi, "help me diagnose", "I want to AI-ify", "take a look for me" Main entry point for langgeladi ASOP. Auto-routes to the best diagnostic tool. Trigger: /lang, /langgeladi, "help me diagnose", "I want to AI-ify my business"
Langgeladi Cognition Check. Two modes: Trace (an idea → trace to the bottom layer → build a system) and Topple (a wrong cognition → flip → see the truth). Trigger methods: /lang-think, "I have an idea", "I think XX is because of YY", "help me figure this out", "is this view correct" Langgeladi cognition check. Two modes: Trace (idea → first principles → system) and Topple (wrong belief → flip → truth). Trigger: /lang-think, "I have an idea", "help me think this through", "is this right"
A natural language workflow for converting literary works (novels, stories, scripts, one-sentence concepts, etc.) into film and video content, which converts novel content into complete videos by orchestrating multiple skills in sequence. This skill is used when users need to convert novels, stories or other literary works into videos.
Northeast Yujie Buddy Pet. TUI-style virtual pet interaction, responds in Northeastern Chinese dialect. Trigger methods: /yujie, "雨姐", "东北雨姐" Dongbei Yujie virtual buddy pet with TUI display and interactive commands. Trigger: /yujie, "雨姐", "东北雨姐"
Better Harness Tools for Claude Code — a Python (and in-progress Rust) rewrite of the Claude Code agent harness, with CLI tooling for manifest inspection, parity auditing, and tool/command inventory.
Connect Codex CLI as an MCP server — giving you codex_run and codex_review as native tool calls instead of black-box bash commands. codex_run covers six modes: explore (broad codebase discovery), inspect (targeted read-only and injected-context follow-up), build (write/edit code), debug (reproduce→diagnose→fix→verify), test (write/run tests), research (web search only). codex_review runs independent code review in an isolated thread. Each mode bakes in task-specific instructions so Codex performs well per task type. Use this skill whenever the user mentions: "set up codex MCP", "connect codex to claude", "codex MCP server", "install codex tools", "configure codex integration", or wants Codex available as native tools in any agent. Distributed via `npx skills add` — no global install needed.
OpenClaw Task Protocol Worker skill. Access the OpenClaw distributed task network, automatically poll for available tasks, claim, execute and submit results. Trigger keywords:「claim task」「view task」「access task network」「openclaw task」「task protocol」「be a lobster」「do task」 When to use: (1) Agent needs to access the OpenClaw task network to claim and complete tasks, (2) User requests to view/claim/submit tasks, (3) User wants to create tasks as a publisher for other lobsters to complete, (4) Any operations involving the OpenClaw distributed content publishing protocol.