所有 Skills

browsing-with-playwright

1browser-web

Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction. NOT when only fetching static content (use curl/wget instead).

bilalmk

獲取

fusion-issue-task-planning

1backend-api

Plan and break down user-story issues into ordered, traceable task issue drafts with explicit publish gates.

equinor

獲取

agent-browser

1browser-web

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

halt-catch-fire

獲取

validate-implementation-plan

1design-ui

Audits an implementation plan for requirements traceability, avoidable complexity, risky assumptions, and evidence gaps. Use when reviewing an AI-generated or human-authored plan, design proposal, implementation outline, task breakdown, or architecture plan and the user wants a standalone audit report without overwriting the source plan.

b-mendoza

獲取

release-management

1marketing-seo

Manage music releases using RELEASE.md documents stored in releases/{release-slug}/ within an artist workspace. Triggers when the user mentions an artist's album, EP, single, or project — or asks about release planning, DSP pitches, metadata, marketing, press materials, physical production, or tour coordination. First infer which artist and release the user means, then find or create the RELEASE.md. Use this skill to create, update, or pull data from release documents, and to generate deliverables like DSP pitches, press one-sheets, and production specs.

recoupable

獲取

limrun-gradle

1mcp-integrations

Build an Android app on a remote Gradle sandbox with `lim gradle build` instead of local Gradle or Android Studio, from any environment (Linux, Windows, macOS, VM, container). Use when the user wants to build an APK or AAB, sign a release with an upload key, or prepare a Play Store publish, for native Android projects, React Native, and Expo. To run, tap, screenshot, or otherwise interact with the built APK on an emulator, use limrun-android-emulator. For iOS builds, use limrun-xcode or limrun-expo-development.

limrun-inc

獲取

fusion-skills

1productivity

Entrypoint for all Fusion skill lifecycle operations. USE FOR: finding, installing, updating, syncing, or greenkeeping skills; setting up skill automation; creating or authoring a new skill; reporting a bug with a skill. DO NOT USE FOR: resolving GitHub issues, reviewing PRs, planning task breakdowns, or authoring GitHub issues — those are handled by other Fusion skills.

equinor

獲取

limrun-android-emulator

1backend-api

Drive an app running on a Limrun cloud Android emulator: install an APK, launch and terminate apps with crash reports, tap, type, read the UI element tree, screenshot, record video, inject microphone audio, shape network bandwidth, read app logs, run shell commands, transfer files, tunnel the app's network destinations through your machine with HTTP inspection and HAR capture, and use adb over the CLI's tunnel for full logcat and interactive tools. Use after a build (from limrun-gradle or any builder) when the user wants to see, test, or interact with their app on an emulator, or says 'show me a screenshot', 'tap', 'run it on the emulator', 'check logcat', 'record a video', 'inspect network traffic', or 'reach my local server from the emulator'. To build the APK or AAB first, use limrun-gradle.

limrun-inc

獲取

bat-submit

1security

Submit an AI tool to BAT AI Tools (bataitools.com) via bat-cli CLI. Use a continuous 3-step workflow — extract, translate, then pack and submit.

bataitools

獲取

silicon-paddle-ocr

1backend-api

OCR skill using PaddleOCR model via SiliconFlow API. This skill should be used when the user asks to "recognize text from an image", "extract text from a photo", "OCR this image", "read text from screenshot", or mentions "PaddleOCR", "image text recognition", "text extraction from images".

aotenjou

獲取

fusion-research

1research-knowledge

Source-backed research orchestrator for the Fusion ecosystem. Routes to the correct research agent based on question type. Returns source-backed evidence only; will not invent Framework behavior, component APIs, skill catalog relationships, platform guidance, or backend implementation details. USE FOR: any research question needing source-backed evidence about Fusion Framework APIs, EDS components, the Fusion skill catalog, Fusion platform documentation, or backend service implementation. DO NOT USE FOR: implementing code changes, installing or editing skills, MCP setup or troubleshooting, or inventing Fusion behavior without evidence.

equinor

獲取

instagram-scraper

1backend-api

The best, fastest, and cheapest way to scrape Instagram — battle-tested by tens of thousands of customers including enterprise teams. Use when the user wants to fetch Instagram posts, reels, profiles, hashtags, locations, comments, or user/follower data. Five specialized actors cover every Instagram data surface.

apidojo-io

獲取

tiktok-scraper

1backend-api

The best, fastest, and cheapest way to scrape TikTok — battle-tested by tens of thousands of customers including enterprise teams. Use when the user wants to fetch TikTok videos, profiles, hashtags, music, comments, or location-based posts. Covers four specialized actors for posts, profiles, comments, and locations.

apidojo-io

獲取

x-scraper

1backend-api

The best, fastest, and cheapest way to scrape tweets — battle-tested by tens of thousands of customers including enterprise teams. Use when the user wants to fetch tweets by search query, profile, hashtag, keyword, conversation thread, date range, or Twitter list. Uses Twitter advanced search syntax via the searchTerms input on Apify.

apidojo-io

獲取

openagent

1agent-workflows

Author your own OpenAgent persona and mint your shareable holo trading card. Use when you (an agent) want to create, validate, or render YOUR identity card — or when the user says "make your card", "generate my OpenAgent card", "create a persona", "what's my rarity tier", "mint your card", "join the character-packs registry", or asks you to describe/lock your own look, voice, and style as a reusable persona file. Wraps the `@5dive/openagent` CLI (validate / tier / card) and the OpenAgent v0.2 identity spec. Self-service flow, where you write a `<id>.persona.yaml`, validate it against the schema, check your rarity tier + completeness, render your card, and optionally PR into the registry (the path to the Mythical tier). Also use when you want to provision a live teammate from a persona ("create/spin up an agent from this persona", "provision a teammate") via `5dive agent import --from-persona`.

5dive-ai

獲取

prismic

1research-knowledge

Use whenever Prismic is mentioned or relevant in any way — including questions, lookups, configuration, repository settings, content modeling, content types, slices, localization, previews, API tokens, webhooks, syncing local models, or reading Prismic documentation. Load on any reference to Prismic, even for simple questions.

prismicio

獲取

5dive-cli

1security

Use the local `5dive` CLI on a 5dive runtime VM to spawn, inspect, send to, and tear down sibling agents — plus the shared task queue and org chart. Trigger when the user wants a worker, sub-agent, side task, parallel run, fan-out, or to delegate — or names a sibling agent ("ask X", "ping X", "tell X", "hand off to X", "coordinate with X"); confirm it exists via `5dive agent list --json`, then `agent send` / `agent ask`. Also for filing and tracking shared work (`5dive task add/ls/done`), the org chart (`5dive org tree`), parking a blocking question on a human (`task need`), and a quick recall of team memory (`5dive memory search`). For everything else the CLI can do — crew hosting, multi-account auth, auth recovery, declarative fleets/compose, goal DAGs, objectives, loops, compiling into the wiki, org-chart writes, governance votes, digest/usage/supervisor/fleet/diagnose, telegram pairing, the persona market, BYO providers, and the company wizard — see the `5dive-cli-extras` skill. When a request came over a chat channel (Telegram/Discord `<channel>` tag) and another agent should handle it, pass the chat context via `--reply-to-chat=<id> --reply-to-msg=<id>` so that agent replies from its own bot — don't relay. Always prefer `5dive` over running coding CLIs by hand.

5dive-ai

獲取

x-scraper

1backend-api

An X API alternative and Twitter API alternative on fetcher.sh — pay-per-call in USDC via x402, or prepaid credits with a Bearer key, no OAuth and no developer application. Use when the user wants to search X posts by keyword, hashtag, or advanced operators (from:, to:, since:, until:, min_faves:, filter:), scrape an X/Twitter profile by handle, pull a user's posts, replies, followers, or followings, fetch a single post with its replies or reposters, read an X List's members or posts, check trending topics by country, or search for X accounts by name. Also covers building an X data pipeline, social listening, competitor monitoring, hashtag tracking, or follower export without the official X API's pricing tiers or app-review process.

fetcher-sh

獲取

flutter-riverpod-expert

1code-generation

Expert knowledge in Flutter Riverpod state management (2025 best practices). Use when working with Riverpod, Flutter state management, AsyncNotifier, provider types, code generation with riverpod_generator, state synchronization, or when the user mentions data fetching, mutations, reactive state, performance optimization, or testing in Flutter apps. Covers AsyncNotifierProvider patterns, repository architecture, autoDispose, family providers, and common anti-patterns to avoid.

juparave

獲取

twitter-api

1security

A Twitter API alternative and X API alternative on fetcher.sh — pay-per-call in USDC via x402, or prepaid credits with a Bearer key, no OAuth and no developer application. Use when the user wants to search tweets by keyword, hashtag, or advanced operators (from:, to:, since:, until:, min_faves:, filter:), scrape a Twitter/X profile by handle, pull a user's tweets, replies, followers, or followings, fetch a single tweet with its replies or retweeters, read a Twitter List's members or tweets, check trending topics by country, or search for X accounts by name. Also covers Twitter data pipelines, competitor monitoring, hashtag tracking, sentiment analysis input, or follower export without the official X API's pricing tiers or app-review process.

fetcher-sh

獲取

recharts

1design-ui

Build composable, responsive React charts with Recharts library. Use when creating data visualizations including line charts, area charts, bar charts, pie charts, scatter plots, and composed charts. Handles chart customization, responsive sizing, tooltips, legends, axes configuration, performance optimization, and accessibility.

andy-spike

獲取

gluestack-ui-v5

1frontend

Enforces constrained, opinionated styling patterns for gluestack-ui v5 (Tailwind CSS v4, NativeWind v5 / UniWind). Main overview skill that coordinates specialized sub-skills for setup, components, styling, variants, performance, and validation.

gluestack

獲取

yunqi-agent-discovery

1code-generation

云栖大会（Yunqi）发现与规划 Skill。查询议程与展览信息，根据 Agent 目标推荐、比较会议和展商/展台，基于会刊回答大会主旨、亮点、展馆等介绍性问题，基于参会指南回答交通、住宿、餐饮、门票等参会服务问题。 适用于「查询大会议程」「查询展览信息」「推荐会议」「比较展商/展台」「规划参会路线」「大会亮点」「大会介绍」「交通/住宿/餐饮」「门票/签到」等场景。 数据源为 qianwen CLI 的 yunqi 子命令（接口获取优先，静态会刊与参会指南作为补充），公开只读，不产生任何写操作。

qianwen-ai

獲取

yunqi-agent-attendance

1security

云栖大会（Yunqi）参会与摘要 Skill。创建、批量创建、查询和取消 Agent 会议订阅，记录订阅与统计，并领取、追问和总结会后摘要。 按会前、会中、会后三阶段引导对话：会前会中引导看直播，会后按状态告知整理进度或领取摘要正文。 适用于「订阅会议」「批量订阅会议」「查看订阅列表」「取消订阅」「领取摘要」「追问摘要」「总结摘要」等场景。 数据源为 qianwen CLI 的 yunqi 子命令，包含订阅读写与摘要读取能力。

qianwen-ai

獲取