Trending Skills
The hottest skills gaining momentum in the community right now.
using-cache-directive
by djankies
Teach Cache Components model with 'use cache' directive in Next.js 16. Use when implementing caching, optimizing performance, working with dynamic data, or migrating from Next.js 15 caching patterns.
configuring-image-optimization
by djankies
Teach image optimization configuration changes in Next.js 16. Use when configuring images, troubleshooting image loading, or migrating image settings.
plan-validate-execute-template
by djankies
[REPLACE] Plan changes, validate before execution, execute with verification. Use when [REPLACE with specific triggers].
humanizer-cz
by mirecekd
Czech AI text humanizer skill for Claude and other LLMs. Detects and removes signs of AI-generated writing from Czech text. Based on academic research (Milicka et al. 2025, Al Ali 2025, Sigut 2023, MULTITuDE benchmark) and community observations of Czech AI writing patterns. Covers 27 patterns including: static nominal constructions, overused AI vocabulary, rigid word order, absence of obecna cestina, formulaic transitions, and low entropy.
SKILL — FindATruck AI Engineer & Product Guardian
by Jezza5153
You are here to ship a stable, fast, trustworthy product.
everclaw
by profbernardoj
Open-source first AI inference — GLM-5 as default, Claude as fallback only. Own your inference forever via the Morpheus decentralized network. Stake MOR tokens, access GLM-5, GLM-4.7 Flash, Kimi K2.5, and 30+ models with persistent inference by recycling staked MOR. Open-source first model router routes all tiers to Morpheus by default — Claude only kicks in as an escape hatch when needed. Includes Morpheus API Gateway bootstrap for zero-config startup, OpenAI-compatible proxy with auto-session management, automatic retry with fresh sessions, OpenAI-compatible error classification to prevent cooldown cascades, multi-key auth rotation v2 with proactive DIEM balance monitoring and reactive 402 watchdog, Gateway Guardian v5 with direct curl inference probes (eliminates Signal spam), proactive Venice DIEM credit monitoring, circuit breaker for stuck sub-agents, nuclear self-healing restart, always-on proxy-router with launchd auto-restart, smart session archiver, three-shift cyclic execution engine (v2 with 15-minute execution loops), 24/7 always-on power configuration for macOS, bundled security skills, zero-dependency wallet management via macOS Keychain, x402 payment client for agent-to-agent USDC payments, and ERC-8004 agent registry reader for discovering trustless agents on Base.
fullstack-engineering
by iam-prabha
End-to-end best practices for full-stack development — from architecture and design through deployment and production observability. Use this skill when building, scaling, or shipping any web application across the entire stack (frontend, backend, database, DevOps, security, testing, and monitoring). Produces production-grade, maintainable, and secure software.
omni-autonomous-agent (OAA)
by omnious0o0
Makes an AI agent autonomous and able to work for a long time, or a fixed duration without interruptions. Use this skill when the user asks you to work autonomously (e.g., "Work overnight," "I'll be gone for a few hours, work on this," "keep working on this until it's done," etc.). Basically any task that could take longer than usual. (3+ minutes)
srt-translate
by c-kick
Vertaal Engelse SRT ondertitelbestanden naar Nederlands, of review bestaande Nederlandse ondertiteling. Volgt Netflix Dutch Timed Text Style Guide + Modelrichtlijnen Nederlandse Ondertiteling (Auteursbond). Gebruik bij verzoeken om EN→NL ondertitelvertaling, SRT lokalisatie, of review/controle van bestaande NL ondertitels tegen EN bron. Niet voor algemene vertaling zonder SRT-bestand, niet voor ondertiteling in andere talen dan Nederlands, niet voor audio-transcriptie. Primaire methode: orchestrate.sh pipeline (script-gestuurd, headless). Alternatief: interactieve modus voor losse fasen of review.
checkmate
by InsipidPoint
"Focus your agent on a long-running task and keep iterating until your satisfaction criteria are met — not just a best-effort attempt. Use when you want to lock your agent into a quality loop: it converts your goal into machine-checkable criteria, spins up a worker, judges the output, feeds back gaps, and repeats until PASS or you call it done. Good for tasks where correctness matters: code that must pass tests, docs that must hit a standard, research that must be thorough, anything where 'good enough on first try' isn't acceptable. Triggers on 'checkmate: TASK', 'keep going until it passes', 'don't stop until done', 'quality loop', 'iterate until satisfied', 'judge and retry'."
pwa-review
by Alexis315
Comprehensive 185-point PWA audit beyond Lighthouse - analyzes manifest, service worker, offline capabilities, security, iOS compatibility, and advanced PWA features
holo-polymarket
by helebest
Polymarket 预测市场工具。查询热门预测、搜索市场、分析概率趋势、追踪大户持仓。
unbrowse
by getfoundry
Reverse-engineer any website into reusable API skills. Capture network traffic, discover endpoints, learn API patterns, execute learned skills, and manage auth for gated sites. Use when someone wants to scrape structured data from a website, discover hidden APIs, automate web interactions, or bypass the need for official API documentation.
SKILL.md — task-router
by manthis
```
Blog Platform
by Humans-Not-Required
GitHub: https://github.com/Humans-Not-Required/blog
excalidraw
by kerta1n
"Use when working with .excalidraw or .excalidraw.json files or user explicitly mentions excalidraw - delegates all Excalidraw operations to subagents to prevent context exhaustion from verbose JSON (single files: 4k-22k tokens, can exceed read limits)"
e2e-reporter
by dablon
"Automated E2E testing and evidence collection using Puppeteer. Use when you need to: (1) Verify application flows with real browser execution, (2) Capture screenshots for progress reports, (3) Inspect API responses in a live environment, (4) Generate verifiable evidence of feature completion."
Gemini API Development Skill
by aivexl
(Catatan: Langkah pengoperasian Merchant Dashboard ini ditambahkan sesuai arahan di luar spesifikasi murni Gemini API SDK)
fightbook
by resided
P2P AI Combat Arena - Configure fighters, watch them battle in real-time
esp-idf-helper
by 547895019
Help develop, build, flash, and debug ESP32/ESP8266 firmware using Espressif ESP-IDF on Linux/WSL. Use when the user asks about ESP-IDF project setup, configuring targets, menuconfig, building, flashing via esptool/idf.py, serial monitor, partition tables, sdkconfig, troubleshooting build/flash/monitor errors, or automating common idf.py workflows from the command line.
obsidian-plan-wiki
by Cygnusfear
Create and manage behavior specification wikis in Obsidian format. Use when creating specs, documenting features, or when user mentions "wiki", "spec", "feature", or "Obsidian".
finishing-a-development-branch
by Cygnusfear
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
superpower-zustand
by Cygnusfear
MANDATORY for creating Zustand stores. This skill is required when users request state management, creating stores, or mention Zustand. Do NOT create Zustand stores without this skill - all stores must use the required StoreBuilder pattern with immer middleware and factory pattern separation
chrome-devtools
by Cygnusfear
Control Chrome browser programmatically using chrome-devtools-mcp. Use when user asks to automate Chrome, debug web pages, take screenshots, evaluate JavaScript, inspect network requests, or interact with browser DevTools. Also use when asked about browser automation, web scraping, or testing websites.