Menu
Skills in this repository
SkillsMP has collected 1,040 skills from autohandai/community-skills. Open a skill to review its source and details.
autohandai/community-skillsShowing 40 of 1,040 collected skills.
Review, 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…
Generate 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…
Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile…
Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major to column-major), type system mapping, and launch API…
Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton…
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile…
Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and…
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the…
Manage and monitor VSS alerts after the alerts profile is deployed. The deployment's mode (CV vs VLM real-time) is fixed at deploy time and determines the workflow — start/stop real-time alerts via the VSS Agent on a VLM deployment, onboard CV alerts by…
Deploy, debug, or tear down any VSS profile using a compose-centric workflow — config (dry-run) with env overrides, review resolved compose, then compose up. Use this skill when the user says "deploy vss", "deploy `profile`", "debug deploy", "verify…
Produce video analysis reports by discovering the deployed VSS agent, querying POST /generate for a timestamped captioned summary of the clip, then formatting the agent reply as the standard Video Analysis Report markdown.
Use this skill when working with the RTVI VLM or RT-VLM microservice API on VSS 3.1. Generate dense captions and alerts for stored video files and live RTSP streams via `/v1/generate_captions_alerts`; upload media via `/v1/files`; add and remove live streams…
Query 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…
Search video archives using natural language — find events, objects, actions, and people across recorded video using fusion search (Cosmos Embed1 semantic search + CV attribute search). Use when asked to search for something in video, find actions and events,…
Summarize a video by calling the VLM NIM or the Long Video Summarization (LVS) microservice directly. For short videos (under 60s) call the VLM's OpenAI-compatible chat completions endpoint; for long videos (60s or longer) call the LVS microservice. Use when…
Call the vss agent to run video understanding on video to answer a text question. Use when the user asks about video content, or about visual details that cannot be answered from conversation history, search hits, or metadata alone.
Query VIOS REST APIs: sensor list, recording timelines, video clip extraction, snapshot capture, add/delete sensors and streams
Generate video summary reports using the VSS video_search_frag extension with Long Video Summarization (LVS), Enterprise RAG knowledge retrieval, and human-in-the-loop parameter collection. Use when: user wants to generate a video summary, report, or analysis…
Use spring-boot-skills for production-grade Spring Boot agent guidance, modernization, testing, and operations.
Inventory COBOL estates and classify modernization go/no-go readiness with ATLAS toolkit discovery.
Reverse-engineer COBOL systems into structured requirements, business rules, and dependency maps with cobol-o-matic.
Modernize COBOL systems to Java Quarkus or .NET with Microsoft Legacy Modernization Agents workflows.
Plan and execute AI-assisted COBOL to Java migrations with LegacyBridge OSS COBOL.
Use AI assistance for IBM z/OS and mainframe modernization tasks from the mainframe-ai project.
Use the Mainframe AI-native Bash runtime and bundled skills for legacy system analysis automation.
SOC 2 Type II audit preparation involves designing, implementing, and demonstrating the operational effectiveness of controls aligned to the AICPA Trust Services Criteria (TSC) over a defined audit pe
UI/UX best practices for web interfaces. Use when reviewing animations, CSS, audio, typography, UX patterns, prefetching, or icon implementations. Covers 11 categories from animation principles to typography. Outputs file:line findings.
Configure AWS Verified Access to provide VPN-less zero trust network access to internal applications using identity and device posture verification with Cedar policy language.
Configuring Google Cloud Identity-Aware Proxy (IAP) to enforce per-request identity verification for Compute Engine, App Engine, Cloud Run, and GKE services using access levels, context-aware policies, and programmatic access with service accounts.
Configuring Zscaler Private Access (ZPA) to replace traditional VPN with zero trust network access by deploying App Connectors, defining application segments, configuring access policies based on user identity and device posture, and integrating with IdPs.
Deploying Cloudflare Access with Cloudflare Tunnel to provide zero trust access to self-hosted and private applications, configuring identity-aware access policies, device posture checks, and WARP client enrollment for VPN replacement.
Deploying Palo Alto Networks Prisma Access for SASE-based zero trust network access using GlobalProtect agents, ZTNA Connectors, security policy enforcement, and integration with Strata Cloud Manager for unified security management.
Deploy and configure Tailscale as a WireGuard-based zero trust mesh VPN with identity-aware access controls, ACLs, and exit nodes for secure peer-to-peer connectivity.
Implementing Google's BeyondCorp zero trust access model to eliminate implicit trust from the network perimeter, enforce identity-aware access controls using IAP, Access Context Manager, and Chrome Enterprise Premium for VPN-less secure application access.
Implement the CISA Zero Trust Maturity Model v2.0 across the five pillars of identity, devices, networks, applications, and data to achieve progressive organizational zero trust maturity.
Implementing device posture assessment as a zero trust access control by integrating endpoint health signals from CrowdStrike ZTA, Microsoft Intune, and Jamf into conditional access policies that enforce compliance before granting resource access.
Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.
Implement NextDNS as a zero trust DNS filtering layer with encrypted resolution, threat intelligence blocking, privacy protection, and organizational policy enforcement across all endpoints.
Implementing zero trust access controls for SaaS applications using CASB, SSPM, conditional access policies, OAuth app governance, and session controls to enforce identity verification, device compliance, and data protection for cloud-hosted services.