メニュー
Extract and save browser screenshots from session transcripts
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | chrome-screenshot |
| description | Extract and save browser screenshots from session transcripts |
| allowed-tools | Bash, Read |
Extract browser screenshots from Claude Code transcripts by their ss_* ID.
Screenshot IDs are returned when you take screenshots with claude-in-chrome tools. These images are stored in the session transcript and can be retrieved later.
chrome-screenshot # List all screenshot IDs
chrome-screenshot ss_abc123 # Extract to stdout
chrome-screenshot ss_abc123 file.jpg # Save to file
chrome-screenshot ss_abc123 file.jpg <session> # From specific session
# Save screenshot to file
chrome-screenshot ss_3669oma6t .ai-reference/screenshots/homepage.jpg
# Then Read it to view
Read .ai-reference/screenshots/homepage.jpg
Save multiple screenshots, then Read them together:
chrome-screenshot ss_abc123 .ai-reference/screenshots/before.jpg
chrome-screenshot ss_def456 .ai-reference/screenshots/after.jpg
Read .ai-reference/screenshots/before.jpg
Read .ai-reference/screenshots/after.jpg
Claude sees both images for visual comparison.
Wrapper around codex CLI for non-interactive runs (prompt via args/file/stdin) with resume support. Outputs session_id for conversation continuation.
Multi-agent debate orchestrator. Use when you want multiple AI perspectives on a question, plan review, or architectural decision. Runs parallel agent panels with a Chair synthesizing responses.
Wrapper around gemini CLI for non-interactive runs (prompt via args/file/stdin) with resume support. Outputs session_id for conversation continuation.
SDK-based Claude agent with full Task tool access. Use for executing handoff prompts or spawning nested sub-agents.
This skill should be used when the user asks to "implement this plan", "generate execution prompts", "super implement", "create handoff from plan", or wants to transform a large plan into self-contained execution-ready prompt artifacts.
ALWAYS use this skill instead of Read when reading Claude Code transcript files (.jsonl in ~/.claude/projects/, ~/.claude/history.jsonl, or paths containing 'transcript'). Token-efficient format that extracts USER/ASSISTANT exchanges and tool summaries, strips metadata.