Results for “bridge”

Bridge Codex to web-based AI model products by packaging local task context, scrub-checking it, sending it through an approved browser surface to ChatGPT Pro, Claude, Grok, Gemini, or another web model, waiting for the answer, and returning the model response to the user or Codex. Also guide DevSpace-like MCP Connector Mode when the user wants ChatGPT Pro or another MCP-capable web host to access approved local workspaces without relying on Codex browser automation. Use when the user asks for GPT Pro, ChatGPT Pro, Claude web, Grok, Gemini web, web model bridge, external model consult, ask another model, second opinion, use a web AI model, browserless agent access to GPT Pro, MCP connector, DevSpace-like workflow, or send local repo context to a browser-based model for planning, review, debugging, architecture discussion, or implementation guidance.

The English summary is being prepared. Showing the original description.

Process the batch of incoming Bridge Classroom feedback. Pull open `classroom-feedback` issues from the PBS repo, cluster them by defect class, verify each against the actual board, and fix at the right altitude — patch a single board, or (when a class recurs) build a gate, sweep the whole corpus, and regenerate/drop collectively. Engine bugs route to the Classroom repo; bridge-judgment calls go to Rick. Nothing leaves the machine without David's OK. Invoke as `/issue` (optionally with an issue number or scenario to restrict the run).

The English summary is being prepared. Showing the original description.

Control MARS/Innate robots over rosbridge WebSocket. Covers connecting to the robot, executing skills, moving the arm, driving the base, tilting the head, and reading sensors — all via JSON-over-WebSocket to rosbridge_server on port 9090. Use this skill whenever working with MARS robots, Innate OS, rosbridge, ROS2 robot control, maurice_arm, brain_client, or any project that talks to a robot over WebSocket. Also trigger when seeing imports from brain_client, brain_messages, maurice_msgs, or references to topics like /cmd_vel, /mars/arm, /brain/chat_in, /execute_skill.

The English summary is being prepared. Showing the original description.

agents-bridge — the Lifeboat, auch: Time Capsule. Portable, provider-neutral file bridge for bootstrap surfaces, truth pointers, separate memory silos, messaging, presence, cooperative locks, and reversible host recovery.

The English summary is being prepared. Showing the original description.

Review changes to the Agent Skills import/export bridge for path safety, round-trip fidelity, and validation correctness.

The English summary is being prepared. Showing the original description.

Use when working with Aws Eventbridge — aWS EventBridge event bus management, rule analysis, target health monitoring, and schema registry exploration. Covers event pattern matching, rule invocation metrics, dead-letter queue analysis, cross-account event routing, and event replay.

The English summary is being prepared. Showing the original description.

Quality-assure integrated tdmcp features: run the four PR gates + recipe/bridge tests, cross-boundary coherence checks (tool schema↔CLI↔docs↔registry, operator↔createable, bridge↔client), and live TouchDesigner validation (preview + post-cook error check) when the bridge is reachable. Use when validating/QA-ing/testing tdmcp tools, checking a feature actually cooks in TD, verifying CLI matches a tool, or gating a release.

The English summary is being prepared. Showing the original description.

Create Paperclip tasks, add progress comments, update statuses, and list assignments from Hermes. A helper uses API credentials with restricted permissions to keep task creation and updates within approved work boundaries.

• Creating child tasks under approved work
• Recording progress in Paperclip comments
• Updating review or blocked statuses

Import Claude Code auto-memory into AgentDB and search past notes by meaning across sessions and projects. The skill checks import status, consolidates near-duplicate entries, and returns search results with their memory sources identified.

• Search past notes across projects
• Import all project memories for the first time
• Consolidate near-duplicate memories

Store and retrieve knowledge across agent sessions with AgentDB. Organize memories into tiers, search learned patterns, combine related memories into context, and record causal links to support later work.

• Reuse knowledge from previous agent sessions
• Store and search learned patterns
• Combine related memories into context

Structure a post-acquisition improvement plan linking revenue, cost, and operational initiatives to EBITDA, a profit measure. Produce a roadmap with 100-day priorities, performance targets, responsible owners, and an Excel model showing each initiative’s profit contribution.

• Planning the first 100 days after an acquisition
• Mapping growth and cost initiatives to profit targets
• Preparing a value creation roadmap for the board

Build an investor fundraising presentation as a single PowerPoint file. The skill adapts the narrative, metrics, charts, and funding request to the company’s financing stage and business sector, with checks for numerical clarity and slide quality.

• Preparing a seed fundraising presentation
• Explaining growth metrics for a Series B round
• Presenting technical milestones for a deep tech raise

Embed Zoom meetings in React Native iOS and Android apps using @zoom/meetingsdk-react-native. Get guidance on setup, authentication, joining and starting meetings, cleanup, and troubleshooting communication between JavaScript and native SDK components.

• Adding Zoom meeting participation to a React Native app
• Implementing host meeting starts with ZAK
• Investigating iOS and Android setup or native bridge issues

Turn method notes or figure descriptions into academic architecture and concept illustrations. Claude plans and reviews the layout, while a local Codex bridge generates images, with refinement rounds and final PNG, LaTeX snippet, and review records.

• Illustrating a model architecture for a paper
• Turning method notes into a workflow diagram
• Creating concept or comparison figures

Create and edit CARLA driving routes by placing waypoints and scenario triggers in the simulator. Inspect routes visually, review summary tables, check XML structure and trigger positions, and convert older route files to the 2.x format.

• Create a short route for testing one scenario
• Investigate scenarios that never trigger
• Review route lengths and scenario types

Launch and control a real game to verify mods through screenshots and logs. Automate menus, keyboard and mouse input, and repeatable test scenes, with guidance for connecting an agent to game state through a JSON bridge.

• Verify a mod inside the running game
• Automate menu navigation and keyboard or mouse input
• Build a repeatable test or demo scene

Manage Mixpanel Headless login and connection settings, check credentials, and switch accounts, projects, or workspaces. Save named combinations of these settings as targets so an agent can select the intended connection together.

• Check the active account and project
• Set up login and test credentials
• Switch projects or workspaces

Manage a crypto wallet through the onchainos CLI, a command-line tool. Check balances, send or swap tokens, bridge assets between blockchains, manage limit orders, track transactions, and inspect token approvals and security risks.

• Check wallet balances and transaction history
• Send or swap tokens
• Move assets between blockchains and track arrival

Build token swaps and transfers within or across blockchains using the LI.FI REST API. Compare routes, prepare transactions, track transfer status, discover decentralized finance yields, and connect swaps or transfers with deposits into supported protocols.

• Comparing token swap and cross-chain transfer routes
• Implementing decentralized finance deposits and withdrawals
• Finding yield opportunities and reviewing holdings

Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

The English summary is being prepared. Showing the original description.

Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and Qwen3-Next long-context experiments.

The English summary is being prepared. Showing the original description.

Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

The English summary is being prepared. Showing the original description.

Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. Use for activation memory OOMs or regressions involving recompute_granularity, recompute_num_layers, recompute_modules, recompute_method, selective recompute, full recompute, or activation checkpointing.

The English summary is being prepared. Showing the original description.

Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.

The English summary is being prepared. Showing the original description.