prelude-docs
Manage a consumer repo's Prelude docs viewer content — prelude.docs.pages, groups, mdSplit README hero, and generated nixosOptions pages. Use when adding or…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-10 00:15
All skills
249,253 results
databricks-genie-agents
Create, manage, and query Databricks Genie Agents — curated, per-data natural-language agents (formerly Genie Spaces): build, export/import, migrate across…
clinpgx-database
Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and…
Pentest Commands
This skill should be used when the user asks to "run pentest commands", "scan with nmap", "use metasploit exploits", "crack passwords with hydra or john",…
claude
Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate…
project-architect
Documentation-first project planning that produces implementation-ready blueprints and single-shot coding agent prompts. Generates 4 interconnected docs —…
chakra-ui
Chakra UI v3 (React component library) reference. Also known as: Chakra, chakra, chakra-ui. Components (Button, Input, Modal, Drawer, Toast, Menu, Tabs, Tooltip, etc.), ...
gadget-best-practices
Best practices for building Gadget apps. Use for Gadget-specific models, fields, actions, routes, access control, Shopify/BigCommerce integrations, frontend…
daily-task-prep
Morning preparation. Calendar lookahead, meeting context loading, open threads from yesterday, active task review. Extends briefing with actionable prep.
cboe-data
Datos de CBOE via APIs publicas: cotizaciones delayed de indices, futuros VX, charts intraday, most-active, market summary (equities + opciones), symbol…
qbcore-framework
Trigger: QBCore, qb-core, Player object, PlayerData, QBCore.Functions.GetPlayer, Player.Functions, QBCore callbacks, jobs, gangs, economy. Build qb-core…
create-context-tests
Generate a test suite of natural-language → SQL pairs that becomes the quality benchmark for a nao agent, then run it via `nao test`. Use when the user wants…
drupal-contrib-mgmt
Manages Drupal contributed modules via Composer - module updates and major-version upgrades, cweagans/composer-patches v2 (patches.lock.json, composer…
deliverability-checker
Check email deliverability and DNS configuration. Use when: diagnosing email delivery issues; setting up new email domains; auditing email authentication;…
openai-ui-skills
OpenAI's UI design system. Use when building interfaces inspired by OpenAI's aesthetic - light mode, Inter font, 4px grid.
ga4
Read Google Analytics 4 reporting data through the GA4 Data API. Use for explicit GA4 property metadata, compatible metric/dimension reports, traffic analysis,…
sw-format-adaptation
Screenplay format, page craft, the writing process and adaptation (剧本格式/写作流程/改编) — merged from Wendy Henson (spec format rules), Richard Walter (page craft,…
jupiter-vrfd
Use when a user mentions Jupiter token verification, VRFD eligibility, paying 1000 JUP to verify a token, submitting a verification request, or updating…
home-assistant-manager
Manage Home Assistant configuration safely and fast — edit and deploy YAML (automations, blueprints, scripts, scenes, templates, MQTT), validate with ha core…
cypress-skill
Generates production-grade Cypress E2E and component tests in JavaScript or TypeScript. Supports local execution and TestMu AI cloud. Use when the user asks to…
webdriverio-skill
Generates WebdriverIO (WDIO) automation tests in JavaScript or TypeScript. Supports local and TestMu AI cloud. Use when user mentions "WebdriverIO", "WDIO",…
hidden-talent
Original text of the deep talent mining prompt. Use when the user wants to find their neglected or suppressed talents, doubts whether they have any talent, or wants a personal talent user manual. This is a multi-turn deep conversation lasting more than half an hour, asking only one question at a time, with at most ten main questions, and finally producing a user manual of about ten thousand words.
horizontal-vertical-analysis
Original text of the horizontal-vertical analysis prompt. Use when the user wants to deeply research an unfamiliar product, company, person, technology, industry, or event. Trigger words include horizontal-vertical analysis, deep research, help me understand this company, research this track, write a research report, vertical history horizontal comparison, deep research. Recommended to run with deep research or internet access capabilities, producing a 10,000 to 30,000 word traceable report.
no-fluff-output
Original text of the direct-output method prompt. Use when users complain that the AI talks verbosely and beats around the bush, want more direct and actionable answers, or get distracted by long passages. Trigger words include: cut the crap, get to the point, give me the conclusion, don't beat around the bush, just say it straight, no fluff, tell me what to do first, no nonsense, ADHD-friendly, not enough focus. Hang the whole thing at the start of a session to constrain the structure of all subsequent answers; it turns off only when the user says to return to normal mode.