doing-a-simple-two-sta…
Use when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orchestrates parallel…
Use when the user wants to export a Claude Code session transcript as a readable Markdown file — converts the current session (or a specified transcript path) into GitHub-flavored Markdown with metadata header, collapsible tool results, and thinking blocks
Claude Code
$ npx -y skills add ed3dai/ed3d-plugins --skill export-session-as-markdown --agent claude-code
Codex
$ npx skills add ed3dai/ed3d-plugins --skill export-session-as-markdown -a codex -y
Cursor
$ npx skills add ed3dai/ed3d-plugins --skill export-session-as-markdown -a cursor -y
Gemini CLI
$ npx skills add ed3dai/ed3d-plugins --skill export-session-as-markdown -a gemini-cli -y
GitHub Copilot
$ npx skills add ed3dai/ed3d-plugins --skill export-session-as-markdown -a github-copilot -y
OpenCode
$ npx skills add ed3dai/ed3d-plugins --skill export-session-as-markdown -a opencode -y
Windsurf
$ npx skills add ed3dai/ed3d-plugins --skill export-session-as-markdown -a windsurf -y
name: export-session-as-markdown description: Use when the user wants to export a Claude Code session transcript as a readable Markdown file — converts the current session (or a specified transcript path) into GitHub-flavored Markdown with metadata header, collapsible tool results, and thinking blocks
Export a Claude Code session transcript to a human-readable GitHub-flavored Markdown file.
The user may invoke this as:
If an argument was provided, use it as the transcript path. Otherwise, use the current session's transcript path from the SessionStart hook injection.
If you cannot determine the transcript path, tell the user:
I don't know the current session's transcript path. Either provide a path: /export-session-as-markdown /path/to/session.jsonl Or ensure the ed3d-session-reflection SessionStart hook is active.
If a second argument was provided, use it as the output path. Otherwise, default to the current working directory with a descriptive filename:
session-transcript-YYYY-MM-DD.md
If a file with that name already exists, append a counter: `session-transcript-YYYY-MM-DD-2.md`.
Run the script with the `--markdown` flag:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/reduce-transcript.py" "<transcript_path>" "<output_path>" --markdownTell the user where the file was written and its size. Example:
Exported session transcript to ./session-transcript-2026-03-20.md (346 KB)
Ed's repo of Claude Code plugins, centered around a research-plan-implement workflow. Only a tiny bit cursed. If you're lucky.
Use when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orchestrates parallel…
Use when creating a new Claude Code plugin or setting up plugin structure - provides complete file organization, manifest format,…
Use when creating specialized subagents for Claude Code plugins or the Task tool - covers description writing for…
Use when creating, releasing, or maintaining a Claude Code Plugin Marketplace - covers marketplace.json schema, version…
Use when completing development phases or branches to identify and update CLAUDE.md or AGENTS.md files that may have become stale…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.