Loading...
Loading...
Found 103 Skills
General web search and content extraction skill. It supports multi-source parallel search (WebSearch, MCP search tools, ctx7, agent-browser), web page main content extraction (defuddle/WebFetch) and structured article analysis. This skill is used when users need to search for information, research topics, find materials, obtain web content, read articles, or analyze web pages. Trigger scenarios include: search, research, investigation, fetch, check for me, help me find, read this link, analyze this article. Even if the user doesn't explicitly say "search", this skill should be triggered as long as it involves information acquisition and web content processing.
Create a Linear OAuth application and configure Cyrus to use it — supports agent-browser automation or guided manual setup.
Comprehensive end-to-end validation of the Archon Web UI using browser automation and codebase review. Use when: User wants to validate, test, or audit the Archon web interface, find UI/UX bugs, test workflow management, verify parallel agent orchestration, or run comprehensive browser-based E2E tests. Triggers: "validate ui", "test the ui", "e2e test", "browser test", "validate archon", "test archon ui", "ui audit", "ux review", "comprehensive test", "validate everything". Capability: Starts Archon, runs exhaustive browser automation tests via agent-browser CLI, performs codebase review, and produces a detailed bug/UX report. NOT for: Unit tests (use `bun test`), CLI-only validation (use /validation:validate-simple).
Desktop & Tauri app testing for AI agents — Tauri v2 + WebKitGTK in Docker (AppImage extraction, Gemini Computer Use, virtual display, DOCX export verification) plus Electron app automation (VS Code, Slack, Discord, Figma) via `agent-browser skills get electron`. Use when testing a Tauri desktop app (Cicero), Electron app, or any non-browser desktop UI. For web browser testing, see `browser-test-agent`.
[BETA] Dogfood the active branch end-to-end as a QA engineer. Diffs the branch against main, builds an exhaustive browser test matrix of every change (full user journeys, not just features), drives the app with agent-browser, then auto-fixes issues, adds regression tests, and commits each fix until the matrix is green. Use when you want a hands-off 'test everything we just built and make it actually work' pass before shipping.
This skill should be used to watch a long-running background job (ffmpeg/media encode, qmd or other embedding/vector-DB run, batch agent/LLM pipeline, or a real-browser/agent-browser daemon) until it finishes or wedges, then deliver a verdict (done, needs-attention, or blocked) plus the exact next command, without burning dozens of manual poll commands. Triggers on "babysit this job", "watch this until it's done", "ping me when the encode/embed/batch finishes", "is this background process stuck", "monitor this ffmpeg/qmd run", or any request to wait on a long-running process and be told when it's complete or hung.
Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots. Capabilities: web scraping, form filling, clicking, typing, 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
Generate and verify web scraper scripts using Actionbook's verified selectors. Auto-validates generated scripts and fixes errors.
Run browser tests on pages affected by current PR or branch
Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermaid diagram.
This skill should be used when the user asks to "create a Feishu doc", "create a new doc in Feishu", "open Feishu and create document", "create document in leiniao-ibg", or mentions creating documents in Feishu/Lark workspace.
Take focused, region-specific screenshots from web pages. Navigates to the right page based on user context (URL, search query, social media post), locates the target region via DOM selectors, and crops to a clean, focused screenshot.