发现 Skills

browser-cloud — agent skill for TestMu AI Browser Cloud. Generates production-ready TypeScript code to spin up cloud browser sessions, connect via Puppeteer/Playwright/Selenium, and run agent workflows — with stealth, auth persistence, file transfer, tunnel access, and full observability baked in. Trigger on: "use browser cloud", "browser agent", "scrape with cloud browser", "automate browser for agent", "cloud puppeteer", "cloud playwright", "headless cloud", "spin up browser session", "TestMu browser", "browser cloud session", "web scraping agent", "fill form with agent", "screenshot from cloud", "PDF from cloud", "browser automation agent", "agent browser task", or any request to connect an AI agent to the web via a real browser. Agent-agnostic: works with LangChain, CrewAI, AutoGen, raw LLM tool calls, and custom agent loops.

Lansenger callback event parsing — 24 event types across 13 categories, structured dataclass parsing, payload parsing, signature verification

Review weekly notes, tasks, and meetings to surface items at risk of being dropped. Use when user requests a weekly review, uses /weekly-review, or asks to review a specific week. Invocation: /weekly-review [date|week-number] Examples: /weekly-review, /weekly-review 2025-03-12, /weekly-review 2025-W12

One sentence describing what this skill does and when an agent should use it. Include trigger keywords and scenarios (1–1024 characters).

Battle-tested pipeline patterns — QA gates, command phases, conflict resolution, CI checks, stale PR handling

Generate a complete, working integration for the LaunchPath API channel — Slack bot, voice agent, custom chat UI, email autoresponder, or any other platform. Creates the channel and outputs ready-to-use code.

Create, test, and package Helm charts for Kubernetes. Covers helm create, Chart.yaml, values.yaml, template development, chart dependencies, packaging, and repository publishing. Use when user mentions Helm charts, helm create, Chart.yaml, values.yaml, helm lint, helm template, helm package, or Kubernetes packaging.

Use this skill when a user needs to review a contract in Chinese, revise clauses, add annotations/comments, compare against a template, identify risks, and ultimately produce a docx file that directly contains line-by-line comments and tracked changes. Typical triggers include: contract review, contract modification, template-driven optimization, output revised version, output commented version, output revised-and-commented version, check defined terms, check clause logic, check formatting, output clean version. **Important: The default deliverable must be a directly openable docx with line-by-line comments and tracked changes — do not first output md or txt to the user for interim confirmation; whenever revisions and comments are involved, always write by directly manipulating the DOCX underlying XML and do not switch to other implementation paths, to ensure WPS compatibility.**

Pre-coding design sketch with the rubber duck — runs BEFORE the user asks AI to implement. Use when the user states implementation intent ("구현해줘", "build me X", "let's add Y") and no plan, diff, or code exists yet, or when they explicitly say "duck design" / "sketch first" / "design check". The duck forces a 30-second self-sketch so the user has their own mental model before the AI generates code, then probes the weakest spot. Do NOT use after code is already written — use /duck-verify or /duck-review instead.

File-based routing with page patterns for lists, details, and navigation. Use when creating pages, defining page meta (permissions, layouts), implementing list/detail patterns, or setting up breadcrumbs and headers.

Turn student-style resumes, cover letters, interview answers, LinkedIn summaries, and career stories into employer-facing evidence of role fit. Use this skill whenever the user asks for resume edits, job application positioning, interview self-introductions, internship or new-grad applications, project bullet rewrites, career-switch narratives, one-page resume pruning, or help translating academic/project experience into business, research, data, product, quant, AI, or technical hiring language.

Finalize a ticket (requires SHIP review + logging).

Skill imported from leionion/ClawForge-beta

Skill imported from leionion/ClawForge-beta

Skill imported from leionion/ClawForge-beta

You are a Senior QA Engineer and ISTQB-certified Testing Specialist with deep expertise in software testing principles and quality assurance.

Guides and best practices for working with Neon Serverless Postgres. Covers getting started, local development with Neon, choosing a connection method, Neon features, authentication (@neondatabase/auth), PostgREST-style data API (@neondatabase/neon-js), Neon CLI, and Neon's Platform API/SDKs. Use for any Neon-related questions.

Route and execute Omniskill vault work from CLI: create skills, edit skills, search/import/delete/sync, and propose linking or curation actions. Trigger on "create a skill", "edit/update a skill", "omniskill", "omniscent", "omni skill", "skill vault", "import this skill", "link this skill", and similar requests.

Comprehensive OpenTUI skill for building terminal user interfaces. Covers the core imperative API, React reconciler, and Solid reconciler. Use for any TUI development task including components, layout, keyboard handling, animations, and testing.

Performance optimization guidelines for React and Next.js from Vercel Engineering. Use this skill when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or other performance improvements.

Find other agents on the same server. Use when the user asks about other agents, wants to migrate memory from another agent, or needs to find an agent by name or tags.

Produce a clean summary of a meeting (decisions, action items, attendees, open questions) and append it to today's daily log. Source can be Granola via Composio, another connected note-taking toolkit, or content the user pastes directly. Invoke when user says "summarize my last meeting", "what happened in my last meeting", "summarize the X meeting", or when notes are pasted.

A dynamic UI design-system generator that creates 10 unique, diverse design directions every time it runs. It produces both detailed specifications and an interactive HTML preview so users can visually explore all options. Each direction includes complete specifications—typography scales, color palettes, spacing systems, component libraries, motion principles—so designs are exportable and actionable. It automatically triggers before any new UI or frontend work to ensure intentional, cohesive aesthetics, and it never returns the same set of 10 designs twice—always generating fresh options based on varied inspirations, aesthetics, and use cases.

Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, and writes a concise Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Do not trigger for general architecture summaries, code review, or non-security design work.