🔌
Plugins
Loading...
Showing 30 of 27339 results
跨 AI 长期记忆:每轮自动召回你的持久记忆并注入对话,自动把对话沉淀进云端大脑,与你的 Codex / Hermes 等所有 AI 共享同一账户的记忆。
Get screenshots, GIFs, recordings, and files into GitHub PRs and issues via uploads.sh. Bundles the github-screenshots, annotate-screenshots, and uploads-cli skills, and the hosted MCP server.
UpRock: Scrape, crawl, search & sweep the web from real devices worldwide — clean, LLM-ready markdown with anti-bot, JS rendering & geo-targeting. Powered by a real global device network, not datacenter proxies. Includes an autonomous research agent.
Upstash's own skills — Redis, QStash, Workflow, Vector, Search and the CLI. Every product here uses Upstash; credentials are at /infrastructure/upstash in each Infisical project.
Remote MCP server for the Upstox Developer API — live NSE/BSE/MCX market data and read-only account/portfolio access.
Agent skill for interacting with NSE/BSE equities, F&O, and MCX commodities via the Upstox Developer API.
Automatically checks for and installs plugin updates from the urikan-ai-marketplace on session start. Opt-in: only install if you want automatic updates.
Build and refine a working app from a reference URL with built-in design direction, visual craft, interaction hardening, optimization, and UI verification
Feasibility answers and validated routing plans for the YAMAHA URX22 / URX44 / URX44V from plain-language requests.
Local web dashboard for Claude Code token usage, cost, cache hit-rate, live 5-hour block, and per-project/session breakdown.
Makes Claude Code aware of subscription usage limits. Injects live 5h/7d usage into context and pauses tool execution when usage crosses a threshold (default 98%), resuming automatically after the window resets.
Claude Code用量监控：各模型token用量与成本、5小时/7天限额窗口利用率与刷新时间、会话排行、工具调用统计、HTML可视化报告、状态栏实时显示
Claude Code 구독 사용량(5시간·주간 한도)을 매일 지정 시각에 MS Teams로 자동 알림합니다. claude.ai 클라우드 routine으로 세션·PC가 꺼져 있어도 발동하며, haiku 1토큰 호출의 rate-limit 응답 헤더에서 사용량을 읽어 예쁜 AdaptiveCard로 전송합니다.
79 cybersecurity skills + 12 cs-* orchestrator agents. Bundles 7 slash commands and 6 user-invocable orchestrator skills (Alex, CISO, DevSecOps, IR, Program Manager, Red Team). Every skill emits a typed 11-field JSON output contract mapped to MITRE ATT&CK and NIST CSF 2.0. Apache 2.0, runs in any LLM.
See and interact with the user's screen using Agent Vision — screenshots, element discovery, clicks, form filling, and visual QA
Browser automation, web testing, and page interaction driven from the command line with `playwright-cli`, defaulting to the Lightpanda headless browser. ALWAYS use this skill when the agent needs a browser — opening pages, navigating, clicking/typing/filling forms, taking snapshots or screenshots, scraping or reading page content, logging in, running or debugging Playwright tests, mocking network requests, managing cookies / localStorage / storage state, recording traces or video, or generating tests. The agent defaults to Lightpanda (installed locally and driven over CDP) without asking, and switches to Chromium, Chrome, Firefox, WebKit, or Microsoft Edge only when the user asks. Falls back to a full browser when Lightpanda cannot render a page.
Budget loop for long-running or parallel agent work under Claude's 5-hour and weekly usage limits — run bounded waves, check real usage between them, pause before the cap, and resume with self-contained prompts only when the window is actually clear.
Stop suggesting stale package versions from training data. 15 MCP tools over 39 package registries (npm, PyPI, Maven, crates.io, Go, RubyGems, NuGet, Packagist, Docker/GHCR/Quay/GCR, Hex, pub.dev, CRAN, Homebrew, and more): latest-version + package-info lookups, semver compare, install-command generation, batch checks, project dependency scanning, outdated reports, conflict detection, compatibility checks, and a scan -> optimize -> validate -> apply upgrade pipeline that edits manifests with dry-run + automatic backups by default. Local-first, no API key required (an optional GITHUB_TOKEN raises GitHub rate limits).
Run expensive top-tier models (Claude Fable/Opus, GPT-5.6 Sol, or similar) efficiently — the premium model keeps judgment, architecture, synthesis, and final review, while cheaper subagents (Sonnet, Haiku, Terra, Luna) do bounded token-heavy research, coding, and testing with self-contained handoffs and verified results.
유스케이스 주도 설계 스킬 모음. OOA(8단계 분석)와 OOD(6단계 설계)를 연결하여 분석부터 클래스 설계까지 체계적으로 수행한다.
Research an AI Agent product idea into a dossier + four research docs and a Proceed/Pivot/Narrow/Kill decision.
29 investigation workflows for people, companies, domains, images, phones, emails, usernames, crypto and vessels — scope-gated, source-graded, and built for due diligence, KYB, fraud and attack-surface work.
29 investigation workflows for people, companies, domains, images, phones, emails, usernames, crypto and vessels — scope-gated, source-graded, and built for due diligence, KYB, fraud and attack-surface work.
Diátaxis-shaped user-guide skeleton: guides/ + tutorials/how-to/reference/explanation seed READMEs, new-guide skill.
Create user stories with Mike Cohn format and Gherkin acceptance criteria.
Create a user story map with activities, steps, tasks, and release slices.
Run a user story mapping workshop with adaptive questions and structured output.