524 skills · sorted by relevance
Run one cycle of autonomous task work in Claude Code: check progress, select and execute the next action, log the work, and schedule another cycle. Stop when all tasks are complete or the iteration limit is reached.
Review how a website behaves when images fail to load and add fallback images or meaningful placeholder content. Check loading behavior, consider loading placeholders, and use error logging and browser developer tools to investigate and verify fixes.
Assess an application against OWASP Top 10:2025 risk categories using Strix. Get findings backed by working exploit examples, organized by category, with clear explanations of what was tested and what remains unassessed.
Inspect NSLogger logs from iOS and macOS apps, filter messages by severity, tag, text, or thread, summarize counts, export text, JSON, or CSV, and receive live logs for debugging.
Organize PyTorch models and data pipelines with PyTorch Lightning, automate training, save checkpoints, and track experiments. Includes templates and guidance for configuring training across multiple GPUs or TPUs.
Design, build, debug, and optimize connections to external APIs. The skill covers REST, GraphQL, event notifications through webhooks, authentication, retries, request limits, and logging to help produce integrations whose failures can be traced.
Design layered protections for AI agents against malicious instructions, tool misuse, and data leakage. Provides guidance and code examples for input checks, isolated tool execution, permission limits, and audit logging to help review and strengthen agent security.
Evaluate job offers by separating guaranteed pay, conditional bonuses, and estimated equity value. Compare terms, develop an evidence-based counteroffer, draft emails and call scripts, rehearse recruiter conversations, and prepare deadline extensions, acceptance, or decline messages.
Add retries and timeouts to Python service calls, with increasing and randomized waits between attempts. Use examples to distinguish temporary failures from permanent errors, limit retry duration, and record retries in logs.
Build Node.js APIs and backend services with Express/Fastify. The skill guides authentication, database integration, error handling, and operational practices such as logging and health checks, which report whether a service is working.
Design application and API behavior when operations fail. Choose between exceptions and Result types, which explicitly represent success or failure, and improve retries, error messages, logging, and resource cleanup so failures are easier to handle and investigate.
Build Spring Boot applications with guidance on project structure, configuration, APIs, database access, logging, testing, and security. Apply practices such as constructor injection, passing required components through constructors, and consistent handling of validation errors.
Review and improve .NET/C# code against project conventions. Cover public API documentation, dependency injection for supplying services to classes, asynchronous operations, tests, configuration, logging, and input validation, including guidance for Semantic Kernel integrations.
Turn a business use case into a Dataverse solution using Python. Get table and relationship designs, implementation code, usage instructions, and recommendations for error recovery, logging, monitoring, and performance based on the expected workload.
Build and troubleshoot C#/.NET MCP servers that expose tools and information to AI agents. Guidance targets the official 2.x SDK and covers transport setup, authentication, interactive features, basic clients, and migration issues caused by changed defaults.
Collect and review SGLang startup logs to identify unnecessary output and trace its source. Get saved logs and specific cleanup proposals while preserving useful diagnostics, with runtime changes left for user approval.
Investigate SGLang runs that freeze across multiple GPUs. It uses stack traces, communication logs, GPU memory dumps, and comparisons between processes to locate state differences, trace their causes, and guide fixes.
Investigate CUDA crashes in SGLang using logs and inputs saved before execution. Inspect tensor shapes, data types, and numerical anomalies, with guidance for separate process logs and additional CUDA debugging tools.
Build detection rules for suspicious Windows scheduled tasks by correlating Sysmon and Windows Security logs. Examine parent processes, file paths, encoded commands, and remote task creation to uncover persistent access and movement between systems.
Detect attacks that misuse legitimate Windows tools by examining command arguments, parent and child processes, and network connections. Create Sysmon logging configurations and Sigma detection rules, analyze endpoint logs, and review application controls while accounting for legitimate usage.
Examine Windows and Active Directory logs for attempts to extract passwords and other credentials. Identify suspicious memory access and database exports, correlate events with user and host context, and produce findings with severity ratings and detection queries.
Investigate suspected email account takeovers by examining audit logs, sign-ins, inbox rules, and app permissions. Identify suspicious forwarding, unlikely travel between sign-ins, and unusual access, then summarize findings and recommended containment actions in a severity-rated report.
Deploy Prisma Access to secure access to internal applications for remote users and branches. Configure connectors, GlobalProtect agents, access policies based on user groups and device security, and centralized logging through Strata Cloud Manager.
Deploy Suricata to detect suspicious network traffic or block it inline. Configure protocol inspection, detection rules, and structured EVE JSON logs, then connect logs to analysis platforms and check packet drops and alert quality during operation.