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
Nvidia tensorrt llm exec slurm compile
autohandai/community-skills/nvidia-tensorrt-llm-exec-slurm-compile Skill
10★ repoCompile TensorRT-LLM on a SLURM cluster. Covers submitting a batch job with a container image, monitoring the job, and verifying the build. Use when the user wants to compile TRT-LLM remotely via SLURM rather than on a local compute node.
Nvidia tensorrt llm kernel cute writing
autohandai/community-skills/nvidia-tensorrt-llm-kernel-cute-writing Skill
10★ repo'Write and implement GPU kernels using NVIDIA CuTe DSL (CUTLASS 4.x Python API) — NOT for Triton, CUDA C++, or conceptual explanations. Trigger only when the user wants to write or implement a kernel, not when asking questions about CuTe DSL concepts or layouts. CuTe DSL uses cute.jit/cute.kernel decorators and cutlass.cute imports. Covers element-wise kernels, GEMM patterns, reductions, memory hierarchy (global/shared/register/TMA), MMA tensor core operations, software pipelining, and framework integration.
Nvidia tensorrt llm kernel tileir optimization
autohandai/community-skills/nvidia-tensorrt-llm-kernel-tileir-optimization Skill
10★ repo'Optimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+). Adds TileIR-specific autotune configs: occupancy, num_ctas, TMA descriptors. Covers kernel classification (dot-related, norm-like, elementwise, reduction), type-specific transformations, and PTX-vs-TileIR benchmarking. Triggered by: "optimize for TileIR", "add TileIR configs", "Blackwell optimization", "TMA descriptors", "2CTA mode", "occupancy tuning". Kernels use standard `import triton`; TileIR activates via ENABLE_TILE=1 when nvtriton is installed.
Nvidia tensorrt llm kernel triton writing
autohandai/community-skills/nvidia-tensorrt-llm-kernel-triton-writing Skill
10★ repo'ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user''s request must involve Triton explicitly. Covers Triton-specific patterns: fused elementwise, reductions (softmax, LayerNorm, RMSNorm), tiled GEMM with triton.autotune, and flash attention. Workflow: design, write, verify (with fast-path for explicit requests).
Nvidia tensorrt llm perf analysis
autohandai/community-skills/nvidia-tensorrt-llm-perf-analysis Skill
10★ repo'Performance analysis coordination workflow. Guides profiling delegation, bottleneck classification (compute/memory/launch/communication/sync), and structured report generation. Use when the user asks to analyze performance, profile a workload, check MFU/SOL, or diagnose bottlenecks.
Nvidia tensorrt llm perf host analysis
autohandai/community-skills/nvidia-tensorrt-llm-perf-host-analysis Skill
10★ repo'Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify scheduling or request-management overhead. Supports optional inter-kernel gap, eager-vs-graph, pattern mapping, and multi-rank straggler drill-down. Use standalone or within perf-analysis. Triggers: host overhead, inter-step gap, scheduling overhead, forward step isolation, nsys iteration analysis, NVTX breakdown, request management overhead, GPU idle, host bottleneck, host prep exposed, inter-kernel gap, bubble analysis, graph coverage, eager kernel, rank imbalance, straggler detection.
Nvidia tensorrt llm perf host optimization
autohandai/community-skills/nvidia-tensorrt-llm-perf-host-optimization Skill
10★ repoProfiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.
Nvidia tensorrt llm perf nsight compute analysis
autohandai/community-skills/nvidia-tensorrt-llm-perf-nsight-compute-analysis Skill
10★ repo'Analyze ncu (NVIDIA Nsight Compute) profiling output: SOL% bottleneck classification, roofline analysis, occupancy diagnosis, memory hierarchy analysis, warp stall analysis, metric interpretation, and programmatic .ncu-rep report analysis. NOT for kernel writing or code generation, Nsight Systems (nsys), host-side profiling, or system-level profiling.
Nvidia tensorrt llm perf nsight systems
autohandai/community-skills/nvidia-tensorrt-llm-perf-nsight-systems Skill
10★ repoNsight Systems (nsys) CLI for system-level timeline profiling. Use when the user wants to run nsys profile, analyze .nsys-rep reports, use nsys stats/analyze/recipe commands, diagnose GPU idle time from timeline traces, or profile distributed training with NCCL overlap analysis. NOT for kernel-level metrics like SOL%, occupancy, or roofline (use perf-nsight-compute-analysis for ncu). NOT for writing or generating kernels. NOT for applying optimizations like CUDA Graphs.
Nvidia tensorrt llm perf optimization
autohandai/community-skills/nvidia-tensorrt-llm-perf-optimization Skill
10★ repo'Performance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection, prioritization criteria, and safe modification workflow. Use when the user asks to apply optimizations, write kernels, or improve performance. Covers both user-specified optimization and autopilot-driven iterative optimization.
Nvidia tensorrt llm perf torch cuda graphs
autohandai/community-skills/nvidia-tensorrt-llm-perf-torch-cuda-graphs Skill
10★ repoApply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager, FullCudaGraphWrapper, manual torch.cuda.graph), code compatibility, capture workflows, dynamic pattern handling, and troubleshooting. Triggers: CUDA graph, torch.cuda.graph, make_graphed_callables, reduce-overhead, graph capture, graph replay, kernel launch overhead, CudaGraphManager, FullCudaGraphWrapper, full-iteration graph, stream capture.
Nvidia tensorrt llm perf torch sync free
autohandai/community-skills/nvidia-tensorrt-llm-perf-torch-sync-free Skill
10★ repoIdentify and eliminate host-device synchronizations in PyTorch code. Detects sync points (.item(), .cpu(), boolean indexing, torch.tensor on CUDA), classifies false vs true dependencies, provides sync-free alternatives. Triggers: sync-free, synchronization, .item(), .cpu(), host-device sync, eliminate syncs, CPU stall, non_blocking, set_sync_debug_mode, cudaStreamSynchronize, cudaEventSynchronize, remove syncs, async GPU.
Nvidia tensorrt llm perf workload profiling
autohandai/community-skills/nvidia-tensorrt-llm-perf-workload-profiling Skill
10★ repo'Code instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec), and data load time. (2) Standalone kernel/op — write CUDA event timing code with warmup, per-iteration statistics, and anti-pattern avoidance. Also covers NVTX annotation for labeling profiler timelines. NOT for: running or analyzing profiler tools (nsys, ncu, Nsight Systems, Nsight Compute), writing kernels (Triton, CuTe, CUDA), applying optimizations (CUDA Graphs, gradient checkpointing, fusion), or interpreting roofline/SOL% metrics. Triggers: "measure throughput", "benchmark this function", "time my training loop", "samples per second", "NVTX annotate", "instrument my dataloader", "data load time", "kernel timing", "how do I time".
Nvidia tensorrt llm trtllm code contribution
autohandai/community-skills/nvidia-tensorrt-llm-trtllm-code-contribution Skill
10★ repo'Best practices for contributing code to TensorRT-LLM. Covers the official contribution process (issue tracking, fork workflow, DCO signing), coding guidelines, implementation workflow, common mistakes, testing strategy, commit hygiene, and review readiness. Incorporates rules from CONTRIBUTING.md and CODING_GUIDELINES.md plus lessons distilled from real PR retrospectives. Use when implementing new features, optimizations, or bug fixes in the TensorRT-LLM codebase.
Nvidia tensorrt llm trtllm codebase exploration
autohandai/community-skills/nvidia-tensorrt-llm-trtllm-codebase-exploration Skill
10★ repo'Systematic approach to exploring the TensorRT-LLM codebase before implementing new features or optimizations. Teaches how to discover existing infrastructure, trace code paths, and avoid reimplementing what already exists. Derived from real mistakes where ~250 lines of code were written and deleted because existing forward methods weren''t discovered upfront. Use when starting any new feature, optimization, or code modification in TRT-LLM.
Nvidia tensorrt llm trtllm flashinfer upgrade
autohandai/community-skills/nvidia-tensorrt-llm-trtllm-flashinfer-upgrade Skill
10★ repoUpgrade flashinfer-python version in TensorRT-LLM. Fetches the latest releases from GitHub (stable and nightly), compares with the current pinned version, lets the user pick a target version, and updates all version references across the repo. Use when the user wants to bump or upgrade flashinfer.
Nvidia tensorrt llm trtllm moe develop
autohandai/community-skills/nvidia-tensorrt-llm-trtllm-moe-develop Skill
10★ repoReview, design, and refactor TensorRT-LLM PyTorch MoE code for architecture fit, clean code, maintainability, and testability. Always use for any modification, review, refactor, or design planning that touches MoE modules, including tensorrt_llm/_torch/modules/fused_moe, ConfigurableMoE, MoE backends, MoEScheduler/moe_scheduler.py, forward execution/chunking, communication strategies, EPLB, quantization/weight handling, routing, factories, MoE docs, or MoE tests. Also use when the user asks whether a MoE design follows the current architecture or whether a MoE refactor is reasonable.
Nvidia tensorrt llm trtllm serve config guide
autohandai/community-skills/nvidia-tensorrt-llm-trtllm-serve-config-guide Skill
10★ repoGenerate a source-backed starting `trtllm-serve --config` YAML for basic aggregate single-node PyTorch serving, aligned with checked-in TensorRT-LLM configs and deployment docs. Preserves explicit latency / balanced / throughput objectives. Excludes disaggregated, multi-node, and non-MTP speculative configs.
Nvidia video search and summarization video analytics
autohandai/community-skills/nvidia-video-search-and-summarization-video-analytics Skill
10★ repoQuery video analytics data and metrics from Elastic search via the VA-MCP server (port 9901). This includes incidents, alerts, sensor data, and metrics. Use for any question about violations, alerts, incidents, object counts, speeds, occupancy, or anything that requires looking up recorded events. This is the primary way to answer a question that requires incidents, alerts and other metrics such as people counts and violations.
autohandai/community-skills/openai-docs-skill Skill
10★ repoQuery the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, or migrations and you need up-to-date official guidance.
The same file is in 4 other repositories
autohandai/community-skills/opencontext Skill
10★ repoPersistent memory and context management for AI agents using OpenContext. Keep context across sessions/repos/dates, store conclusions, and provide document search workflows.
The same file is in 4 other repositories
Performing kubernetes cis benchmark with kube bench
autohandai/community-skills/performing-kubernetes-cis-benchmark-with-kube-bench Skill
10★ repoAudit Kubernetes cluster security posture against CIS benchmarks using kube-bench with automated checks for control plane, worker nodes, and RBAC.
Performing memory forensics with volatility3 plugins
autohandai/community-skills/performing-memory-forensics-with-volatility3-plugins Skill
10★ repoAnalyze memory dumps using Volatility3 plugins to detect injected code, rootkits, credential theft, and malware artifacts in Windows, Linux, and macOS memory images.
Performing memory forensics with volatility3
autohandai/community-skills/performing-memory-forensics-with-volatility3 Skill
10★ repoAnalyze volatile memory dumps using Volatility 3 to extract running processes, network connections, loaded modules, and evidence of malicious activity.
The same file is in 1 other repository
autohandai/community-skills/prompt-repetition Skill
10★ repoA prompt repetition technique for improving LLM accuracy. Achieves significant performance gains in 67% (47/70) of 70 benchmarks. Automatically applied on lightweight models (haiku, flash, mini).
The same file is in 4 other repositories
autohandai/community-skills/skill-creator Skill
10★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
The same file is in 66 other repositories
autohandai/community-skills/subagent-driven-development Skill
10★ repoUse when executing implementation plans with independent tasks in the current session
The same file is in 7 other repositories
autohandai/community-skills/super-swarm-spark Skill
10★ repoOnly to be triggered by explicit super-swarm-spark commands.
The same file is in 3 other repositories
autohandai/community-skills/swarm-planner Skill
10★ repo[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.
The same file is in 2 other repositories
katalon-labs/true-skills/io.github.katalon-studio/testops-mcp MCP server
10★ repoKatalon True Platform MCP: design tests, run with AI, upload reports, assess release readiness.
mansurjisan/ocean-mcp/io.github.mansurjisan/adcirc-mcp MCP server
10★ repoADCIRC model configuration debugging, parameter lookup, and validation
mansurjisan/ocean-mcp/io.github.mansurjisan/ofs-mcp MCP server
10★ repoNOAA OFS regional ocean model forecasts — water level, temperature, salinity
mansurjisan/ocean-mcp/io.github.mansurjisan/nhc-mcp MCP server
10★ repoNHC storm tracks, forecast advisories, watches/warnings, and HURDAT2 data
mansurjisan/ocean-mcp/io.github.mansurjisan/erddap-mcp MCP server
10★ repoAccess ocean data from 80+ ERDDAP servers worldwide
mansurjisan/ocean-mcp/io.github.mansurjisan/schism-mcp MCP server
10★ repoSCHISM model configuration debugging, parameter lookup, and validation
mansurjisan/ocean-mcp/io.github.mansurjisan/recon-mcp MCP server
10★ repoHurricane reconnaissance data — HDOB flight observations, Vortex Data Messages, SFMR, and ATCF fixes
mansurjisan/ocean-mcp/io.github.mansurjisan/ww3-mcp MCP server
10★ repoGFS-Wave (WAVEWATCH III) forecasts and NDBC buoy wave observations
USGS Water Services MCP Server
mansurjisan/ocean-mcp/io.github.mansurjisan/usgs-mcp MCP server
10★ repoUSGS Water Services streamflow, flood stages, and peak events via waterservices.usgs.gov
mansurjisan/ocean-mcp/io.github.mansurjisan/stofs-mcp MCP server
10★ repoNOAA STOFS storm surge forecasts, observation validation, and OPeNDAP data
mindstone/mcp-servers/io.github.mindstone/mcp-server-elevenlabs MCP server
no license10★ repoElevenLabs MCP server: TTS, music, sound effects, voices, and audio transcription
mindstone/mcp-servers/io.github.mindstone/mcp-server-freshdesk MCP server
no license10★ repoFreshdesk Support MCP server for Model Context Protocol hosts
mindstone/mcp-servers/io.github.mindstone/mcp-server-fathom MCP server
no license10★ repoFathom AI meeting transcription MCP server for Model Context Protocol hosts
mindstone/mcp-servers/io.github.mindstone/mcp-server-email-imap MCP server
no license10★ repoEmail IMAP/SMTP MCP server: iCloud, Gmail, Yahoo, Outlook, and custom IMAP providers
mindstone/mcp-servers/io.github.mindstone/mcp-server-google-analytics MCP server
no license10★ repoGoogle Analytics 4 MCP server with reporting, schema discovery, and admin visibility tools
mindstone/mcp-servers/io.github.mindstone/mcp-server-gamma MCP server
no license10★ repoGamma AI presentation generation MCP server for Model Context Protocol hosts
mindstone/mcp-servers/io.github.mindstone/mcp-server-humaans MCP server
no license10★ repoHumaans HR platform MCP server for Model Context Protocol hosts
mindstone/mcp-servers/io.github.mindstone/mcp-server-google-workspace MCP server
no license10★ repoGoogle Workspace MCP server for Gmail, Calendar, Drive, Docs, Sheets, Slides, Contacts, and more
mindstone/mcp-servers/io.github.mindstone/mcp-server-kling MCP server
no license10★ repoKling AI video generation MCP server for Model Context Protocol hosts
mindstone/mcp-servers/io.github.mindstone/mcp-server-mixmax MCP server
no license10★ repoMixmax email productivity MCP server for Model Context Protocol hosts
mindstone/mcp-servers/io.github.mindstone/mcp-server-napkin MCP server
no license10★ repoNapkin AI visual generation MCP server for Model Context Protocol hosts
mindstone/mcp-servers/io.github.mindstone/mcp-server-openai-image MCP server
no license10★ repoOpenAI image generation MCP server for Model Context Protocol hosts
mindstone/mcp-servers/io.github.mindstone/mcp-server-office MCP server
no license10★ repoMicrosoft Office MCP server: read and edit Word documents, Excel workbooks, and PowerPoint files
mindstone/mcp-servers/io.github.mindstone/mcp-server-nano-banana MCP server
no license10★ repoNano Banana MCP server — Google Gemini image generation and editing via Model Context Protocol
mindstone/mcp-servers/io.github.mindstone/mcp-server-opus-video-clip MCP server
no license10★ repoOpusClip MCP server — clip long-form videos, manage projects, collections, censor jobs, posts
mindstone/mcp-servers/io.github.mindstone/mcp-server-pandadoc MCP server
no license10★ repoPandaDoc document automation MCP server for Model Context Protocol hosts
mindstone/mcp-servers/io.github.mindstone/mcp-server-outreach MCP server
no license10★ repoOutreach sales engagement MCP server: prospects, sequences, accounts, tasks, and mailings
mindstone/mcp-servers/io.github.mindstone/mcp-server-runway MCP server
no license10★ repoRunway ML MCP server: AI video, image, audio, voice generation, and task management
mindstone/mcp-servers/io.github.mindstone/mcp-server-quickbooks MCP server
no license10★ repoQuickBooks Online MCP server: invoices, bills, customers, vendors, employees, and accounts
mindstone/mcp-servers/io.github.mindstone/mcp-server-servicenow MCP server
no license10★ repoServiceNow ITSM MCP server for Model Context Protocol hosts
mindstone/mcp-servers/io.github.mindstone/mcp-server-vanta MCP server
no license10★ repoVanta compliance MCP server: vulnerabilities, tests, controls, evidence, people, vendors, docs