Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Explains on-demand code loading with dynamic import(). Focuses on deferring modules that are not required at startup to reduce initial bundle size.
Execute and analyze malware samples within a highly controlled, instrumented sandbox environment to observe their true behavior, network communications, file system modifications, and registry changes in real-time.
Select alternative execution paths when a plan step fails — branch on outcomes instead of blind retry. Load when a structured plan step fails, an unexpected observation arrives, or the user asks what to try next after an error. Also triggers on "try another approach", "route around this failure", "replan on failure", "if X fails try Y", or outcome-based branching during multi-step work. Pairs with…
Checks NIXL, UCX, and NCCL interconnect readiness after a Dynamo deployment starts, especially in disaggregated or multi-node setups. Confirms KV transport correctness; diagnosing already-failed pods is outside its scope.
Brings up existing Dynamo Kubernetes recipes for a chosen model, backend, GPU, and deployment mode. Covers recipe selection, validation, patching, and deployment, excluding router-only setup and failure diagnosis.
Starts or patches Dynamo routers with round-robin, KV-aware, least-loaded, or device-aware routing. Runs endpoint smoke checks; full recipe deployment and failure diagnosis are handled separately.
Investigates failures involving pods, model-cache jobs, PVCs, workers, frontend or router health, endpoints, and benchmark jobs. Focuses on unhealthy deployments rather than normal initial setup.
Provides DynamoDB-Toolbox v2 patterns for schema, table, and entity modeling. Covers the .build() command workflow, queries, scans, batch operations, transactions, and single-table design with computed keys.
Copies a standard template tab into a target Google spreadsheet through MCP tools, renames it, and fills header metadata. Preserves formulas and formatting while writing detailed step-by-step test cases from the screen design document.
Identifies a World E skill without describing its functionality.
E2B Desktop Sandbox with autonomous computer use — cloud Linux environments for browser automation, visual UI grounding, screenshot analysis, and shell execution. Supports Browser Use cloud sessions, Playwright integration, and LLM-driven desktop control. Use when asked about sandboxes, computer use, browser automation, E2B, desktop control, visual testing, or cloud Linux environments.
Skill for the E2e area of Securacy. 3 symbols across 1 files.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name