agentsclimarketplace

Context & AI engineering

25,772 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Github copilot models

    pantheon-org/tekhne/skills/specialized/github-copilot-models Skill

    10★ repo

    Query and display available GitHub Copilot AI models with their capabilities, context limits, and features. Use when: "what models are available", "show copilot models", "list github models", "check model capabilities", "switch models". Examples: - user: "What models can I use with GitHub Copilot?" → fetch and display available models - user: "Show me models with vision support" → filter models by capability - user: "Which model has the largest context window?" → compare model specifications - user: "List all GPT-5 models" → filter by model family

  • Handoff

    maaarcooo/agent-skills/chatgpt-skills/handoff Skill

    no license10★ repo

    Create a structured handoff document for seamless continuity across Claude conversations. Use when the user explicitly asks to create a handoff, handover, or session transfer document, or signals they want to stop now and continue this work in a future conversation. Trigger phrases include: "create a handoff", "handoff document", "handover", "save session", "continue later", "session handoff", "transfer context", "let's pick this up tomorrow", "save this so we can continue next time", or "/handoff". Do NOT trigger for general conversation summaries, meeting notes, or when the user simply asks "summarise this conversation" without handoff/continuity intent. Do NOT trigger when the user uploads an existing handoff document to resume from — handoff documents are self-contained and carry their own resumption instructions; this skill is for creating them only.

  • Handoff

    maaarcooo/agent-skills/claude-ai-skills/handoff Skill

    no license10★ repo

    Create a structured handoff document for seamless continuity across Claude conversations. Use when the user explicitly asks to create a handoff, handover, or session transfer document, or signals they want to stop now and continue this work in a future conversation. Trigger phrases include: "create a handoff", "handoff document", "handover", "save session", "continue later", "session handoff", "transfer context", "let's pick this up tomorrow", "save this so we can continue next time", or "/handoff". Do NOT trigger for general conversation summaries, meeting notes, or when the user simply asks "summarise this conversation" without handoff/continuity intent. Do NOT trigger when the user uploads an existing handoff document to resume from — handoff documents are self-contained and carry their own resumption instructions; this skill is for creating them only.

  • Handoff

    maaarcooo/agent-skills/claude-code-skills/handoff Skill

    no license10★ repo

    Generate a structured handoff document for session continuity. Captures decisions, rationale, failed approaches, and next steps so a fresh session can continue without re-explanation.

  • Handoff

    maaarcooo/agent-skills/codex-skills/handoff Skill

    no license10★ repo

    Create a structured handoff document for Codex task continuity, capturing decisions, rationale, failed approaches, current state, and next steps so a fresh task can continue without re-explanation. Use when explicitly invoked with $handoff; text supplied alongside the invocation may identify a focus.

  • Handoff

    a-tokyo/agent-skills-harness/.agents/skills/handoff Skill

    10★ repo

    Compact the current conversation into a handoff document for another agent to pick up.

    The same file is in 13 other repositories

  • Llm council

    a-tokyo/agent-skills-harness/.agents/skills/llm-council Skill

    10★ repo

    Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.

    The same file is in 4 other repositories

  • Agent browser amwill

    autohandai/community-skills/agent-browser-amwill Skill

    10★ repo

    A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

  • Agent browser toolshell

    autohandai/community-skills/agent-browser-toolshell Skill

    10★ repo

    Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

    The same file is in 3 other repositories

  • Agent browser

    autohandai/community-skills/agent-browser Skill

    10★ repo

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

    The same file is in 1 other repository

  • Agent configuration

    autohandai/community-skills/agent-configuration Skill

    10★ repo

    AI agent configuration policy and security guide. Project description file writing, Hooks/Skills/Plugins setup, security policy, team shared workflow definition.

  • Agent email cli

    autohandai/community-skills/agent-email-cli Skill

    10★ repo

    Operate the agent-email CLI to create disposable inboxes, poll for new mail, retrieve full message details, and manage local mailbox profiles. Use when the user needs terminal-based email inbox access for LLM or agent automation workflows.

    The same file is in 4 other repositories

  • Agent evaluation

    autohandai/community-skills/agent-evaluation Skill

    10★ repo

    Design and implement comprehensive evaluation systems for AI agents. Use when building evals for coding agents, conversational agents, research agents, or computer-use agents. Covers grader types, benchmarks, 8-step roadmap, and production integration.

  • Agent tools

    autohandai/community-skills/agent-tools Skill

    10★ repo

    Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

    The same file is in 4 other repositories

  • Agentic development principles

    autohandai/community-skills/agentic-development-principles Skill

    10★ repo

    Universal principles for agentic development when collaborating with AI agents. Defines divide-and-conquer, context management, abstraction level selection, and an automation philosophy. Applicable to all AI coding tools.

  • Agentic workflow

    autohandai/community-skills/agentic-workflow Skill

    10★ repo

    Practical AI agent workflows and productivity techniques. Provides optimized patterns for daily development tasks such as commands, shortcuts, Git integration, MCP usage, and session management.

    The same file is in 3 other repositories

  • Analyzing memory dumps with volatility

    autohandai/community-skills/analyzing-memory-dumps-with-volatility Skill

    10★ repo

    Analyzes RAM memory dumps from compromised systems using the Volatility framework to identify malicious processes, injected code, network connections, loaded modules, and extracted credentials. Supports Windows, Linux, and macOS memory forensics. Activates for requests involving memory forensics, RAM analysis, volatile data examination, process injection detection, or memory-resident malware investigation.

    The same file is in 1 other repository

  • Analyzing memory forensics with lime and volatility

    autohandai/community-skills/analyzing-memory-forensics-with-lime-and-volatility Skill

    10★ repo

    Performs Linux memory acquisition using LiME (Linux Memory Extractor) kernel module and analysis with Volatility 3 framework. Extracts process lists, network connections, bash history, loaded kernel modules, and injected code from Linux memory images. Use when performing incident response on compromised Linux systems.

  • Azure hosted copilot sdk ms

    autohandai/community-skills/azure-hosted-copilot-sdk-ms Skill

    10★ repo

    Build and deploy GitHub Copilot SDK apps to Azure. USE FOR: build copilot app, create copilot app, copilot SDK, @github/copilot-sdk, scaffold copilot project, copilot-powered app, deploy copilot app, host on azure, azure model, BYOM, bring your own model, use my own model, azure openai model, DefaultAzureCredential, self-hosted model, copilot SDK service, chat app with copilot, copilot-sdk-service template, azd init copilot, CopilotClient, createSession, sendAndWait, GitHub Models API. DO NOT USE FOR: using Copilot (not building with it), Copilot Extensions, Azure Functions without Copilot, general web apps without copilot SDK, Foundry agent hosting (use microsoft-foundry skill), agent evaluation (use microsoft-foundry skill).

  • Azure hosted copilot sdk

    autohandai/community-skills/azure-hosted-copilot-sdk Skill

    10★ repo

    Build and deploy GitHub Copilot SDK apps to Azure. USE FOR: build copilot app, create copilot app, copilot SDK, @github/copilot-sdk, scaffold copilot project, copilot-powered app, deploy copilot app, host on azure, azure model, BYOM, bring your own model, use my own model, azure openai model, DefaultAzureCredential, self-hosted model, copilot SDK service, chat app with copilot, copilot-sdk-service template, azd init copilot, CopilotClient, createSession, sendAndWait, GitHub Models API. DO NOT USE FOR: using Copilot (not building with it), Copilot Extensions, Azure Functions without Copilot, general web apps without copilot SDK, Foundry agent hosting (use microsoft-foundry skill), agent evaluation (use microsoft-foundry skill).

  • Bmad orchestrator

    autohandai/community-skills/bmad-orchestrator Skill

    10★ repo

    Orchestrates BMAD workflows for structured AI-driven development. Routes work across Analysis, Planning, Solutioning, and Implementation phases.

  • Claude code java

    autohandai/community-skills/claude-code-java Skill

    10★ repo

    Use claude-code-java for reusable Java project agent infrastructure, conventions, testing, and migration workflows.

  • Claude skills for quarkus

    autohandai/community-skills/claude-skills-for-quarkus Skill

    10★ repo

    Use Claude skills for Quarkus to build domain-driven Quarkus applications and Java modernization workflows.

  • Conducting memory forensics with volatility

    autohandai/community-skills/conducting-memory-forensics-with-volatility Skill

    10★ repo

    Performs memory forensics analysis using Volatility 3 to extract evidence of malware execution, process injection, network connections, and credential theft from RAM dumps captured during incident response. Covers memory acquisition, process analysis, DLL inspection, and malware detection. Activates for requests involving memory forensics, RAM analysis, Volatility framework, memory dump investigation, volatile evidence analysis, or live memory acquisition.

    The same file is in 1 other repository

  • Copilot coding agent

    autohandai/community-skills/copilot-coding-agent Skill

    10★ repo

    GitHub Copilot Coding Agent automation. Apply the ai-copilot label to an issue → GitHub Actions auto-assigns Copilot via GraphQL → Copilot creates a Draft PR. One-click issue-to-PR pipeline.

    The same file is in 3 other repositories

  • Deploying edr agent with crowdstrike

    autohandai/community-skills/deploying-edr-agent-with-crowdstrike Skill

    10★ repo

    Deploys and configures CrowdStrike Falcon EDR agents across enterprise endpoints to enable real-time threat detection, behavioral analysis, and automated response. Use when onboarding endpoints to EDR coverage, configuring detection policies, or integrating Falcon telemetry with SIEM platforms. Activates for requests involving CrowdStrike deployment, Falcon sensor installation, EDR policy configuration, or endpoint detection and response.

    The same file is in 1 other repository

  • Dispatching parallel agents

    autohandai/community-skills/dispatching-parallel-agents Skill

    10★ repo

    Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    The same file is in 15 other repositories

  • Dotnet ai

    autohandai/community-skills/dotnet-ai Skill

    10★ repo

    AI and ML skills for .NET: technology selection, LLM integration, agentic workflows, RAG pipelines, MCP, and classic ML with ML.NET.

  • Enhance prompt

    autohandai/community-skills/enhance-prompt Skill

    10★ repo

    Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

    The same file is in 6 other repositories

  • Exploiting constrained delegation abuse

    autohandai/community-skills/exploiting-constrained-delegation-abuse Skill

    10★ repo

    Exploit Kerberos Constrained Delegation misconfigurations in Active Directory to impersonate privileged users via S4U2self and S4U2proxy extensions for lateral movement and privilege escalation.

  • Extracting config from agent tesla rat

    autohandai/community-skills/extracting-config-from-agent-tesla-rat Skill

    10★ repo

    Extract embedded configuration from Agent Tesla RAT samples including SMTP/FTP/Telegram exfiltration credentials, keylogger settings, and C2 endpoints using .NET decompilation and memory analysis.

  • Extracting credentials from memory dump

    autohandai/community-skills/extracting-credentials-from-memory-dump Skill

    10★ repo

    Extract cached credentials, password hashes, Kerberos tickets, and authentication tokens from memory dumps using Volatility and Mimikatz for forensic investigation.

    The same file is in 1 other repository

  • Extracting memory artifacts with rekall

    autohandai/community-skills/extracting-memory-artifacts-with-rekall Skill

    10★ repo

    Uses Rekall memory forensics framework to analyze memory dumps for process hollowing, injected code via VAD anomalies, hidden processes, and rootkit detection. Applies plugins like pslist, psscan, vadinfo, malfind, and dlllist to extract forensic artifacts from Windows memory images. Use during incident response memory analysis.

  • Firebase ai logic

    autohandai/community-skills/firebase-ai-logic Skill

    10★ repo

    Integrate Firebase AI Logic (Gemini in Firebase) for intelligent app features. Use when adding AI capabilities to Firebase apps, implementing generative AI features, or setting up Firebase AI SDK. Handles Firebase AI SDK setup, prompt engineering, and AI-powered features.

    The same file is in 3 other repositories

  • Hardening linux endpoint with cis benchmark

    autohandai/community-skills/hardening-linux-endpoint-with-cis-benchmark Skill

    10★ repo

    Hardens Linux endpoints using CIS Benchmark recommendations for Ubuntu, RHEL, and CentOS to reduce attack surface, enforce security baselines, and meet compliance requirements. Use when deploying new Linux servers, remediating audit findings, or establishing security baselines for Linux infrastructure. Activates for requests involving Linux hardening, CIS benchmarks for Linux, server security baselines, or Linux configuration compliance.

    The same file is in 1 other repository

  • Hardening windows endpoint with cis benchmark

    autohandai/community-skills/hardening-windows-endpoint-with-cis-benchmark Skill

    10★ repo

    Hardens Windows endpoints using CIS (Center for Internet Security) Benchmark recommendations to reduce attack surface, enforce security baselines, and meet compliance requirements. Use when deploying new Windows workstations or servers, remediating audit findings, or establishing organization-wide security baselines. Activates for requests involving Windows hardening, CIS benchmarks, GPO security baselines, or endpoint configuration compliance.

    The same file is in 1 other repository

  • Implementing memory protection with dep aslr

    autohandai/community-skills/implementing-memory-protection-with-dep-aslr Skill

    10★ repo

    Implements memory protection mechanisms including DEP (Data Execution Prevention), ASLR (Address Space Layout Randomization), CFG (Control Flow Guard), and other exploit mitigations to prevent memory corruption attacks. Use when hardening endpoints against buffer overflow exploits, ROP chains, and code injection. Activates for requests involving memory protection, exploit mitigation, DEP, ASLR, or CFG configuration.

  • Implementing policy as code with open policy agent

    autohandai/community-skills/implementing-policy-as-code-with-open-policy-agent Skill

    10★ repo

    This skill covers implementing Open Policy Agent (OPA) and Gatekeeper for policy-as-code enforcement in Kubernetes and CI/CD pipelines. It addresses writing Rego policies, deploying OPA Gatekeeper as a Kubernetes admission controller, testing policies in development, and integrating policy evaluation into deployment pipelines.

    The same file is in 1 other repository

  • Legacy modernization orchestrator

    autohandai/community-skills/legacy-modernization-orchestrator Skill

    10★ repo

    Orchestrate multi-agent legacy modernization assessment, planning, and code-conversion workflows.

  • Llm council

    autohandai/community-skills/llm-council Skill

    10★ repo

    Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.

    The same file is in 4 other repositories

  • Mcp builder

    autohandai/community-skills/mcp-builder Skill

    10★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

    The same file is in 42 other repositories

  • Nvidia megatron bridge perf memory tuning

    autohandai/community-skills/nvidia-megatron-bridge-perf-memory-tuning Skill

    10★ repo

    Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes.

  • Nvidia model optimizer accessing mlflow

    autohandai/community-skills/nvidia-model-optimizer-accessing-mlflow Skill

    10★ repo

    Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs by invocation ID, compare metrics across models, fetch artifacts (configs, logs, results), or set up the MLflow MCP server. ALWAYS triggers on mentions of MLflow, experiment results, run comparison, invocation IDs in the context of results, or MLflow MCP setup.

  • Nvidia model optimizer launching evals

    autohandai/community-skills/nvidia-model-optimizer-launching-evals Skill

    10★ repo

    Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals, analyzing or analysing runs or results, run directories or artifact paths on clusters, Slurm job issues, invocation IDs, or inspecting logs (client logs, server logs, SSH to cluster, tail logs, grep logs). Do NOT use for creating or modifying evaluation configs.

  • Nvidia nemo evaluator byob

    autohandai/community-skills/nvidia-nemo-evaluator-byob Skill

    10★ repo

    Create custom LLM evaluation benchmarks using the BYOB decorator framework. Use when the user wants to (1) create a new benchmark from a dataset, (2) pick or write a scorer, (3) compile and run a BYOB benchmark, (4) containerize a benchmark, or (5) use LLM-as-Judge evaluation. Triggers on mentions of BYOB, custom benchmark, bring your own benchmark, scorer, or benchmark compilation.

  • Nvidia nemo evaluator launcher accessing mlflow

    autohandai/community-skills/nvidia-nemo-evaluator-launcher-accessing-mlflow Skill

    10★ repo

    Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs by invocation ID, compare metrics across models, fetch artifacts (configs, logs, results), or set up the MLflow MCP server. ALWAYS triggers on mentions of MLflow, experiment results, run comparison, invocation IDs in the context of results, or MLflow MCP setup.

  • Nvidia nemo evaluator launcher launching evals

    autohandai/community-skills/nvidia-nemo-evaluator-launcher-launching-evals Skill

    10★ repo

    Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed runs, exporting artifacts and logs, and analyzing results. ALWAYS triggers on mentions of running evaluations, checking progress, debugging failed evals, analyzing or analysing runs or results, run directories or artifact paths on clusters, Slurm job issues, invocation IDs, or inspecting logs (client logs, server logs, SSH to cluster, tail logs, grep logs). Do NOT use for creating or modifying evaluation configs.

  • Nvidia nemo gym add benchmark

    autohandai/community-skills/nvidia-nemo-gym-add-benchmark Skill

    10★ repo

    'Guide for adding a new benchmark or training environment to NeMo-Gym. Use when the user asks to add, create, or integrate a benchmark, evaluation, training environment, or resources server into NeMo-Gym. Also use when wrapping an existing 3rd-party benchmark library. Covers the full workflow: data preparation, resources server implementation, agent wiring, YAML config, testing, and reward profiling (baselining). Triggered by: "add benchmark", "new resources server", "integrate benchmark", "wrap benchmark", "add training environment", "add eval".

  • Nvidia nemo rl session memory

    autohandai/community-skills/nvidia-nemo-rl-session-memory Skill

    10★ repo

    Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory.

  • Nvidia nemoclaw user agent skills

    autohandai/community-skills/nvidia-nemoclaw-user-agent-skills Skill

    10★ repo

    Describes the agent skills shipped with NemoClaw and how to access them by cloning the repository. Use when users ask about AI agent support, coding assistant integration, or the .agents/skills/ directory. Trigger keywords - nemoclaw agent skills, ai coding assistant, cursor, claude code, copilot.

  • Nvidia nemoclaw user configure inference

    autohandai/community-skills/nvidia-nemoclaw-user-configure-inference Skill

    10★ repo

    Connects NemoClaw to a local inference server. Use when setting up Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible local model server with NemoClaw. Trigger keywords - nemoclaw local inference, ollama nemoclaw, vllm nemoclaw, local model server, openai compatible endpoint, switch nemoclaw inference model, change inference runtime, nemoclaw additional model, nemoclaw sub-agent model, openclaw sub-agent, agents.list, sessions_spawn, vlm-demo, nemoclaw tool calling, ollama tool calls, vllm tool-call-parser, raw json in tui, nemoclaw inference options, nemoclaw onboarding providers, nemoclaw inference routing.

  • Nvidia nemotron voice agent deploy

    autohandai/community-skills/nvidia-nemotron-voice-agent-deploy Skill

    10★ repo

    Deploy Nemotron Voice Agent on Workstation (x86), Jetson Thor, or Cloud NIMs. Real-time speech-to-speech using NVIDIA ASR, TTS, LLM with WebRTC/WebSocket transport.

  • Nvidia rag blueprint

    autohandai/community-skills/nvidia-rag-blueprint Skill

    10★ repo

    NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, and more).

  • Nvidia tensorrt llm ad accuracy debug

    autohandai/community-skills/nvidia-tensorrt-llm-ad-accuracy-debug Skill

    10★ repo

    'Debug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline). Use when an AutoDeploy model''s eval score is significantly below the reference and the root cause is unknown.

  • Nvidia tensorrt llm ad add fusion transformation

    autohandai/community-skills/nvidia-tensorrt-llm-ad-add-fusion-transformation Skill

    10★ repo

    'Claude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout. Prefer existing kernels and custom ops; use Triton only when no viable existing-kernel path exists. Use ad-graph-dump for AD_DUMP_GRAPHS_DIR workflows. Covers TRT-LLM paths, registry, default.yaml registration, graph validation, tests, and a review checklist — without prescribing profiling tools or throughput targets.

  • Nvidia tensorrt llm ad conf check

    autohandai/community-skills/nvidia-tensorrt-llm-ad-conf-check Skill

    10★ repo

    'Check whether AutoDeploy YAML configs were actually applied by analyzing server logs and optionally graph dumps (AD_DUMP_GRAPHS_DIR). Use when the user wants to verify config application, debug config issues, or check if AutoDeploy transforms (piecewise CUDA graph, multi-stream, sharding, fusion, etc.) were applied or fell back. Triggers on: "check config", "verify config", "ad-conf-check", "were my configs applied", "config not working", "check if piecewise is enabled", "check log for config", or any request to compare AD YAML settings against runtime behavior.

  • Nvidia tensorrt llm ad graph dump

    autohandai/community-skills/nvidia-tensorrt-llm-ad-graph-dump Skill

    10★ repo

    'Enable and interpret TensorRT-LLM AutoDeploy FX graph text dumps via AD_DUMP_GRAPHS_DIR. Use when you need before/after graphs per transform, to locate subgraphs, or to confirm a rewrite ran. Paths and behavior are grounded in tensorrt_llm/_torch/auto_deploy (GraphWriter, BaseTransform). Complements ad-add-fusion-transformation.

  • Nvidia tensorrt llm ad layer visualizer

    autohandai/community-skills/nvidia-tensorrt-llm-ad-layer-visualizer Skill

    10★ repo

    'Visualize a specific transformer decoder layer from an AutoDeploy FX graph text dump as a hierarchical DOT/PNG diagram. Optionally annotate nodes with actual GPU kernel names and durations from an nsys trace. Use when the user wants to visualize, inspect, or debug a layer in an AutoDeploy model graph dump. Triggers on: "visualize layer", "show layer", "graph of layer", "layer visualization", "dump graph layer". Assumes graph dumps already exist in a directory (produced by AD_DUMP_GRAPHS_DIR).

  • Nvidia tensorrt llm ad model onboard

    autohandai/community-skills/nvidia-tensorrt-llm-ad-model-onboard Skill

    10★ repo

    'Translates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.

  • Nvidia tensorrt llm exec local compile

    autohandai/community-skills/nvidia-tensorrt-llm-exec-local-compile Skill

    10★ repo

    Compile TensorRT-LLM on a compute node inside a Docker container. Use this when already on a compute node with GPUs visible.