Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM. Use when user says "deploy model", "serve model", "start vLLM server", "launch SGLang", "TRT-LLM deploy", "AutoDeploy", "benchmark throughput", "serve checkpoint", or needs an inference endpoint from a HuggingFace or ModelOpt-quantized checkpoint. Do NOT use for quantizing models (use ptq) or evaluating accuracy (use evaluation).
Prepare and run a release you can explain and undo — exact artifact identity, environment parity, config and secrets, a rollout strategy matched to blast radius, and a preflight that names the abort condition in advance. Use when planning or performing a deploy, building a release path, or when someone says "ship it" and the steps are not written down anywhere. Not for proving the deployed thing is healthy (release-verification) or for getting back out (rollback), and it never treats a green build or an approved plan as permission to deploy.
Import, release, and manage Falcon Fusion workflow definitions in a CID. TRIGGER when user asks to import a workflow, release a workflow version, list existing workflows, check for duplicates, or manage workflow definitions. DO NOT TRIGGER for writing YAML (use authoring), executing workflows, or monitoring (use execution).
GCP deployment patterns for Cloud Run, Cloud Build, Terraform, OAuth. Use when deploying services, setting up CI/CD, or troubleshooting deployment issues.
How this repo is built and served in production (Cloudflare Pages). Read before changing build output, scripts, Node/pnpm version, redirects, headers, or the `site` URL.
Safe release practices when shipping a change to a real environment — pre-deploy checklist, rollback plan, gradual rollout (feature flags/canary), and post-deploy verification. Use when the user asks to deploy, release, ship to production/staging, or plan how a risky change should go out. Not for local git branch management (see branching) or CI pipeline configuration itself — this is about the judgment calls around a release, not the mechanics of any one platform.
Deployment workflows, pre-deploy validation, smoke testing, and rollback procedures. Use when deploying to staging or production, running smoke tests, validating deployments, or planning rollback. Do NOT use for local development or CI pipeline configuration.
Deployment workflows, pre-deploy validation, and smoke testing patterns. Use when deploying to staging or production, running smoke tests, or validating deployments.
Use when deploying to a Salesforce org. SF CLI source deploy, metadata API, package deployment, validation-then-quick-deploy, rollback planning, and production deployment best practices.
Generates code that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Bedrock. Use when the user says "deploy my model", "create an endpoint", "make it available", or asks about deployment options. Identifies the correct deployment pathway (Nova vs OSS), generates deployment code, and handles endpoint configuration.
Deploy Sablier EVM contracts (Utils, Flow, Lockup, Airdrops, Bob) with full workflow automation. This skill should be used when the user asks to "deploy", "deploy protocol", "deploy to chain", or mentions deployment-related tasks. Handles contract deployment, explorer verification, SDK updates, and initial setup through Init scripts.
Use this skill for BlueField-3 (BF3) day-1 platform bring-up via the classic RShim/BFB path: pushing a BlueField bundle (BFB) to the DPU over RShim with bfb-install from the host, the host-to-DPU TMFIFO management channel (tmfifo_net0, the 192.168.100.x convention), RShim daemon state and console-over-rshim, DPU mode selection (DPU/embedded-function vs separated-host/NIC mode) via mlxconfig, post-BFB recovery, a six-state BlueField-state classifier, and verifying the install (cat /etc/mlnx-release plus version checks). Trigger even when the user does not say "BF3" — typical phrasings include {push a BFB to my BlueField-3}, {bfb-install exited 0 but the DPU never came back}, {ping 192.168.100.2 works but ssh fails}, or {is DOCA on the host or the Arm side?}. BFB reflash, mlxconfig set, mode changes, and firmware burns are destructive: require explicit target-bound confirmation and load doca-hardware-safety. App launch, container deploy, env install, and the BF4 BMC-Redfish path route elsewhere.
WARNING: guides potentially IRREVERSIBLE BlueField-4 hardware operations (PLDM firmware burns, ISO reflashes, power cycles, BMC factory resets) that can brick firmware, corrupt boot media, or cause outages — a maintenance window and rollback plan are required, and every mutating step is governed by doca-hardware-safety, loaded alongside. Use this skill for BlueField-4 (BF4) day-1 platform bring-up from the BMC: installing the BlueField/DOCA bundle ISO onto the DPU (Grace, the Arm complex) over UEFI HTTP Boot, PXE, or Redfish Virtual Media; the PLDM firmware-update flow (BMC, NIC firmware, SBIOS, ERoT) via the Redfish UpdateService and pldmtool; and a Grace Ubuntu image with optional cloud-init. Trigger on BlueField-4/BF4 bring-up phrasings even without "BF4": {bring up my new BlueField-4}, {the BlueField ISO will not boot over HTTP from the BMC}, {attach BF4 virtual media via Redfish}, {BF4 firmware Task stuck at Running}. BF3 bring-up, application launch, and library APIs belong to other skills.
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
NVIDIASkill
