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.Uses @upstash/qstash for background jobs, cron schedules, delayed messages, FIFO queues, and endpoint fan-out. Covers retries, callbacks, dead letter queues, deduplication, flow control, webhook signature verification, local development, and region migration.
Uses @upstash/ratelimit to throttle requests by user, IP, API key, or tenant. Covers fixed and sliding windows, token buckets, deny lists, caching, analytics, multi-region limits, timeouts, and Redis command cost estimates.
Work with the @upstash/redis TypeScript/JavaScript SDK, a serverless HTTP-based Redis client for Next.js, Vercel, Cloudflare Workers, edge runtimes, and Node.js. Use when adding a cache (cache-aside, write-through, TTL and expiration strategies), session storage and user sessions, a key-value store, leaderboards and rankings with sorted sets, counters, distributed locks, queues with lists, streams and consumer groups, sparse index-addressed arrays and ring buffers (ARSET, AR…
Supports Upstash Workflow and QStash implementation. Covers handlers, triggers, durable execution steps, and asynchronous fan-out.
Creates multi-step workflows that survive timeouts, retries, and restarts. Covers durable steps, sleeps, API calls, external events, nested workflows, approvals, concurrency controls, failure handling, run management, local development, and safe migrations.
Drafts reproducible, maintainer-ready GitHub issues for upstream mlx-vlm from check_models failures or native repros, starting from existing diagnostics and issue_*.md drafts. Use for crashes, load or processor failures, wrong outputs, media-input bugs, and regressions.
Verifies explicit authorization and completes pull request grooming before upstream submission actions. Applies to creating or reopening a pull request and requesting review.
Maintains a configurable registry of upstream sources supporting plugin development rules. Ranks authority and volatility, prioritizes rechecks using local citations, tracks verification status, and checks freshness on request. Supports custom sources and ranking overrides.
Analyzes dashboard data to diagnose the market environment with a 0–100 composite score. Combines breadth, sector participation, rotation, momentum, and historical context; no API key is required.
URDF robot description authoring and validation. Use when creating, editing, inspecting, validating, or debugging `.urdf` files, robot links, joints, limits, inertials, visual/collision geometry, mesh references, frame conventions, or robot-description artifacts. Use the SRDF skill for MoveIt2 semantic groups and IK/path-planning semantics; use the CAD skill for STEP/STL/3MF/DXF/GLB outputs. Open and visually review existing URDF files in CAD Viewer.
Sets up, configures, and debugs URP post-processing with the Volume framework. Use for bloom, tonemapping, color adjustments, depth of field, vignette, or other Volume overrides.
Uses the revised Minsky/Kindleberger framework v2.1 to evaluate bubble risk from indicators such as put/call ratios, VIX, margin debt, breadth, and IPO data. Requires data collection and mechanical scoring, with strict qualitative adjustments to limit confirmation bias.
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