AGENT SKILLS · EQUIPAGGIAMENTO / TerminalSkills

TerminalSkills · Agent Skills

1053 skills with substantive source documentation and an official publisher or observed installation demand. Read each skill’s original documentation through its card.

TerminalSkills

Community

bug-hunt-swarm

Finds the cause of a hard bug by running several read-only subagents in parallel, each attacking it from a different angle (change history, code path, data and state, environment, reproduction), then checking their evidence, ranking the hypotheses and naming the one experiment that would confirm the leader. It diagnoses and does not fix. Use when someone says "hunt this bug with multiple agents", "swarm on this regression", "investigate in parallel", "find the root cause", or when a failure is i

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

building-spec

Read and apply a project-specific BUILDINGSPEC.md or DIMENSIONS.md file before generating any architectural elements. Use when: generating floor plans, 3D buildings, or any spatial design where the project has defined custom dimensions, room requirements, or design standards.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

bull-mq

Runs background jobs in Node.js with BullMQ, a job queue library backed by Redis (or PostgreSQL since v6): delayed and prioritized jobs, retries with backoff, rate limiting, cron-style job schedulers, parent-child flows and concurrency control. Use when a user asks to add a background worker, queue emails or webhooks, schedule recurring jobs, retry failed jobs, rate limit an API client, or migrate from Bull or from BullMQ 5 repeatable jobs.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

bun

Assists with using Bun as an all-in-one JavaScript/TypeScript runtime, package manager, bundler, and test runner. Use when building HTTP servers, managing packages, running tests, or migrating from Node.js. Trigger words: bun, bun serve, bun install, bun test, bun build, javascript runtime, bun runtime.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

bun-runtime

Bun — fast all-in-one JavaScript runtime, bundler, test runner, and package manager. Use when speeding up Node.js projects, using Bun as a drop-in Node replacement, bundling with Bun, or running tests faster. Covers runtime APIs, package management, bundling, and Bun-specific features like Bun.serve, Bun.file, and bun:sqlite.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

burp-suite

Test web application security with Burp Suite. Use when a user asks to intercept HTTP traffic, test for web vulnerabilities, fuzz API endpoints, analyze authentication flows, or perform manual web application pentesting.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

business-finance-fundamentals

Understand essential business finance — profit margins, unit economics, cash flow, LTV/CAC, and the 4 methods to increase revenue. Use when: analyzing business profitability, making pricing decisions, evaluating SaaS unit economics, financial planning.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

cache-strategy

Design and implement caching layers for APIs and web applications using Redis or Memcached. Use when you need to reduce database load, improve response times, or handle traffic spikes. Covers cache-aside, write-through, and write-behind patterns, TTL strategies, cache invalidation, and stampede prevention. Trigger words: cache, Redis, Memcached, TTL, cache invalidation, response time, throughput, rate limiting.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

caddy

Caddy is a web server and reverse proxy that obtains and renews HTTPS certificates automatically. Covers reverse proxying, load balancing, file serving, redirects, headers, rate limiting, and configuration through the admin API. Use when tasks involve serving websites, proxying to backend services, automatic TLS certificate management, or replacing Nginx with a simpler configuration.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

cal-com

Cal.com is an open-source scheduling platform for booking pages, availability and calendar sync, with an embed, a REST API v2 and webhooks. Use when the user wants to add a booking widget to a React or plain site, create event types, list free slots, create, cancel or reschedule bookings through the Cal.com API, verify booking webhooks, set up round-robin team events, or self-host a community edition (Cal.diy) with Docker.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

calendar-integration

Integrate with Google Calendar and Microsoft Outlook Calendar for scheduling, event management, and availability tracking. Use when someone asks to "create calendar events", "check availability", "schedule meetings", "sync calendars", "Google Calendar API", "Outlook Calendar API", "booking system", "find free slots", or "manage recurring events". Covers Google Calendar API v3, Microsoft Graph Calendar API, event CRUD, availability/free-busy queries, recurring events, and building scheduling feat

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

canny

Canny is a hosted product-feedback tool with feature-request boards, voting, a public roadmap and a changelog. Use when a user asks to set up a feature request board, identify logged-in users in Canny, embed the feedback widget, create or list posts through the Canny API, change a post's status, or verify Canny webhooks.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

canva

Automate Canva from an agent — via the AI Connector MCP server (generate, find, edit, export designs in natural language) or the Connect REST API (OAuth 2.0 + PKCE, brand template autofill, asset uploads, exports, folders, comments). Use when: connecting an agent to Canva, batch-producing social posts or decks from a brand template and a spreadsheet, exporting designs to PDF/PNG/PPTX/MP4, uploading assets into a Canva account, building a Canva integration, or when the user mentions "Canva", "bra

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

canvas-api

Draw 2D graphics with the HTML5 Canvas API — shapes, text, images, gradients, transformations, pixel manipulation, and offscreen rendering. Use when tasks involve generating images server-side (with node-canvas), creating charts, image compositing, watermarking, or browser-based drawing applications.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

capacitor

Capacitor is a runtime that packages a web app as a native iOS and Android app and exposes native device APIs to JavaScript. Use when someone asks to "convert my website to a mobile app", "Capacitor", "web to native app", "access camera from JavaScript", "deploy web app to App Store", "hybrid mobile app", or "Ionic Capacitor". Covers native API access, plugin system, web-to-native bridge, and app store deployment.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

capacity-planner

Translates performance test results into infrastructure scaling recommendations with cost estimates. Use when someone has load test data and needs to know what infrastructure changes are required to handle target traffic. Trigger words: capacity planning, scaling plan, infrastructure sizing, how many pods, RDS sizing, handle more traffic, scale for launch.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

caprover

Expert guidance for CapRover, the open-source PaaS that turns any Linux server into a Heroku-like platform with automatic HTTPS, one-click app deployment, and Docker-based containerization. Helps developers deploy applications, configure custom domains, and manage the CapRover cluster.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

cassandra

Apache Cassandra is a distributed NoSQL database designed for high availability and linear scalability. Learn CQL (Cassandra Query Language), data modeling with partition keys, replication strategies, and integration with Node.js using the DataStax driver.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

cc-connect

Bridge local AI coding agents (Claude Code, Cursor, Gemini CLI, Codex) to messaging platforms (Slack, Telegram, Discord). Use when: controlling AI agents from team chat, sending coding tasks via Slack/Telegram, building team-accessible AI workflows.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

ccpa-compliance

Builds California Consumer Privacy Act (CCPA, as amended by CPRA) compliance features: consumer request handling, opt-out of sale/sharing, Global Privacy Control detection and privacy-notice content. Use when serving California users, building privacy features, implementing consumer data rights, or responding to data subject requests.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

celery

Celery is a Python distributed task queue: web code puts jobs on a broker (Redis or RabbitMQ) and separate worker processes run them, with retries, schedules, rate limits and result storage. Use when a user asks to process tasks asynchronously, schedule periodic jobs, run background workers, build task queues in Python, or offload heavy processing from web requests in Django, Flask or FastAPI.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

censys

Censys search engine for internet-connected hosts, TLS certificates, and web properties. Use when: certificate transparency monitoring, finding hosts by certificate fingerprint, alternative to Shodan for TLS/SSL analysis, discovering hosts running specific services, or tracking infrastructure changes via cert issuance.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

centrifugo

Centrifugo is a self-hosted real-time messaging server: your backend publishes over an HTTP or gRPC API and browsers or mobile apps receive messages over WebSocket, SSE or HTTP streaming. Use when the user wants chat, live notifications, presence ("who is online"), message history with recovery, or any WebSocket pub/sub without writing a socket server.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

cerebras

Cerebras Inference is a hosted LLM API that runs open models on Cerebras wafer-scale chips at thousands of tokens per second, through an OpenAI-compatible endpoint. Use when a user wants the lowest-latency chat, code completion or agent loop, asks how to call the Cerebras API or SDK, needs streaming, tool calling, strict JSON schema output or reasoning control, or hits a "model not found" error from a retired Cerebras model ID.

installazioni: 0
GitHub Stars: 180
Aggiornato: 25 ott

Apache-2.02 File

Vedi dettagli →