Results for “bridge”

Optimizes MoE expert-parallel communication overlap in Megatron Bridge, covering dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.

Provides practical guidance for training Mixture-of-Experts Vision-Language Models in Megatron Bridge, comparing FSDP and 3D-parallel approaches with lessons from recent multimodal experiments.

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

Reduces peak GPU memory in Megatron Bridge training by applying expandable segments, parallelism resizing, activation recompute, and CPU offloading constraints.

Validate and configure packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs with correct context parallelism constraints.

Audits a project's agent configuration files, establishes a source-of-truth skills directory, normalizes naming, and generates bridge files to make the workspace consistent across Claude Code, Codex, Grok, and generic Agents.

Control Blender from the shell via Flue - a Python bridge to bpy without an MCP server.

How Hermes talks to Gas Town from outside the Mayor session — listing beads, slinging work to rigs, sending mail, escalating, all via the `gt` MCP server (Ophis Cobra→MCP bridge). Use whenever the user asks Hermes to dispatch agent work, check what the swarm is doing, or coordinate across rigs.

Per-group MCP JSON-RPC proxy routing AI tool calls to multiple backend MCP servers with tool group filtering

Executes Python code iteratively via an MCP bridge to produce verified results for calculations, data analysis, and task decomposition.

Executes Python code iteratively via an MCP bridge to produce verified results for calculations, data analysis, and task decomposition.

Use when the user wants to build, extend, or debug the Python MCP bridge that exposes Mermate actions and stage flows to OpenClaw or other MCP clients.

Scaffolds a new OpenAI Agents SDK agent with instructions, tools, API route, and bridge wiring, following existing project conventions.

Convert single-node PyTorch distributed scripts into multi-node Slurm sbatch jobs and debug common multi-node failures, covering srun-native and torch.distributed approaches, container setup, NCCL timeouts, and interactive allocation.

Control Philips Hue lights, scenes, rooms via OpenHue CLI.

Manage Shopify stores via GraphQL Admin and Storefront APIs using curl, with Bankr-native bridges for onchain data, x402 payments, and loyalty drops.

Discovers and executes bioinformatics tools from the Galaxy ecosystem via natural language, with multi-signal scoring, workflow templates, and reproducibility bundles.

Control tmux panes and communicate between AI agents. Use this skill whenever the user mentions tmux panes, cross-pane communication, sending messages to other agents, reading other panes, managing tmux sessions, or interacting with processes running in tmux. Includes tmux-bridge CLI for agent-to-agent messaging and raw tmux commands for direct session control.

BOB (Build on Bitcoin): hybrid Bitcoin/Ethereum L2 using OP Stack + Bitcoin security. Bridges to Bitcoin via threshold signatures + zk-proofs. USE WHEN: building cross-chain Bitcoin/Ethereum apps, evaluating BOB hybrid model.

Human interface agent that translates ecosystem activity into clear, actionable communication. Creates status briefings, decision requests, celebration reports, concern alerts, and opportunity summaries. Use for 'status update', 'brief me', 'what's happening', 'summarize progress', or when complex multi-agent work needs human-readable reporting.

After the learner demonstrates understanding of a concept, present near-transfer and far-transfer challenges. Use to test whether learning is portable or task-specific — this is what separates understanding from familiarity.

Controls a Chrome browser through the AIPex extension and MCP bridge, enabling navigation, clicking, form filling, screenshots, tab management, and content downloads.

This skill should be used when the user asks to "buy crypto", "sell tokens", "swap ETH", "trade on Base", "exchange tokens", "cross-chain swap", "bridge tokens", "convert ETH to WETH", or any token trading operation. Provides guidance on supported chains, amount formats, and swap operations.

Delegates a coding task to pi (dev/pi), a minimal terminal coding harness. This skill should be used when the user asks to "use pi", "run pi", "delegate to pi", "let pi handle this", "ask pi to", "have pi do", or invokes /pi:delegate. It bridges the current Claude Code context to the pi CLI, passing relevant files, git state, and the task description for execution by the pi-agent.

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow through the openai-docs skill or an official OpenAI documentation connector before generating code.

Integrate services or agent harnesses with the 33GOD Bloodbank event bus. Covers schemas in Bloodbank schemas/ and docs/event-naming.md, producing events (NATS preferred; Dapr, HTTP /publish, hookd_bridge alternatives), consuming events (NATS, Dapr, FastStream, event-toaster), and agent hook wiring through the canonical services/agent-hooks publisher. Use for event publish/consume, authoring schemas, integrating harnesses (Claude Code, Copilot CLI, OpenCode, Cursor, Aider, Codex CLI, Hermes), or debugging missing envelopes. Triggers: bloodbank, event bus, publish, subscribe, NATS subject, holyfields legacy, CloudEvents, event-toaster, ntfy.delo.sh/bloodbank, bloodbank.v1.agent.session.started, bloodbank.v1.agent.tool.completed, bloodbank.cmd.v1.agent.invocation.start. Skip for generic brokers, n8n, hindsight memory, or non-event-bus 33GOD.

Route web-game auto-playtesting with WAI Play (waiterve/wai-play): decide whether the next move is a testability check, authoring or repairing the `GameFlowAgentAPI` bridge, running a real browser playtest, reading the five-dimension quality report, or unblocking a key node the agent cannot reach. Use when the user wants an AI agent to actually play their HTML5 / canvas / vibe-coded web game and return reproducible evidence, scores, and fix suggestions across the five supported types (survivor-like, arcade shooter, platformer, puzzle/card, visual novel). Triggers on: wai-play, WAI Play, auto-playtest, AI plays my game, web game testing agent, GameFlowAgentAPI, GameFlowIntegration, jumpToScenario, game quality score, playtest evidence. Route Unity/Unreal frame-time work to `game-performance-profiler`, engine build failures to `game-build-log-triage`, human playtest notes to `game-demo-feedback-triage`, and generic browser automation to `browser-harness`.