852 skills · sorted by relevance
Helps plan and implement database structure changes and data transformations using Sequelize, TypeORM, or Prisma. Includes staged changes intended to avoid downtime, plus transaction and backup examples for rolling back failed migrations.
Configure Zscaler Private Access to replace VPN access with access to specific internal applications. The skill covers connectors, application groups, identity and device checks, browser access, and logging for deployment and migration reviews.
Configure Google Cloud IAP to check identity before granting access to internal applications and virtual machines. Set permissions by user group, device, and network, configure reauthentication, enable service-account access, and record access decisions for monitoring.
Configure AWS Verified Access for VPN-free access to internal applications. Combine user identity and device security checks, write Cedar access policies, and use Terraform and AWS RAM to deploy and share access controls across AWS accounts.
Plan and configure large language model training with OpenRLHF to better match human preferences. Covers training method selection, distributed GPU setup, inference acceleration with vLLM, and troubleshooting memory or training stability issues.
Use SAM to identify object regions in images from points, boxes, or existing masks. The skill provides implementation examples for transparent cutouts, automatic mask generation, annotation tools, and model selection based on available resources.
Build image captioning, visual question answering, and text-based image search with BLIP-2. The skill explains model selection, batch processing, and memory-saving settings, with Python examples for connecting image understanding to language models.
Diagnose failures in GKE HorizontalPodAutoscaler (HPA), which adjusts Pod counts automatically. Investigate missing metrics, unexpected scaling behavior, and slow reactions, then receive proposed configuration fixes or commands for review before deployment.
Switch PUA to offline mode from Codex CLI. This alias updates the offline setting and sets feedback frequency to zero while preserving other configuration fields, then reports the mode change.
Disables PUA's always-on mode from Codex CLI and sets feedback frequency to zero. The alias updates the local configuration while preserving unknown fields, then reports completion with evidence from the executed command.
Enable PUA always-on mode from Codex CLI using a short command alias. It preserves existing configuration fields, restores feedback frequency when it is zero, and requires command output as evidence before reporting completion.
Automate web page tasks such as clicking, filling forms, uploading and downloading files, and taking screenshots. Work across tabs using a browser on the connected host machine or inside a Docker container.
Guide shell, Python, and Node.js execution on the computer running a connected A0 CLI. It explains session reuse, interactive input, output retrieval, and recovery steps when execution permissions, timeouts, or disconnections interrupt the work.
Run model training, fine-tuning, inference, and batch jobs on Modal’s cloud GPUs. Estimate hardware needs and cost, generate Python launch scripts, run or deploy workloads, monitor logs, and retrieve results without managing remote servers.
Create masks that identify object regions in images using points, boxes, or existing masks. The skill guides automatic mask generation, transparent-background extraction, annotation workflows, and deployment, without requiring training for each specific task.
Build image captioning, visual question answering, and text-based image search with BLIP-2. The skill guides model selection, batch processing, and memory optimization, with examples for understanding images without training for each specific task.
Guide large language model training with OpenRLHF using human preference feedback. Covers training method selection, distributed GPU setup, reward model training, and memory tuning, with examples for PPO, GRPO, and DPO.
Write, review, and debug Rust applications, including ownership and borrowing rules that govern memory use. Covers trait-based APIs, explicit error handling, asynchronous work with tokio, and tests with Cargo validation.
Analyze agent runs that fail before any work begins. Check iteration counts, tool use, logs, and outputs to identify startup failures, then direct investigation toward environment setup, input formatting, permissions, or resource limits.
Check generated PDFs with Python and PyPDF2 before delivery. Verify expected page counts, detect unreadable or zero-page files, and collect results across multiple documents, with optional file size checks for unusually small outputs.
Identify agent failures that happen before any work starts by checking iteration counts, tool use, artifacts, and logs. Classify these incidents as pre-execution failures and guide investigation toward environment setup, initialization, and resource limits.
Analyze agent runs that fail before any work begins. By checking execution counts, tool calls, outputs, and conversation logs, this skill classifies startup failures and directs investigation toward system setup, resources, or input processing.
Assess LoRaWAN and sub-GHz wireless devices by capturing signals, examining packet formats, and checking key reuse and replay weaknesses, where recorded messages are resent. It covers IoT networks, fixed-code remotes, and proprietary radio protocols.
Estimate GPU memory, training step time, checkpoint costs, and recovery overhead for training or reinforcement learning. Compare state partitioning, recomputation, offloading, and device counts to assess whether a job can finish within its deadline.