AI Agent Skills

Multi-agent orchestration for AI coding agents — pluggable runtime adapters for Claude Code, Pi, and more

Analyze a ticker with AlphaGBMs five-pillar framework: fundamentals, technicals, sentiment, flows, and valuation.

Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows,…

Football pitch plotting and soccer analytics visuals for match reports and dashboards.

Every past session, subagent, and workflow -- queryable by your agent, browsable by you

Deep learning gateway on Raspberry Pi and other edge devices

Generate topic-first, two-part video-title candidates from an approved video brief or final script.

SiteWhere is an industrial strength open-source application enablement platform for the Internet of Things (IoT). It provides a multi-tenant microservice-based infrastru…

Install and configure the generic and optional Effect anti-slop Oxlint plugins in a local TypeScript or JavaScript repository. Use whenever a user asks to add anti-slop…

Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks. Use for "run every N minutes", "schedule a task", "run on a loop",…

Control the cmux macOS terminal app (CLI + socket API) — cmux workspaces, panes, surfaces, browser automation, notifications, settings, hooks. MUST be read before runnin…

Query-driven targeted ingest from a specific AI agent's raw history. Use this skill when the user invokes /wiki-claude, /wiki-codex, /wiki-hermes, /wiki-openclaw, /wiki-…

Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launc…

Unified wiki-history-ingest entrypoint for conversation/session sources. Use this when the user says "/wiki-history-ingest claude", "/wiki-history-ingest copilot", "/wik…

[omh] Agent instruction file for a repo -- AGENTS.md, CLAUDE.md, a Cursor rule: write or update what an agent cannot derive from the code, inside a marked region, with e…

[omh] Uncertain technical choice for a spike: bounded decision prototype workflow: resolve one uncertain interaction, API, performance, or integration choice with a disp…