495 skills · sorted by relevance
Investigate security incidents in Google SecOps by connecting host, user, and network events. Reconstruct attack timelines, trace movement between systems, assess affected assets, and organize findings into case notes and investigation reports.
Check Google Cloud IAM allow policy changes against the last 90 days of access logs. The skill identifies access that could be lost and applies changes only after a successful simulation and user approval.
Assess how changes, failures, or paused updates to a BigQuery table or view affect downstream assets. Trace data lineage, the relationships showing where data flows, and summarize dependent tables, dashboards, and processes with direct and indirect impacts.
Design Google Cloud infrastructure with Terraform, validate it locally, and assess the planned changes for security, cost, and reliability. The skill then imports templates into Application Design Center, deploys them, investigates failures, and checks the deployed services.
Review daily Google Ads and Meta Ads results for budget pacing, declining performance, and unusual activity. Get prioritized findings with supporting numbers and concrete recommendations for a marketing team to assess and carry out.
Route requests that explicitly name lark-vc to lark-meeting. This compatibility entry preserves an older skill name and delegates handling to the instructions in lark-meeting rather than performing business operations itself.
Automate Desktime operations through Rube MCP, a connection for agent tools. The skill finds available actions, checks the service connection, and uses current input requirements to run the requested workflow.
Automate Bugherd operations through Rube MCP, a connection between the agent and external tools. The skill guides tool discovery, connection checks, and execution using current input requirements, with support for bulk operations.
Automate Browserhub operations through Rube MCP, a connection between the agent and external tools. The skill covers finding available tools, checking authentication, and executing operations with current input requirements, including bulk workflows.
Automate Breezy HR operations through Rube MCP, a connection between the agent and external tools. The skill provides a workflow for discovering tools, verifying the connection, and executing individual or bulk operations with current input requirements.
Automate Anchor Browser operations through Rube MCP, a connection between the agent and external tools. The skill guides tool discovery, connection verification, and execution using current input requirements, and describes how to handle bulk operations.
Create, read, and edit Word documents with headings, tables, page numbers, and images. Use it to turn content into formatted reports or letters, reorganize existing documents, replace text, and work with tracked changes and comments.
Build image generation workflows in Python with Stable Diffusion and HuggingFace Diffusers. The guide covers text prompts, transforming existing images, replacing selected regions, controlling composition, applying learned styles, and adjusting memory use during generation.
Guides experiments that change internal values in PyTorch models to test what causes their behavior. Uses pyvene to swap or remove activations, locate influential components, train interventions, and save experiments for reuse.
Investigate how transformer language models produce predictions with TransformerLens. This skill guides inspection of intermediate values and attention patterns, plus experiments that replace internal values to test their effects and identify components involved in model behavior.
Investigate errors, crashes, and unexpected behavior by reproducing failures, tracing execution, and comparing logs. Tests one explanation at a time, then provides a verified fix, supporting evidence, and tests or safeguards to prevent recurrence.
Guide OpenRig CLI and background service upgrades while protecting active sessions and local file changes. The skill provides staged checks, verified database backups, selective plugin refreshes, and migration helpers, with evidence checked after each change.
Scan Android APK files for Firebase configuration and access-control weaknesses in databases, storage, authentication, and cloud functions. Produce text and JSON reports with evidence, severity ratings, and suggested fixes for authorized security assessments.
Investigate organizations, domains, media locations, and cryptocurrency flows using open-source intelligence, or OSINT. The skill helps select relevant research tools, connect findings across sources, and preserve evidence with timestamps, screenshots, file hashes, and reproducible logs.
Assess web applications and APIs for SQL injection, where input changes database queries. The skill covers finding vulnerable inputs, testing different database systems, automating checks, and documenting findings with remediation suggestions.
Assess Kubernetes security from an existing pod or API access point. Covers permission checks, exposed node services, secrets, host access, and cloud metadata to explain how configuration weaknesses can expand access across a cluster.
Draft and revise machine learning, computer vision, and natural language processing papers. Improve section structure, paragraph flow, and figures or tables, then check major claims against experimental evidence and review the draft from a skeptical reviewer’s perspective.
Assess customer acquisition channels using acquisition costs, lifetime customer value, payback time, retention, and growth capacity. Compare channels and receive recommendations to increase spending, improve performance, pause activity, or continue with a spending cap.
Route product design requests to focused skills for user research, experience reviews, visual exploration, prototype building, or sharing. This entry point selects the appropriate workflow rather than performing the design work itself.