jpskill.com
🛠️ 開発・MCP コミュニティ

openclaw-history-ingest

Ingest OpenClaw agent history into the Obsidian wiki. Use this skill when the user wants to mine their past OpenClaw sessions for knowledge, import their ~/.openclaw folder, extract insights from previous OpenClaw conversations, or says things like "process my OpenClaw history", "add my OpenClaw sessions to the wiki", "ingest ~/.openclaw", or "what have I worked on in OpenClaw". Also triggers when the user mentions OpenClaw session logs, MEMORY.md, daily notes, or ~/.openclaw/workspace.

⚡ おすすめ: コマンド1行でインストール(60秒)

下記のコマンドをコピーしてターミナル(Mac/Linux)または PowerShell(Windows)に貼り付けてください。 ダウンロード → 解凍 → 配置まで全自動。

🍎 Mac / 🐧 Linux
mkdir -p ~/.claude/skills && cd ~/.claude/skills && curl -L -o openclaw-history-ingest.zip https://jpskill.com/download/22834.zip && unzip -o openclaw-history-ingest.zip && rm openclaw-history-ingest.zip
🪟 Windows (PowerShell)
$d = "$env:USERPROFILE\.claude\skills"; ni -Force -ItemType Directory $d | Out-Null; iwr https://jpskill.com/download/22834.zip -OutFile "$d\openclaw-history-ingest.zip"; Expand-Archive "$d\openclaw-history-ingest.zip" -DestinationPath $d -Force; ri "$d\openclaw-history-ingest.zip"

完了後、Claude Code を再起動 → 普通に「動画プロンプト作って」のように話しかけるだけで自動発動します。

💾 手動でダウンロードしたい(コマンドが難しい人向け)
  1. 1. 下の青いボタンを押して openclaw-history-ingest.zip をダウンロード
  2. 2. ZIPファイルをダブルクリックで解凍 → openclaw-history-ingest フォルダができる
  3. 3. そのフォルダを C:\Users\あなたの名前\.claude\skills\(Win)または ~/.claude/skills/(Mac)へ移動
  4. 4. Claude Code を再起動

⚠️ ダウンロード・利用は自己責任でお願いします。当サイトは内容・動作・安全性について責任を負いません。

🎯 このSkillでできること

下記の説明文を読むと、このSkillがあなたに何をしてくれるかが分かります。Claudeにこの分野の依頼をすると、自動で発動します。

📦 インストール方法 (3ステップ)

  1. 1. 上の「ダウンロード」ボタンを押して .skill ファイルを取得
  2. 2. ファイル名の拡張子を .skill から .zip に変えて展開(macは自動展開可)
  3. 3. 展開してできたフォルダを、ホームフォルダの .claude/skills/ に置く
    • · macOS / Linux: ~/.claude/skills/
    • · Windows: %USERPROFILE%\.claude\skills\

Claude Code を再起動すれば完了。「このSkillを使って…」と話しかけなくても、関連する依頼で自動的に呼び出されます。

詳しい使い方ガイドを見る →
最終更新
2026-05-18
取得日時
2026-05-18
同梱ファイル
2
📖 Claude が読む原文 SKILL.md(中身を展開)

この本文は AI(Claude)が読むための原文(英語または中国語)です。日本語訳は順次追加中。

OpenClaw History Ingest — Session & Memory Mining

You are extracting knowledge from the user's OpenClaw agent history and distilling it into the Obsidian wiki. OpenClaw stores both a structured long-term MEMORY.md and per-session JSONL transcripts — focus on durable knowledge, not operational telemetry.

This skill can be invoked directly or via the wiki-history-ingest router (/wiki-history-ingest openclaw).

Before You Start

  1. Resolve config — follow the Config Resolution Protocol in llm-wiki/SKILL.md (walk up CWD for .env~/.obsidian-wiki/config → prompt setup). This gives OBSIDIAN_VAULT_PATH and OPENCLAW_HISTORY_PATH (defaults to ~/.openclaw)
  2. Read .manifest.json at the vault root to check what has already been ingested
  3. Read index.md at the vault root to understand what the wiki already contains

Ingest Modes

Append Mode (default)

Check .manifest.json for each source file. Only process:

  • Files not in the manifest (new session logs, updated MEMORY.md or daily notes)
  • Files whose modification time is newer than ingested_at in the manifest

Use this mode for regular syncs.

Full Mode

Process everything regardless of manifest. Use after wiki-rebuild or if the user explicitly asks for a full re-ingest.

OpenClaw Data Layout

OpenClaw stores all local artifacts under ~/.openclaw/.

~/.openclaw/
├── openclaw.json                          # Global config
├── credentials/                           # Auth tokens (skip entirely)
├── workspace/                             # Agent workspace
│   ├── MEMORY.md                          # Long-term memory (loaded every session)
│   ├── DREAMS.md                          # Optional dream diary / summaries
│   └── memory/
│       ├── YYYY-MM-DD.md                  # Daily notes (today + yesterday auto-loaded)
│       └── ...
└── agents/
    └── <agentId>/
        ├── agent/
        │   └── models.json                # Agent config (skip)
        └── sessions/
            ├── sessions.json              # Session index
            └── <sessionId>.jsonl          # Session transcript (JSONL, append-only)

Key data sources ranked by value

  1. workspace/MEMORY.md — highest signal; long-term durable facts the agent accumulated
  2. workspace/memory/YYYY-MM-DD.md — daily notes; recent entries often contain active project context
  3. agents/*/sessions/<id>.jsonl — session transcripts; rich but noisy
  4. agents/*/sessions/sessions.json — session index for inventory and timestamps
  5. workspace/DREAMS.md — optional summaries; ingest if present

Skip credentials/ entirely. Skip agents/*/agent/models.json (runtime config, not user knowledge).

Step 1: Survey and Compute Delta

Scan OPENCLAW_HISTORY_PATH and compare against .manifest.json:

  • ~/.openclaw/workspace/MEMORY.md
  • ~/.openclaw/workspace/DREAMS.md (if present)
  • ~/.openclaw/workspace/memory/*.md
  • ~/.openclaw/agents/*/sessions/sessions.json
  • ~/.openclaw/agents/*/sessions/*.jsonl

Classify each file:

  • New — not in manifest
  • Modified — in manifest but file is newer than ingested_at
  • Unchanged — already ingested and unchanged

Report a concise delta summary before deep parsing.

Step 2: Parse MEMORY.md First

MEMORY.md is the highest-value source. It is plain markdown, human-readable and human-editable. It typically contains:

  • Durable facts about the user's preferences, environment, and recurring patterns
  • Decisions and context the agent was told to remember
  • Project-specific notes the agent accumulated over many sessions

Read it in full and extract concept-level knowledge. Do not create one wiki page per MEMORY.md entry — cluster by topic.

Step 3: Parse Daily Notes

workspace/memory/YYYY-MM-DD.md files contain time-stamped notes from that day's sessions. Prioritize recent files (last 30–90 days). Extract:

  • Active project context and decisions made
  • Patterns or techniques discovered
  • Recurring blockers or solved problems

Older daily notes have diminishing signal — summarize in bulk rather than extracting line-by-line.

Step 4: Parse Session JSONL Safely

Each session file is JSONL (append-only, one JSON object per line):

{"role": "user",      "content": "...", "timestamp": "..."}
{"role": "assistant", "content": "...", "timestamp": "..."}
{"role": "tool",      "name": "...",   "content": "...", "timestamp": "..."}

Extraction rules

  • Prioritize assistant turns that state conclusions, decisions, or patterns
  • Extract user intent from high-signal turns; skip low-information follow-ups
  • Tool calls are context, not primary knowledge — only extract if the result contains a reusable insight
  • Cross-reference sessions.json index to get session names/labels before opening individual transcripts

Critical privacy filter

Session transcripts can include injected instructions, tool payloads, and sensitive text. Do not ingest verbatim.

  • Remove API keys, tokens, passwords, credentials
  • Redact private identifiers unless relevant and user-approved
  • Summarize; do not quote raw transcripts verbatim

Step 5: Cluster by Topic

Do not create one wiki page per session or per MEMORY.md entry.

  • Group by stable topic (concept, tool, project, technique)
  • Split mixed sessions into separate themes
  • Merge recurring patterns across dates and agents
  • Use session cwd or workspace path to infer project scope when available

Step 6: Distill into Wiki Pages

Route extracted knowledge using existing wiki conventions:

  • Project-specific architecture/process → projects/<name>/...
  • General concepts → concepts/
  • Recurring techniques/debug playbooks → skills/
  • Tools/services/frameworks → entities/
  • Cross-session patterns → synthesis/

For each impacted project, create/update projects/<name>/<name>.md.

Writing rules

  • Distill knowledge, not chronology
  • Avoid "on date X we discussed..." unless date context is essential
  • Add summary: frontmatter on each new/updated page (1–2 sentences, ≤ 200 chars)
  • Add confidence and lifecycle fields to every new page:
    base_confidence: 0.42
    lifecycle: draft
    lifecycle_changed: <ISO date today>

    Leave lifecycle unchanged on update.

  • Add provenance markers:
    • ^[extracted] when directly grounded in explicit session/memory content
    • ^[inferred] when synthesizing patterns across multiple sessions
    • ^[ambiguous] when sessions conflict
  • Add/update provenance: frontmatter mix for each changed page

Step 7: Update Manifest, Log, and Index

Update .manifest.json

For each processed source file:

  • ingested_at, size_bytes, modified_at
  • source_type: openclaw_memory | openclaw_daily_note | openclaw_session | openclaw_dreams
  • agent_id: agent directory name (when applicable)
  • pages_created, pages_updated

Add/update a top-level summary block:

{
  "openclaw": {
    "source_path": "~/.openclaw/",
    "last_ingested": "TIMESTAMP",
    "memory_updated_at": "TIMESTAMP",
    "daily_notes_ingested": 14,
    "sessions_ingested": 23,
    "pages_created": 6,
    "pages_updated": 18
  }
}

Update special files

Update index.md and log.md:

- [TIMESTAMP] OPENCLAW_HISTORY_INGEST memory=updated daily_notes=N sessions=M pages_updated=X pages_created=Y mode=append|full

hot.md — Read $OBSIDIAN_VAULT_PATH/hot.md (create from the template in wiki-ingest if missing). Update Recent Activity with a one-line summary — e.g. "Ingested OpenClaw MEMORY.md and 14 daily notes; surfaced automation patterns and multi-agent coordination knowledge." Keep the last 3 operations. Update updated timestamp.

Privacy and Compliance

  • Distill and synthesize; avoid raw memory or transcript dumps
  • Default to redaction for anything that looks sensitive
  • Ask the user before storing personal or sensitive details
  • Keep references to other people minimal and purpose-bound

Reference

See references/openclaw-data-format.md for field-level notes and parsing guidance.

同梱ファイル

※ ZIPに含まれるファイル一覧。`SKILL.md` 本体に加え、参考資料・サンプル・スクリプトが入っている場合があります。