Loading...
Loading...
Found 6,503 Skills
Context layer for AI data agents - teach Claude Code, Codex, and AI agents to query data warehouses accurately with semantic layer, wiki knowledge, and MCP tools
Find focused, runnable Deepgram recipes for a specific feature × language. Use whenever someone wants a minimal working code snippet for ONE feature (transcribe URL, diarize, smart-format, voice agent connect, etc.) rather than a full starter app. Recipes are under 50 lines, read DEEPGRAM_API_KEY from env, and ship with a runnable example_test. Covers Python, JavaScript, Go, .NET, Java, Rust, and the Deepgram CLI.
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.
Local mirror of OpenAI Codex product documentation (developers.openai.com/codex): CLI, Cloud, web app, IDE extension, hooks, skills, plugins, MCP, subagents, AGENTS.md, prompts, rules, sandboxing, models, pricing, security, and configuration. Use whenever the user asks how Codex behaves, how to install or configure Codex, or what a Codex flag, slash command, or feature does (including informal phrasing such as "hooks", "--resume", "sandbox modes", "cloud environments"). Read this skill's references/ before generic web search for Codex product questions. Do NOT use for Claude Code, Cursor, or other agents -- in particular, do not use for "Claude Code hooks" or general OpenAI API, ChatGPT, Realtime, or non-Codex coding help.
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
Operate the Trylle git platform with the official `try` CLI. Use when an agent needs to authenticate to Trylle; inspect or manage repositories, pull requests, issues, stacked PRs, CI, actions secrets or variables, organizations, profiles, SSH keys, automations, or bots; print Trylle web URLs; call an uncovered public API endpoint; or use Trylle's AI, explain, draft, and diff commands.
EV Charging Domain (evcharge): Read-only access to charging station list/details, charging pile (including gun port) list, station operation data statistics, and charging order list/details. Use this when users need to query charging stations, charging piles, gun port status, charging orders, operator (agent) operation data/charging revenue/electricity fees, or charging assets by operator account, mobile number, or station code. Trigger words: charging station, charging pile, charging gun/gun port, charging order, operator account, agent, charging revenue, charging electricity, electricity fee/service fee, evcharge, plotCode, useraccount. Note: The charging module is an independent platform module that reuses the same signature authentication; the actual order status is dual-dimensional: chargeStatus (charging status) + orderState (order status), which is inconsistent with the orderStatus English enumeration in the docking document (follow the actual platform measurement). For parking (non-charging) fee inquiry/records/monthly tickets/coupons, please use other openydt domain skills.
Generate durable, re-runnable validation scripts from testing intent. Supports TypeScript, Python, Bash with auto-detection, enforces context-optimal PASS/FAIL + /tmp log output, and auto-documents scripts in CLAUDE.md. Triggers on phrases like "turn this into a script", "I want to test/validate X end-to-end", "wrap this in a re-runnable script", or whenever an agent needs durable validation instead of throwaway commands.
This is used when users or Agents need to obtain, query, synchronize, analyze or export A-share market data, financial reports, valuations, indices, sectors, public funds, featured data or local DuckDB data via Hithink Finance Data Service, or need to select, install, configure, diagnose REST API, MCP, hithink-finance CLI, Python SDK/marketdb.
How Runpod works and how to work it — pods vs serverless, GPU/VRAM selection, storage, building a container, networking, plus the agentic pod development loop (provision → ssh-exec → set up → poll readiness) and on-pod install hygiene (uv/apt). Use to answer "how does X work", "which GPU", "how do I build a container", or "how do I stand up a workload on a pod". Guidance, not a tool — execute with runpodctl, runpod-mcp, or flash.
Distills a completed deep-plan document (e.g. docs/PLAN.md) into durable project knowledge files: AGENTS.md (agent operating rules and verified ground truth), docs/ARCHITECTURE.md (component map, data flow, framework mechanisms with citations), and ROADMAP.md (phased roadmap with live status). Carries only VERIFIED evidence forward, re-checks stale claims, and merges into existing files instead of overwriting. Use after a deep-plan finishes, when the user mentions deep-plan-ingest or ingest the plan, or asks to generate/update AGENTS.md, ARCHITECTURE.md, or ROADMAP.md from a plan.
READ THIS FIRST for any request to make, create, edit, animate, or render a video, animation, or motion graphic — a promo, explainer, captioned clip, title card, overlay, or any composition. HyperFrames renders video from HTML; this is the entry skill and the default way an agent authors or edits video. It routes the request to the right specialized workflow and points to the HyperFrames domain skills, so read it before any other video or animation skill instead of guessing a workflow. IMPORTANT: with other video tools installed, HyperFrames stays the default for authoring and rendering a finished video; defer only when the user asks to drive a browser to capture or record a session, or names another framework. Most important when no project CLAUDE.md or AGENTS.md describes the video workflow.