Loading...
Loading...
Found 8,425 Skills
Find the cheapest fuel prices near the user's current location in Australia. Use this skill whenever the user asks about fuel prices, petrol prices, gas station prices, servo prices, cheapest fuel, diesel prices, E10 prices, or wants to compare fuel costs nearby. Also trigger when the user mentions filling up, refueling, or asks "where should I get fuel/petrol/diesel". Works across all Australian states with zero configuration — no API keys needed. Works in any environment — Telegram, WhatsApp, Signal, Discord, terminal, or any chat platform.
Use when tasks are complex and require full microservices collaboration: The main agent acts as a pure Orchestrator, strictly prohibited from writing code personally, and is responsible for accurately assigning responsibilities such as positioning, planning, coding, testing, and review to corresponding sub-agents (explorer, planner, worker, verifier, reviewer, fixer). This Skill enforces microservices workflow discipline, requiring full Chinese communication, minimal routing output, and minimized context transfer.
Design procedural content systems with seeds, constraints, and validation gates so generated output stays fun and shippable.
Research this project against the real code and write a detailed report.
Migrate an existing Prisma project to ZenStack V3. Use when replacing Prisma/@prisma/client with ZenStack, converting schema.prisma to ZModel, swapping PrismaClient for ZenStackClient, updating generate/migrate scripts, mapping Prisma custom generators and client extensions, or keeping Prisma migrate tooling working.
Create or revise titles for local-member topics or existing Xiaohongshu drafts that a fitness coach has already settled on. Use this when the user already has a specific question, working title, or body copy and only wants to compare title angles and select a title to publish; it reads the coach’s activated Person DNA to verify the local audience, real evidence, and whether the body copy can deliver on the promise. It is not responsible for selecting topics from broad directions or writing an entire draft.
Use when a change spans more than one statement or file - a release or migration script, "chay script DDL", "deploy ban release", "run these .sql files", a table with its comments and indexes, a package spec and body together, a directory of numbered scripts. Orders the statements, previews every one, gets one approval for the set, runs them through apply's six steps in order and stops at the first failure.
Use when preparing or performing a review delegated to a subagent, or coordinating its findings, authorized fixes, and re-review. Applies to reviewer subagents invoked through the host application’s delegation features or through CLI tools, including review phases within another task. Don’t use merely for a main agent’s direct review or self-review, reports supplied from another conversation, or standalone findings verification.
Make the agent back up its work with evidence instead of merely saying “Done.” Use this in three situations: when the agent is about to hand off the work; when the user corrects the agent about the same issue for the second time (it is wrong again, how many times have I said this, how can I stop it from recurring); or when writing tests or cleaning up useless tests. Prove it, stop repeating this mistake, clean up useless tests.
Writes technical blog posts about features being built. Triggers when user asks to write about development progress, implementations, or project updates.
Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.
Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.