本文へ移動
cccskills
無料GitHub で公開

deep-recall

4-layer recall procedure (durable → semantic → PostgreSQL → daily notes) before claiming "no context". Invoke when user explicitly asks "do you remember", "what did we discuss about X", "search history". NOT a general assistant — only fires when recall is the explicit task. Drop the prior "use proactively" rule. Triggers: "do you remember", "what did we discuss", "when did", "find that conversation about".

インストール方法を見る

含まれるファイル(1)

  • SKILL.md2.4 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Deep Recall

Rule: Never say "I don't have context" without searching all sources first.

Search Order (mandatory, in sequence)

1. Memory Search (semantic)

memory_search(query="<topic>")

Searches MEMORY.md + memory/*.md + indexed session transcripts.

2. Session Search (FTS + PostgreSQL + daily notes)

python3 tools/session_search.py "<query>" --limit 10 --days 30

Full-text search across SQLite FTS5 index, WhatsApp DB, and daily notes.

3. PostgreSQL Direct (for specific conversations)

import os, psycopg2
conn = psycopg2.connect(os.environ['PA_DB_URL'])
cur = conn.cursor()
cur.execute("""
    SELECT body, ts, chat_id, is_from_me 
    FROM messages 
    WHERE body ILIKE %s 
    AND ts > NOW() - INTERVAL '30 days'
    ORDER BY ts DESC LIMIT 10
""", ('%keyword%',))

4. Daily Notes Grep (for dated events)

grep -rn "<keyword>" memory/daily/ | tail -20

5. WhatsApp DM Context Files

grep -rn "<keyword>" memory/whatsapp/dms/*/context.md

When to Trigger

  • Any question starting with "did we", "when did", "what about", "do you remember"
  • Before saying "I don't have context on this"
  • Before saying "I'll need to check"
  • When the owner references something from a past conversation
  • When another PA asks about a previous interaction

Output Rules

  • If found: cite the source (file:line or timestamp)
  • If not found after all 5 searches: say "I searched memory, WhatsApp history, and daily notes — no match found"
  • Never say "I don't remember" without running all searches
  • If partial match: share what was found and ask for clarification

Common Recall Failures to Avoid

  • Saying "let me check" and then not actually checking
  • Searching only one source and giving up
  • Assuming something wasn't discussed because it's not in MEMORY.md (check PostgreSQL!)
  • Forgetting that WhatsApp group messages exist in the DB too
  • Not checking DM context files in memory/whatsapp/dms/

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

ai-pa

無料

Route and execute inter-PA coordination tasks in the OpenClaw multi-agent PA network. Triggers when: contacting another PA, passing a message between owners, broadcasting to a PA group, handling group lead/silence rules, or adding a new PA to the directory. NOT for: contact lookups (use contact-list skill), calendar invites (use meetings skill), or billing issues (use billing-monitor skill).

日本語の概要は準備中です。原文の説明を表示しています。

netanel-abergel/pa-skills62026年5月10日 更新

ai-pa

無料

AI Personal Assistant network skill for multi-agent PA coordination. Use when: contacting another PA, coordinating with peer agents, scheduling meetings between owners, broadcasting messages to PA groups, or looking up contacts from the local PA directory. Reads contact data from data/pa-directory.json in the workspace.

日本語の概要は準備中です。原文の説明を表示しています。

netanel-abergel/pa-skills62026年5月10日 更新

ai-pa

無料

AI Personal Assistant network skill. Use when: contacting another PA, coordinating with peer agents, scheduling meetings between owners, broadcasting messages, looking up contacts from the local PA directory, or performing any cross-PA task. Reads contact data from data/pa-directory.json in the workspace. Does NOT contain hardcoded contact data — each PA maintains their own directory file.

日本語の概要は準備中です。原文の説明を表示しています。

netanel-abergel/pa-skills62026年5月10日 更新

OpenClaw API gateway proxy for authenticated SaaS calls (100+ services in references/SERVICES.md). Use ONLY when making an HTTP request to a third-party service that requires the gateway's stored credentials. NOT for direct API calls with bearer tokens already in scope, NOT for monday.com (use monday-for-agents), NOT for WhatsApp (use heleni-whatsapp). Triggers: "call the X API", "fetch from <service>", "send to Slack via gateway", "use the gateway for".

日本語の概要は準備中です。原文の説明を表示しています。

netanel-abergel/pa-skills62026年5月10日 更新

Automatically creates new skills from complex problem-solving sessions. Triggers at the end of multi-step tasks that required novel approaches, debugging sessions, or workflow creation. Use when: a task took 3+ tool calls, involved a non-obvious solution, or established a pattern likely to recur. Also triggers on: "create a skill from this", "save this as a skill", "this should be a skill".

日本語の概要は準備中です。原文の説明を表示しています。

netanel-abergel/pa-skills62026年5月10日 更新

Monitor for API billing errors and alert the owner and admin immediately. Use when: an API billing error is detected, a peer PA reports a billing error, or during routine health checks. Handles detection, notification, and fallback model switching. Model-agnostic: works with any LLM provider (Anthropic, OpenAI, Google, etc.).

日本語の概要は準備中です。原文の説明を表示しています。

netanel-abergel/pa-skills62026年5月10日 更新

netanel-abergel のスキルをすべて見る

このスキルの問題を報告する