AI & ML

zoom-skills Bundle

Zoom Meeting SDK for Android native apps. Use when embedding Zoom meetings in Android with default/custom UI, PKCE + SDK auth, join/start flows, and Meeting SDK API integration.

zoom-skills Bundle

Zoom Meeting SDK for Windows - Native C++ SDK for embedding Zoom meetings into Windows desktop applications. Supports custom UI architecture with raw video/audio data, headless bots, and deep integration with meeting features. Includes SDK architecture patterns and Windows message loop handling.

zoom-skills Bundle

Zoom Whiteboard MCP server guidance. Use for Whiteboard MCP auth, endpoints, ID mapping, and tool workflows for creating, reading, listing, and sharing Whiteboards. Prefer this child skill when the request is specifically about Whiteboard MCP rather than general Zoom MCP.

zoom-skills Bundle

Zoom Meeting SDK for Electron desktop applications. Use when embedding Zoom meetings in an Electron app with the Node addon wrapper, JWT auth, join/start flows, settings controllers, and raw data integration.

zoom-skills Bundle

Zoom Virtual Agent Android integration via WebView. Use for Java/Kotlin bridge callbacks, native URL handling, support_handoff relay, and lifecycle-safe embedding.

kevinslin-skills Bundle

Record, sync, and query local agent activity ledger entries.

echoleesong Skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

eron1703 Skill

Testing agent for running tests, capturing results, and reporting pass/fail status

eron1703 Skill

Database agent for schema changes, migrations, and data operations

eron1703 Skill

What to do when a worker agent gets stuck

eron1703 Skill

Resume pattern and agent monitoring for supervisor-worker communication

zoom-skills Bundle

Zoom Revenue Accelerator MCP server guidance for conversation transcripts and analysis, scorecards, deals, customer accounts/contacts, indicators, teams, and users. Use when an AI agent needs read-oriented ZRA sales intelligence through the dedicated MCP endpoint.

erwinkn Bundle

erwin's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for erwin, /erwin-mode, or requests to work in this style.

kevinslin-skills Bundle

Automate browser navigation, interaction, screenshots, and extraction.

kevinslin-skills Bundle

Summarize Codex activity from the agent ledger.

dammianmiller Skill

C++ development worker for llama.cpp speculative decoding fixes, CUDA builds, and server validation

dammianmiller Bundle

Expert Unreal Engine 5 developer and technical artist for complete game development via agentic coding. Enables AI-driven control of Unreal Editor through MCP, Python scripting, Blueprints, and C++ for level design, asset management, gameplay programming, and visual development.

dammianmiller Skill

Use the shared collaboration board to coordinate with other agents — post findings, dead-ends, integrity flags, and handoffs, and read peers' posts before starting work. Use whenever multiple agents work the same repo/goal, or when you discover something other agents should know (a result, a tried-and-failed approach, a verification concern).

draculabo Skill

Comprehensive guide to Antigravity Manager architecture, workflows, and development. Use this to understand how to work on the project.

erwinkn Skill

Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.

erwinkn Bundle

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.

erwinkn Skill

Pre-merge audit of the choices made during implementation, not the code itself. Use before any commit, PR, or merge of agent-implemented work, or when the user says "audit your choices", "which decisions did you make", "pride gate", or asks whether you stand behind the work.

ketomihine Bundle

Comprehensive skill for CellPhoneDB - Database of cell type markers and cell-cell communication analysis for single-cell data. Use for cell type annotation, ligand-receptor analysis, cell-cell interaction inference, and communication network visualization.

kevinslin-skills Bundle

Find, map, or resume Codex CLI sessions.

willyu1007 Bundle

Evidence-driven debugging loop with mandatory instrumentation + fix approvals, run_id-tagged logs, default 3-pass verification for flaky issues, and guaranteed cleanup of debug-only instrumentation.

thkt Skill

Internal helper for /pr. Reads PR body (Preview URL + How to Test), drives agent-browser to capture a screenshot (1 step) or a video (2+ steps), and returns the artifact path that /pr passes to gh pr create --attach.

pr-pm Skill

Use when creating Zed extensions with custom slash commands, language support, themes, or MCP servers - provides Rust/WASM extension structure, slash command API (run_slash_command, SlashCommandOutput), and development workflow for compiled extensions

aeyeops Bundle

Use when writing, reviewing, debugging, or rewriting instructions that Claude itself will read — CLAUDE.md files, skill files (SKILL.md, frontmatter descriptions), slash command templates (.claude/commands/*.md), and agent definitions (.claude/agents/*.md) — and when converting docs or runbooks into skills, drafting agent frontmatter from scratch, or asking what is "pulling weight" in a prompt. Symptoms it covers: an agent firing too often or on the wrong things, a prompt that is too long or full of MUST/NEVER/ALWAYS, Claude ignoring sections of a command, agents looping on tools instead of stopping, skills not activating, and descriptions that do not trigger correctly. Not for general code review, MCP server design, hook scripts, or API/SDK questions unless the artifact under discussion is a prompt Claude reads.

aeyeops Bundle

Use when building autonomous AI agents in Python with the Claude Agent SDK — programmatic agents, tool chains, or multi-agent systems — and when deciding which SDK API or option a task needs. Covers the GTVR execution pattern (gather, take action, verify, repeat), the stateless query() and stateful ClaudeSDKClient APIs, streaming versus batch modes, custom tool creation with the @tool decorator, MCP server integration, hook-based execution control, permission boundaries, API key and OAuth token management, multi-agent coordination, and production deployment strategies. Not designed for basic chat interfaces.

biwakonbu Skill

Use when creating, updating, or maintaining agents, understanding agent structure, or implementing subagents. Also use when user says エージェント, サブエージェント, agents. Claude Code プラグインの agent 仕様知識で、サブエージェントの正しい形式、フロントマター、tools/model/skills フィールドを提供する。

biwakonbu Skill

Use when creating, updating, or maintaining commands, understanding command structure, or implementing slash commands. Also use when user says コマンド, スラッシュコマンド, commands. Claude Code プラグインの command 仕様知識で、スラッシュコマンドの正しい形式、フロントマター、変数、model 指定を提供する。

biwakonbu Skill

Use when user asks about Workers AI, AI models, Vectorize, AI Gateway, LLM, image generation, speech recognition, embeddings, or RAG. Also use when user says Workers AI, AI モデル, ベクトル検索, 埋め込み, RAG. Cloudflare Workers AI の完全ガイドで、利用可能モデル（LLM、画像、音声、埋め込み）、Vectorize、AI Gateway の使い方と設定を提供する。

jason-easyazz Skill

Schedule proactive push notifications and one-shot nudges for users. Use when the user asks for a future reminder, notification, alert, or nudge like 'remind me at 3pm' or 'notify me tomorrow morning'.

jason-easyazz Skill

Run Karpathy-style fixed-budget optimization loops for one approved asset and one objective score. Use when the user asks to optimize, auto-research, run overnight experiments, improve a prompt/tool/copy/config, or turn 'is it good?' into a number.

jason-easyazz Skill

Use for all Zoe engineering work. Makes Hermes the default agent for Zoe planning, implementation strategy, code review, Greptile loops, Graphify-first codebase navigation, and repair work.

jason-easyazz Skill

Use Zoe's local CloakBrowser stealth Chromium through the zoe-tools MCP server for browser research, bot-protected pages, screenshots, and former OpenClaw browser workflows.