每天记住所有提示

SKILL开发规范

原名 remember-all-prompts-daily

开发规范 联网访问 许可证明确 OpenClaw
安装这个技能

用于辅助提示词、系统指令、Agent 行为约束和工作流模板的整理。它适合让 Agent 规范任务边界、统一输出格式、拆分操作步骤或优化提示词可复用性。使用时需要保留真实业务约束,不要把示例当硬规则;涉及自动执行、外部工具或高风险操作时,应在提示词中明确确认步骤、权限边界和失败处理方式。

累计安装 74,150 本周 3,029
GitHub 星标 3 仓库 remember-all-prompts-daily
下载量 23,747 技能市场下载数
权限级别 联网访问 安装前请确认风险范围
许可证 许可证明确 MIT-0

安装

ClawHub 市场
在支持 Skills 的客户端里执行,装完问一句「你有哪些技能」验证
openclaw skills install remember-all-prompts-daily

技能档案

开发规范
字段来自技能仓库与公开索引,中文说明由本站标注
作者 / 维护方syedateebulislam仓库 remember-all-prompts-daily · 版本 1.0.1
宿主客户端OpenClaw技能可被这些客户端加载
安装方式ClawHub 市场安装包 syedateebulislam/remember-all-prompts-daily
权限级别联网访问安装前请确认风险范围
许可证MIT-0许可证明确,商用前请自行确认条款
仓库可用性available技能仓库当前是否可访问
最近核验2026-05-01上游最后核验时间 · 数据更新 未标注
正文体量3.5 KBSKILL.md 原文大小,越大说明说明书写得越细

能做什么

5 项能力
上游给出的能力概览与适用场景
  • 按任务关键词查找相关 Skills
  • 展示可复制的安装命令
  • 保留来源站点、仓库和原始说明,方便继续核验
  • 补充不同宿主或平台的使用分布数据
  • 展示第三方安全扫描或审计结果
OpenClaw 用户查找和安装 Skill 时用户想查找某类 Agent Skill 时需要根据任务场景推荐可安装能力包时需要对比不同来源的安装命令和来源信息时

权限与风险

联网访问
装之前先读完这段

安装与使用指南

安装步骤

本站只展示命令,不托管安装包,也不自动执行。

怎么用

安装后应在对应宿主中按原始 README 的触发条件使用;当前草稿只做目录说明,具体调用方式由规则抽取,异常条目再复核。

SKILL.md 全文

3.5 KB
模型实际读到的说明书原文,来自技能仓库

Remember All Prompts Daily

This skill maintains conversation continuity across token budget cycles by automatically archiving your session history before compaction and restoring it when a new session begins.

How It Works

1. Extraction Trigger (95% Token Usage)

When token usage approaches 95%:
- Run export_prompts.py to extract current session history
- Format all prompts/responses with timestamps
- Append to memory/remember-all-prompts-daily.md with date-wise entry
- Marks the archive point so compaction can proceed

2. Fresh Session Trigger (1% Token Usage)

When a new session starts (fresh 1% token usage):
- Check if memory/remember-all-prompts-daily.md exists
- Read the most recent entry
- Ingest it as "past conversation summary" to restore context
- Continues naturally from where the previous session ended

3. Daily File Structure

# Remember All Prompts Daily

## [DATE: 2026-01-26]

### Session 1 (09:00 - 09:47)
[All prompts and responses from session]

### Session 2 (10:15 - 11:30)
[All prompts and responses from session]

Scripts

scripts/export_prompts.py

Extracts all prompts/responses from current session and archives them.

Usage:

python scripts/export_prompts.py

What it does:
- Uses sessions_history() to fetch all messages from current session
- Formats with timestamps and message IDs
- Appends to memory/remember-all-prompts-daily.md
- Includes metadata (token count, duration, etc.)

scripts/ingest_prompts.py

Reads the daily archive and injects it as context on session start.

Usage:

python scripts/ingest_prompts.py

What it does:
- Reads memory/remember-all-prompts-daily.md (if exists)
- Extracts most recent session
- Returns formatted summary for ingestion into new session

Integration

Heartbeat Check

Add to HEARTBEAT.md to monitor token usage:

Check token usage - if >95%, export session history

Cron Job (Optional)

For automatic triggers:

# Check token at regular intervals
clawdbot cron add --text "Check token usage and export if needed" --schedule "*/15 * * * *"

Example Flow

Session 1:
1. Chat normally
2. Token reaches 95%
3. export_prompts.py runs automatically
4. All prompts archived to daily file
5. Session compacts

Session 2 (New Sprint):
1. Fresh 1% token budget
2. ingest_prompts.py reads archive
3. "Here's what we discussed yesterday..."
4. Context restored, conversation continues seamlessly

Manual Usage

Export Right Now

python skills/remember-all-prompts-daily/scripts/export_prompts.py

View Today's Archive

cat memory/remember-all-prompts-daily.md | tail -100

Ingest Previous Session

python skills/remember-all-prompts-daily/scripts/ingest_prompts.py

Token Monitoring

Monitor token usage via:

session_status  # Shows current token usage %

When you see token usage approaching 95%, the skill can auto-trigger, or you can manually export.

Notes

  • Runs only in main session (direct chat with Ateeb)
  • Respects privacy — only stores your actual prompts and responses
  • Daily file auto-rotates at midnight (one entry per date)
  • Can be manually triggered anytime

安全信息

审计结论
未标注不代表已通过审计
安全审计VirusTotal、ClawScan、Static analysis第三方安全审计平台给出的结论

热门专题

按场景挑技能
全部专题 →

技能内容以作者仓库为准;分类、权限级别与许可证状态的中文说明为中文整理,最近核验 2026-05-01。