Loading...
Loading...
Found 779 Skills
Grafana Professional Services tool for identifying which Prometheus metrics drive high Data Points per Minute (DPM). Analyzes metric-level DPM with per-label breakdown to help optimize Grafana Cloud costs. Use when the user asks about DPM analysis, high-cardinality metrics, metric cost optimization, finding noisy metrics, or running dpm-finder against a Grafana Cloud Prometheus endpoint.
Omi AI wearable platform help — open-source AI necklace for all-day conversation capture (in-person + online meetings), Developer API (`api.omi.me/v1/dev`, Bearer token, 100 req/min), app marketplace with webhook integrations, memories/conversations/action-items endpoints. Use when setting up an Omi wearable for meeting capture, building a custom Omi app or integration, troubleshooting Bluetooth disconnects or transcription accuracy, connecting Omi to Slack or CRM via webhooks, comparing Omi to Plaud or Limitless for in-person recording, or accessing Omi's API to export conversations and action items. Do NOT use for choosing between software-only note-takers without wearable needs (use /sales-note-taker).
Image Generation Skill: Use this skill when users need to generate images, visual infographics, create graphics, or edit/modify/adjust existing images. Based on the official formal version of the ChatGPT Image 2 model (gpt-image-2) from Apiyi Platform (https://api.apiyi.com/). This model supports precise size/quality control (including 4K) and is billed by token. Key differences from gpt-image-2-all (official reverse version): Uses /v1/images/generations and /v1/images/edits endpoints; Has explicit size parameter; Has quality parameter; Billed by token; Uses multipart/form-data to upload reference images; b64_json is pure base64 without prefix.
Use this skill when the user asks to call an authenticated HTTP API (for example "call the GitHub/OpenAI/Slack API", "hit an endpoint that needs a bearer token") and the `sesame` CLI is already installed on this device. The agent invokes `sesame request`, which forwards the HTTP call through the user's own broker and attaches the auth header server-side. The skill does not install software, does not read credentials from the environment, and runs shell only within the fixed `sesame` subcommand surface (`request`, `status`, `hostnames`, `login`, `refresh`). Skip for unauthenticated public endpoints, localhost services, or when the user has already exported a token in the environment for direct use.
Builds production AI/ML systems — model training, fine-tuning, MLOps pipelines, model serving, evaluation frameworks, RAG optimization, and agent orchestration at scale. Use when the user asks to build, train, or deploy ML models, set up MLOps pipelines, optimize RAG systems, create inference endpoints, or design production AI agents.
Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance. Triggers on: "production checklist", "harden agent", "production ready", "secure agent", "inbound auth", "going live", "cold start optimization", "session lifecycle", "StopRuntimeSession", "quota", "throttling", "maxVms", "rate limit", "security audit of outbound API calls", "gateway target audit for production", "restrict who can call", "lock down endpoint", "only our app can call". Not for Cedar tool-restriction policies — use agents-connect. Not for quality measurement — use agents-optimize. Not for outbound credential storage or API key wiring — use agents-connect. Not for A2A agent-to-agent auth — use agents-build. Cold start observation and diagnosis (not optimization) routes to agents-debug.
Every Trigger.dev management endpoint, plus offline FTS over runs, span-cost rollups, and zombie-schedule detection no other tool gives you. Trigger phrases: `trigger.dev failed runs`, `trigger.dev cost rollup`, `trigger.dev schedule health`, `audit trigger.dev env vars`, `watch trigger.dev failures`, `use trigger-dev`, `run trigger-dev`.
Music generation queueing, retrieval, and completion endpoints via Venice.ai. Suited for jingles, background loops, and prototype scoring.
Registers engine-level middleware functions that run before HTTP handlers. Use when adding authentication, request logging, rate limiting, or any pre-handler logic to HTTP endpoints.
Web content fetching via curl and WebFetch when a specific URL is provided. Covers HTTP GET/POST, JSON APIs, HTML, auth, cookies. Triggers on: "fetch this URL", "download HTML", "call this API", "curl this endpoint". NOT for search, use tavily.
Query, search, and download data from the openFDA API for drugs, devices, foods, tobacco, cosmetics, animal and veterinary products, substances, and transparency data. Use for FDA adverse events, recalls, labeling, approvals, shortages, 510(k) clearances, NDC lookups, and any FDA safety or regulatory data query across all 28 API endpoints.
Design carrier- and enterprise-scale backbone networks—core/distribution/edge topology, OSPF, IS-IS, BGP and route policy, WAN/MPLS/SD-WAN, DCI, peering, transit, IX, anycast, ECMP, BFD, FRR, addressing, backbone QoS, capacity, maintenance domains, and observability (NetFlow, SNMP, telemetry); EVPN/VXLAN spine-leaf where relevant. This skill should be used when the user asks about network backbone, backbone architect, BGP design, OSPF, IS-IS, WAN architecture, MPLS, SD-WAN, data center interconnect, DCI, internet peering, transit provider, IX, core network design, route policy, ECMP, network redundancy, spine-leaf, or EVPN—not app HTTP/API (enterprise-integration-api-developer), cloud landing zone or VPC only (cloud-architect, enterprise-cloud-architect), host or endpoint security (information-security-engineer), cloud/Linux sysadmin (cloud-system-administrator), cabling without routing (infrastructure-engineer), or OT/ICS (scada-ics-cyber-security-specialist).