メニュー
Exports the current AI chat session to a Markdown file. Use this skill when the user wants to export, save, sync, or backup their conversation/chat/session content. Supports both raw export and optional summarization.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/crossoverJie/skills --skill session-exportコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Multi-platform, multi-channel notification skill for AI code agents. Sends notifications (sound, macOS alert, Telegram, Email, Slack, Discord, DingTalk) when the agent needs user interaction or completes a task. Supports Claude Code, GitHub Copilot CLI, Cursor, Codex, Aider, and OpenCode.
Agent-driven wiki generation workflow for gRPC + Java projects with consistent styling. ⚠️ This skill is optimized for gRPC + Java architecture. It delivers the best results when the project uses gRPC for service communication and Java as the implementation language. For other architectures (REST, GraphQL, non-Java languages), the output quality may vary. Use this skill whenever the user wants to: - Create a documentation wiki for a Java project - Generate API documentation from gRPC proto files - Set up a project wiki with consistent styling - Create interface documentation for microservices This skill is specifically designed for projects using: - gRPC for service communication - Java as the implementation language - Proto files for API definitions Do not use for: - Non-gRPC projects (REST/GraphQL) - Non-Java projects (Node.js, Python, Go) - Documentation without code generation needs
StarRocks upgrade comparison tool. Compares two local branches of a StarRocks repository via commit log diff. Per-commit diff analysis with risk tier classification (HIGH/MEDIUM/LOW/SKIP) for comprehensive impact assessment beyond scanner coverage. 11 compatibility scanners cover config changes, session/system variables, BE config, protocol changes, parser changes, auth changes, storage format changes, charset/collation, type system changes, and materialized view compatibility. Unified impact model assesses data, behavior, operational, and rolling-upgrade impacts. Four-phase parallel analysis with subagent-driven deep investigation for all HIGH/CRITICAL findings. Requires local StarRocks source code.
SKILL.md を表示中
SOC 職業分類に基づく
| name | session-export |
| description | Exports the current AI chat session to a Markdown file. Use this skill when the user wants to export, save, sync, or backup their conversation/chat/session content. Supports both raw export and optional summarization. |
| license | Apache-2.0 |
| metadata | {"author":"crossoverJie","version":"1.0"} |
Exports AI chat session conversations to readable Markdown files. Supports two modes for cross-agent compatibility.
When running inside Claude Code, the script reads the full JSONL session logs for complete, accurate export (including messages that may have been compressed from context).
python3 skills/session-export/session_export.py --output-dir <directory> [options]
--output-dir: Directory to save the exported markdown (env: SESSION_EXPORT_OUTPUT_DIR, default: current directory)--cwd: Project working directory to locate session logs (default: current directory)--session-id: Export a specific session ID (default: most recent)--name: Custom filename for the exported markdown (without .md extension). AI should summarize the session topic as the name--summarize: Request a summary to be generated after export--no-subagents: Exclude subagent conversations--max-tool-output: Max characters per tool output in export (default: 5000)Export current session:
python3 skills/session-export/session_export.py --output-dir /tmp/sessions
Export a specific session:
python3 skills/session-export/session_export.py --session-id abc12345-... --output-dir ~/exports
Export without subagent conversations:
python3 skills/session-export/session_export.py --output-dir ./exports --no-subagents
Export with summary:
python3 skills/session-export/session_export.py --output-dir ./exports --summarize
When the script exits with code 2 (Claude Code logs not found), the AI should fall back to writing the conversation directly from its current context:
session_id, project, exported_at, message_count, export_mode: ai-context## User / ## Assistant with timestamps if availablesession-fallback-<YYYY-MM-DD-HHMMSS>.mdWhen --summarize is passed:
*-summary.md alongside the originalThe summary should include:
Success (exit code 0):
Exported to: /tmp/sessions/session-1e2b749d-2026-02-06-210100.md
Session: 1e2b749d-f2c1-4a91-b248-6331e48abd6a
Messages: 42
Subagents: 3
Fallback needed (exit code 2):
Claude Code log directory not found (~/.claude/projects/).
FALLBACK_MODE: AI should write conversation from context directly.