熱門 Agent Skills

Write the hackathon challenge document teams read before they build - problem statements sized to the time box, thematic challenge tracks, the published rules and eligibility text, the submission-artifact checklist, sponsor-challenge framing, and naming (never weighting) the evaluation categories.

Review a spec or plan with a panel of six reviewers across two model tiers and three topics, gating the next workflow step with a Blockers/Warnings/Observations verdict.

Use the Modern Go Guidelines CLI when writing, modifying, fixing, or refactoring Go code, applying its version-specific guidance.

Create or update a reviewable pull request for the intended branch.

Interact with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills.

Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF files to GitHub-Flavored Markdown.

Choose a technical event's structure before anything is scheduled - the event shape (recurring meetup, hackathon, unconference day, single-day or multi-day conference), one program or several (single versus multi-track), workshop-day ratios, the session-format mix (curated talks, workshops, open space, ignite, fireside chats, panels), delivery mode (in-person, virtual, hybrid), and hackathon demo/judging structure.

Evaluate Expo skills end-to-end: trigger accuracy, generated code quality, and runtime screenshots on iOS simulator and Android emulator via Expo Go (web optional).

Core infrastructure extension providing backend connection configuration, storage client, and React app entry point.

Analyze a completed Meticulous test run — compare the diffs against the PR description to see what's expected, then focus on finding and flagging potential regressions.

Performs multi-source cross-validation of academic references, comparing authors, titles, years, volumes, issues, and pages field-by-field, and outputs a structured verification report.

小说封面生成。根据书名、作者名自动分析题材风格，调用 GPT-Image-2 生成含标题和署名的专业级网文封面；Codex CLI 优先使用内置 ImageGen，无需单独 API Key。触发方式：/story-cover、/封面、「帮我做个封面」「生成封面图」「做个小说封面」「封面设计」。

Fan out N parallel workers, drain them, and return one report.

Creating and shaping three.js geometry: built-in shapes, 3D text, vertex buffers and attributes, merging, instancing, batching, point clouds and lines, on WebGL or with WebGPU and TSL.

Walden drafts and maintains feature specs in `.walden/specs/` with EARS requirements, reviewed design, tasks, and executable proofs.

Diff the codebase against GitHub issues and matching docs; do not invent a backlog.

Connects to and performs inference with Google Cloud Agent Platform GenAI models, including Gemini and OpenMaaS models.

Vue 3 patterns with Clerk — composables (useAuth, useUser,

Configure and use EAS Update for over-the-air JavaScript and asset updates with expo-updates and EAS CLI.

Pick the date a technical event runs on - the decision every other plan hangs off.

Caffeine AI skill for posting to X (Twitter), mandating the x-client mops package with OAuth 2.0 PKCE flow.

Guides the usage of the Gemini Interactions API on Gemini Enterprise Agent Platform for multi-turn conversations, background execution, streaming, structured output, and function calling.

一套模板驱动的数据可视化与报告生成 skill，既能严格从 Lupi、Basics、Glance、Maps 与 Interactive gallery 的真实实现生成 HTML 图表，也能从 12 套中英文整页报告模板生成可发布的 HTML 报告；以 Mono 为保底，能按数据语义自动选择内置彩色预设，也支持用户明确提供的自定义色板。地图仅在用户明确要求时启用，同一交付禁止混用色系。

Audit a Google Business Profile, compare it to local competitors, and map Maps visibility around a location.

Build production Roblox interfaces with ScreenGui/PlayerGui lifecycle, responsive UDim2 layouts, safe insets, reusable editable Instances, cross-device input and selection, restrained motion, cleanup, and multi-viewport verification.

Triage new issues in the Sentry `javascript` project by archiving non-actionable noise.

Explore a codebase with parallel agents, then hand off findings.

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns.

Build custom authentication flows with Clerk hooks (useSignIn, useSignUp) and customize component appearance via themes, colors, fonts, and CSS.

Document and type a Sentry API endpoint.

Payment support based on Stripe, supporting credit cards and debit cards.

gh-stack is a GitHub CLI extension for managing stacked branches and pull requests, splitting multi-part work into reviewable layers.

Plans, executes, and validates Google Kubernetes Engine (GKE) cluster upgrades and maintenance operations for both Standard and Autopilot clusters.

Defensive Golang coding against accidental bugs — nil panics, typed-nil interfaces, `append` backing-array aliasing, silent int64-to-int32 truncation, float `==` comparison, `defer` inside loops, defensive copies of slices and maps, and usable zero values.

Guides a developer's first steps on Google Cloud, covering account creation, billing setup, project management, and deploying a first resource.

Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA modes.

Generate self-contained HTML visualizations with Plannotator theming.

Operate the Resend platform from the terminal — send emails (including React Email .tsx templates via --react-email), manage domains, contacts, broadcasts, templates, webhooks, API keys, logs, automations, and events via the `resend` CLI.

TypeScript best practices.

Apply, review, and explain discriminated unions in TypeScript.

Write an ordered plan without changing implementation.

Create, record, edit, replay, or repair reusable Argent flow YAML files.

Confirm a change before merge.

EAS Hosting skill: deploy Expo websites and API routes to EAS Hosting, covering export, deploy, environment variables, custom domains, and the Cloudflare Workers runtime.

Mandatory recipe for every Caffeine build that calls OpenAI (ChatGPT, GPT-4o, an LLM, a chatbot, embeddings), supporting only the openai-client mops package with a canister-side API-key bearer.

here.now lets agents publish websites and files to live URLs in seconds.

Run a Meticulous test run after implementing a frontend change, then hand off to the `meticulous-review` skill to classify each visual change as intended or unintended.

Test an application against the OWASP Top 10:2025 and API Security Top 10 with Strix autonomous AI agents that attempt real exploits and report only provable findings.