Loading...
Loading...
Found 1,211 Skills
Guides authoring, review, optimization, and false-positive debugging of YARA-X detection rules for malware identification across PE, script, npm, Office, Chrome extensions (crx module), and Android DEX (dex module). Covers string and atom quality, condition short-circuiting, legacy YARA migration, yarGen/FLOSS workflows, goodware validation, and production deployment—not full malware reverse engineering, network IDS (Suricata/Snort), or memory forensics (Volatility). Use when the user asks to write YARA rule, YARA-X, yr check, yr scan, false positive YARA, yarGen, malware detection rule, crx module, dex module, optimize YARA performance, or migrate legacy YARA.
Use whenever the user mentions LLM prompt/prefix cache misses, cached_tokens=0, cache_read_input_tokens/cache_creation_input_tokens, prompt_cache_key, cache_control/cachePoint placement, stable prefixes, tool/schema stability, TTFT/prefill latency, OpenAI/Claude/Bedrock/OpenRouter routing, vLLM/SGLang KV reuse, or LLM cost/speed regressions on repeated long prompts. Use when reviewing LLM request shape changes: prompt text, message order, request builders, tools, schemas, response_format, provider API surface, model/router settings, agent loop structure, context compaction, or inference deployment. Use for speeding up agents only when prompt-cache stability, TTFT, or cache cost is central. Do not use for generic prompt writing, generic RAG design, token counting, or non-LLM performance.
Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.
Manage Harness Infrastructure as Code Management (IaCM) via MCP. Configure Terraform workspaces with remote state and RBAC, set up continuous drift detection with auto-remediation, design multi-tier change approval workflows, and estimate infrastructure costs before deployment. Use when asked to manage Terraform workspaces, detect infrastructure drift, set up approval workflows for infrastructure changes, or estimate Terraform costs. Do NOT use for creating Harness infrastructure definitions (use create-infrastructure instead) or OPA policies (use create-policy instead). Trigger phrases: terraform, workspace, drift detection, infrastructure cost, IaCM, state management, change approval, terraform plan, infracost, infrastructure governance.
Guideline for designing, implementing, and verifying secure Python applications following OWASP Top 10 best practices. Use when the user wants to: (1) review Python code for security vulnerabilities, (2) design a secure Python application architecture, (3) implement security features (authentication, authorization, cryptography, input validation), (4) audit Python dependencies for known vulnerabilities, (5) create security checklists or verification plans, (6) fix security bugs or harden existing Python code, (7) set up security testing and static analysis (bandit, safety, semgrep), or (8) handle any Python security concern including injection prevention, secure deserialization, SSRF protection, secrets management, and secure deployment.
Full-stack PlantUML expert: create PUML from descriptions, convert images to PUML (vision reverse engineering), render locally (PNG/SVG/PDF) with no internet. macOS/Windows/Linux; auto-installs PlantUML+Java+Python. Covers all 27 chapters of the PlantUML Language Reference Guide v1.2025.0 (607 pages): Sequence, Use Case, Class, Object, Activity (legacy+new), Component, Deployment, State, Timing, JSON, YAML, nwdiag, Salt/Wireframe, Archimate, Gantt, MindMap, WBS, Maths, ER, Common Commands, Creole, Sprites, Skinparam, Preprocessing, Unicode, StdLib (C4/AWS/Azure/K8s/ArchiMate). Use for: draw a diagram, create PUML, convert image to PUML, render .puml, debug PUML, explain PlantUML syntax, any UML task.
World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM, diffusion models, and vision transformers. Includes 3D vision, video analysis, real-time processing, and production deployment. Use when building vision AI systems, implementing object detection, training custom vision models, or optimizing inference pipelines.
Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Debug Docker containers and containerized applications. Diagnose deployment issues, container lifecycle problems, and resource constraints.
Create a Next.js app running on Bun, configure the development environment, and deploy to Vercel with automatic deployments on push.
Deploy and manage Supabase Edge Functions. Use for invoking serverless functions, deploying new functions, and managing function deployments.