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.Covers installation, authentication, model discovery, schema inspection, invocation, status polling, downloads, and error handling. Supports JSON scripting, account checks, serverless ComfyUI deployments, and dataset and LoRA training operations.
Executes chaos engineering experiments for specialized resilience testing. Supports workflows for running chaos tests and injecting failures into systems.
Executes automated release tests using a pre-configured AWS DevOps Agent test profile. Validates multi-step workflows, features, API endpoints, and regressions through UI or API testing.
Provides a starting point for pods, serverless endpoints, templates, network volumes, and container images. Routes provisioning and multi-step tasks to specialized Runpod skills and indexes end-to-end examples.
Manage Runpod infrastructure through the connected Runpod MCP server's tool calls (pods, serverless endpoints and jobs, templates, network volumes, registry credentials, secrets, clusters, the GPU/CPU catalog, and billing), and connect the server when it is missing (hosted or local npx). Load it before the first Runpod MCP tool call of a request: it routes the task to the journey skill that carries the procedure, owns the answer contract and the rules on which resources you…
Inventories Runpod API usage, rewrites call sites for REST v2, flags breaking changes, and verifies the migration. Also supports assessing a codebase's current API versions and the impact of upgrading.
Explains template contents, ports, paths, version pinning, and first-boot gaps. Helps diagnose boot failures, unreachable interfaces, missing models, CUDA mismatches, and imported ComfyUI workflow metadata issues.
Provides guidance on pods versus serverless, GPU and VRAM selection, storage, container builds, and networking. Describes provisioning, SSH execution, readiness checks, and installation practices, with execution delegated to Runpod tools.
Uses the Runpod CLI to manage pods, endpoints, templates, volumes, models, and Hub deployments. Covers scripting, SSH setup, diagnostics, and file transfers, including sessions without connected Runpod MCP tools.
Guides runtime creation and state access for threads, messages, composers, and attachments. Covers local and external stores, providers, selectors, capabilities, and adapters, with troubleshooting for provider errors, outdated hooks, rerender loops, and state updates.
Design a self-improvement loop for a shipped product's AI agents — production traces feed evals, evals feed improvement proposals (prompts, playbooks, retrieval configs), and a human approval gate promotes changes with rollback. Technique-agnostic: chooses per project between ACE-style evolving playbooks, GEPA/MIPROv2 offline optimization, or simple eval-driven iteration via references/techniques.…
Covers Rust async programming with Tokio, async traits, error handling, and concurrency patterns. Supports asynchronous application development, concurrent systems, and async code debugging.
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