1.5K skills · sorted by relevance
Configure safety checks for LLM applications with NeMo Guardrails. Covers attempts to bypass safety rules, input and output validation, masking personal information, and checking factual claims through programmable rules and integrations.
Investigate and fix agent behavior in TradingAgentsCN by checking active database prompt templates, prompt assembly code, and output processing. Apply targeted changes and verify them with focused tests, template checks, and workflow logs.
Run context-mode diagnostics to check runtimes, hooks, full-text search support, plugin registration, and npm and marketplace versions. Results appear directly in the conversation with clear status labels, with a CLI fallback if the MCP call fails.
Choose and run checks for TypeScript SDK changes, including type checks, linting, builds, Vitest suites, and tests of complete runtime flows. Also guides writing or adapting CLI tests for Effect v4.
Reproduce Mastra Code bugs with a real model and compare timestamped logs across network, streaming, execution, and terminal interface layers. Use the evidence to locate timing problems, incorrect token rates, flicker, or stuck status displays.
Build and review Kubernetes Operators, controllers that keep custom resources in their desired state. Included tools check resource definitions and Go reconciliation code, then assess operational capabilities and suggest improvements.
Set up a Windows sandbox in Daytona to test OpenWork with a simulated corporate certificate authority. Check successful and broken HTTPS connections, the desktop app’s use of Windows trust, and certificate handling in runtimes it launches.
Run Openwork end-to-end tests, which verify complete user journeys, locally or on Daytona. Check the exact commit and runtime, investigate failures or skipped tests, and report results with commands, counts, and an explicit overall verdict.
Investigate opaque errors in shipped OpenWork builds using local logs and Sentry exception reports. Identify the change that caused the failure, reproduce it on the affected runtime, file a Linear issue, and reply to the original report.
Reconcile project documentation, agent rules, authorized memory, and workspace leftovers with current code and runtime behavior. Prepare a clear handoff by correcting stale information, identifying authoritative explanations, and reporting what is verified, pending, or awaiting cleanup approval.
Helps address Google Cloud Security Command Center findings by planning targeted fixes for permissions, misconfigurations, vulnerabilities, and combined attack paths. It includes impact checks, verification, rollback steps, and execution after user approval.
Plan and configure security across Google Kubernetes Engine clusters. Review access permissions, enable Secret Manager integration, and configure protections such as Shielded Nodes and Binary Authorization to strengthen the platform supporting your applications.
Explore how coordinating agents can pass relevant working state to workers through KV cache, a model's internal attention memory. Covers task-specific selection, runtime requirements, and comparisons of accuracy, token use, and processing overhead.
Diagnose errors and incorrect inference results in MNN's QNN backend for Qualcomm HTP processors. Compare intermediate calculation data against CPU results to locate the first faulty operator, distinguish bugs from precision limits, and guide operator support and performance fixes.
Prepare a clean Doris package and run Docker regression tests, which check whether changes break existing behavior. Restore configuration and startup files from Git, build the test image, and investigate failures using configuration checks and runtime logs.
Create, migrate, refine, or debug CARLA vehicle assets with Blender and Unreal. Use real vehicle references to guide geometry and materials, configure wheels, lights, and physics, and deliver editable sources with evidence from runtime validation.
Add safety checks to LLM applications with NeMo Guardrails. This skill guides input and output validation, detection of attempts to bypass safety rules, personal information masking, and checks for unsupported or inaccurate answers.
Build JavaScript or TypeScript applications that run text, image, and audio models in browsers or server runtimes. Guides compatible model selection, GPU or CPU execution, caching, and memory cleanup without requiring a Python server.
Build and maintain machine learning apps on Hugging Face Spaces. Choose a suitable app framework and computing hardware, load models, deploy files, and check logs and outputs to diagnose build or runtime problems.
Plan and review new Omnigent harness integrations, the adapters connecting agent runtimes to the platform. Compare SDK and subprocess approaches with native interface wrappers, using capability matrices and checklists for implementation and testing.
Check for GSD updates, preview the changelog, and install the selected release after confirmation. Additional options synchronize managed skills across runtime environments, restore local customizations through comparison, or select a release candidate for installation.
Review 72 hours of Convex deployment health events and trace read limits or conflicting writes to the responsible code. Receive prioritized performance, cost, and reliability findings with runtime evidence, source locations, and concrete fixes.
Tests a specific Convex feature with sample data and simulated users, without deployment. It checks expected results, rejects unauthorized callers, and verifies that queries return only data belonging to the current user.
Apply ClawHub-specific rules when developing with Convex, including deployment targeting, runtime checks, data migrations, search performance, and skill statistics. It also directs specialized work to the appropriate companion skills.