Skip to content

n0an/VivaDicta / .agents/skills/screenshot

screenshot

Verified

Capture screenshots from iOS Simulator using native xcrun simctl command for documentation, debugging, and visual verification. Optionally analyze the screenshot.

screenshot

You are given the following context: $ARGUMENTS

Task

Capture a screenshot of the iOS Simulator using xcrun simctl and optionally analyze it based on user instructions.

Instructions

  1. Create screenshots directory if needed:

    mkdir -p llmtemp/screenshots
    
  2. Capture the screenshot:

    TIMESTAMP=$(date +%Y%m%d_%H%M%S)
    xcrun simctl io booted screenshot llmtemp/screenshots/screenshot_${TIMESTAMP}.png
    
  3. Handle the optional argument:

    • If $ARGUMENTS is empty or not provided: Capture and save, then report the saved path
    • If $ARGUMENTS is provided: After saving, read the screenshot and follow the requested instruction

    Common argument patterns:

    • "take a look" / "analyze" / "what's on screen" - Read and describe what's visible
    • "check for [element]" - Look for specific UI elements
    • "is there [something]" - Verify presence of specific content
    • "extract text" - Extract and list all visible text
    • Any other instruction - Follow it after reading the screenshot
  4. Report results: Always mention the saved screenshot path. If analyzed, provide findings.

Example Usage

screenshot                              # Simple capture
screenshot take a look                  # Capture and analyze
screenshot is there a login button?     # Check for specific element
screenshot extract all visible text     # Extract text

Advanced Options

For advanced use cases, load references/advanced.md.

  • Specific simulator: Use UDID instead of booted when multiple simulators are running
  • Image format: --type=png (default), --type=tiff
  • Specific display: --display=1 (main), --display=2 (secondary, e.g. Apple Watch)
  • Mask sensitive data: --mask=black (iOS 15+)

Troubleshooting

  • "No such device: booted": No simulator running. Check with xcrun simctl list devices | grep Booted
  • Blank/black screenshot: Wait for content to load, ensure simulator is not minimized
  • Wrong simulator captured: Use specific UDID instead of booted

Technical Notes

  • Screenshots saved to llmtemp/screenshots (gitignored)
  • Filenames include timestamps to prevent overwrites
  • Native xcrun simctl command - no external dependencies, only Xcode
  • Captures clean framebuffer without simulator bezel
  • PNG format (lossless)
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 197kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 197kUpdated Claude CodeCodexVerifiedInstall