What's on the bench.
GitHub Scanning
Search GitHub for issues, PRs, discussions, releases, and alerts. Includes query construction, date range handling, repo scoping, and cross-repo intelligence.
GitHub Analytics Scoring
Score repository health (0-100, A-F grades), priorities, and delta tracking. Includes velocity metrics, confidence levels, and bottleneck detection.
GitHub A11y Scanner
Integrate GitHub Accessibility Scanner. Detects configuration, parses scanner issues, correlates with local scans, and tracks Copilot-assigned fixes.
Framework Accessibility
Framework-specific accessibility patterns and fix templates for React, Vue, Angular, Svelte, Next.js, and Tailwind CSS.
Document Scanning
Discover and inventory documents for accessibility audits. Scans folders for .docx, .xlsx, .pptx, and PDFs. Detects git changes and extracts title, author, and language metadata.
Design System
Validate design system tokens for WCAG AA/AAA contrast. Compute color token contrast, focus ring validation (WCAG 2.4.13), motion tokens, and spacing for touch targets across frameworks.
CI Integration
CI/CD accessibility pipeline patterns with axe-core CLI, SARIF output, PR annotations, baseline management, and multi-platform CI templates.
Accessibility Rules
Cross-format accessibility rule reference with WCAG 2.2 mapping for Word, Excel, PowerPoint, and PDF documents.
Vss Summarize Video
Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.
Vss Setup Video Analytics API
Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.
Vss Search Archive
Use to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).
Vss Query Analytics
Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.
Vss Manage Video Io Storage
Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.
Vss Manage Alerts
Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.
Vss Generate Video Report
Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video summarization, real-time alerts, or ad-hoc Q&A.
Vss Deploy Video Embedding
Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file uploads, text and video embeddings, live RTSP streams, health and metrics), Redis/Kafka/OTel integration, common failure modes, and teardown.
Vss Deploy Profile
Use to select, configure, deploy, verify, debug, or tear down a VSS profile (base, search, lvs, warehouse, edge). Not for standalone microservices — use the vss-deploy-* skill.
Vss Deploy Detection Tracking 2d
Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv', 'start warehouse 2d', 'add a stream', 'check rtvi-cv health', or 'stop the perception container'. Not for VLM, embedding, or analytics — use the matching vss-* skill.
Vss Ask Video
Use this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata-answerable questions.
Tilegym Monkey Patch Kernels To Transformers
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 user requires integrating TileGym kernels into `transformers` models.
Tilegym Improve Cutile Kernel Perf
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 IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.
Tilegym Cutile Python
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.
Tilegym Cutile Autotuning
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 kernels. Covers: tune-once/cache/launch pattern, per-architecture configs (sm80–sm120), parameter space design (tile sizes, occupancy, num_ctas), and 7 common pitfalls with solutions.
Tilegym Converting Cutile To Triton
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 equivalents. Covers dual-kernel layout flags (e.g. transpose=True/False + autotune grid via META) per translations/advanced-patterns.md. Use when converting, porting, or translating cuTile kernels to Triton, or debugging existing Triton translations.