Session Recovery logo

Session Recovery

Community
wasintoh
session-recovery

Seamless continuation across sessions and IDEs — on session start, read .toh/memory/ and greet the user with where the last session left off so nothing needs re-explaining. Handles first run (no memory yet), mid-task resume, and returns after days or weeks. Use at the start of every new session or when the user says continue / "ทำต่อ".

Overview

Publisherwasintoh
Repositorytoh-framework
Skill namesession-recovery
Stars
96
Forks
19
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by wasintoh on GitHub. Read the source before you install it.

Installation

Install the Session Recovery AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/wasintoh/toh-framework.git /tmp/toh-framework
mkdir -p .claude/skills
cp -r /tmp/toh-framework/src/skills/session-recovery .claude/skills/session-recovery
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Session Recovery in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Session Recovery on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Session Recovery is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

🔄 Session Recovery Skill

Purpose: Seamless continuation across sessions and IDEs Version: 1.0.0 Author: Toh Framework Team

Overview

This skill enables AI to remember context across sessions and IDEs, so users can continue where they left off without re-explaining everything.

Core Principle

User opens new session (even after days/weeks)
AI reads memory files
AI greets with context: "สวัสดีครับ! ครั้งก่อนเราทำ X ค้างไว้..."
User can continue immediately

ZERO RE-EXPLANATION NEEDED


Session Start Behavior

First Time (No Memory)

When .toh/memory/ is empty or doesn't exist:

markdown
สวัสดีครับ! 👋 ผมเป็น Toh Framework Agent

พร้อมช่วยสร้างระบบให้ครับ บอกได้เลยว่าอยากสร้างอะไร

💡 ตัวอย่าง:
- "สร้างระบบร้านกาแฟ"
- "สร้างเว็บขายของออนไลน์"
- "สร้างระบบจองคิว"

หรือพิมพ์ `/toh-help` เพื่อดูคำสั่งทั้งหมดครับ

Returning User (Has Memory)

When .toh/memory/ has data:

markdown
สวัสดีครับพี่โต! 👋 ยินดีต้อนรับกลับมา

📋 **สรุปโปรเจค:** [project name]
[Brief summary from summary.md]

🔥 **ครั้งก่อนทำค้างไว้:**
- [Last active task from active.md]

📊 **สถานะปัจจุบัน:**
- ✅ [Completed items]
- ⏳ [In progress]
- ⬚ [Not started]

💡 **แนะนำ:** [Next logical step]

ทำต่อเลยไหมครับ? หรือต้องการทำอะไรอื่น?

Memory Reading Protocol

On Session Start

AI MUST read these files in order:

1. .toh/memory/active.md     → Current task, blockers
2. .toh/memory/summary.md    → Project overview, features
3. .toh/memory/decisions.md  → Key decisions made
4. (Optional) .toh/memory/archive/ → If user asks about history

Smart Summary Generation

AI should summarize, not dump raw content:

❌ Bad: "active.md says: Current Focus: Dashboard UI..."

✅ Good: "ครั้งก่อนกำลังทำ Dashboard UI ครับ เหลือแค่เชื่อม API"

Cross-IDE Continuity

Scenario: Claude Code → Cursor

[Claude Code session ends]

[User opens Cursor]

Cursor AI: "สวัสดีครับ! ผมเห็นว่าเมื่อกี้ทำกับ Claude Code อยู่
          กำลังทำ Dashboard ค้างไว้ที่ส่วน API connection ครับ
          
          ทำต่อเลยไหมครับ?"

Scenario: Days Gap

[User returns after 3 days]

AI: "สวัสดีครับพี่โต! 👋 ไม่เจอกัน 3 วัน
    
    📋 โปรเจคร้านกาแฟ - สถานะล่าสุด:
    - ✅ UI ทุกหน้าเสร็จแล้ว
    - ✅ Mock data พร้อม
    - ⏳ ยังไม่ได้เชื่อม Supabase
    
    ครั้งก่อนค้างไว้ที่: จะเชื่อม database
    
    ทำต่อเลยไหมครับ?"

Context Awareness

AI Should Know

InformationSource
Project name & typesummary.md
Business contextsummary.md + business-context skill
Completed featuressummary.md
Current taskactive.md
Blockers/Issuesactive.md
Key decisionsdecisions.md
Tech choicesdecisions.md

AI Should Track

MetricPurpose
Last session dateTime gap awareness
Last command usedContext for continuation
Incomplete tasksRemind user
Errors encounteredAvoid repeating

Memory Update Protocol

After Every Task

1. Update active.md
   - Move completed items
   - Add new next steps
   - Update current focus

2. Update summary.md (if feature completed)
   - Add to completed features
   - Update project structure

3. Update decisions.md (if decision made)
   - Log architectural decisions
   - Log design decisions

Session End (If Detectable)

markdown
## In active.md

### Session Log
- Session ended: [timestamp]
- Last action: [action]
- Pending: [what was in progress]

Quick Continuation Commands

User can say:

CommandAI Does
"ทำต่อ" / "continue"Continue last task
"ทำต่อจากที่ค้างไว้"Same as above
"ทำอะไรค้างไว้"Show pending tasks
"สรุปให้หน่อย"Summarize project state
"เริ่มใหม่"Start fresh (confirm first)

Response Templates

Session Start (With Context)

markdown
สวัสดีครับพี่โต! 👋

📋 **[Project Name]** - [Business Type]

**สถานะ:**
[Progress bar or checklist]

**ครั้งก่อน:** [Last action]

**ถัดไป:** [Suggested next step]

ทำต่อเลยไหมครับ?

Quick Status Check

markdown
📊 **สถานะโปรเจค**

| Phase | Status |
|-------|--------|
| UI | ✅ เสร็จ |
| Logic | ⏳ 70% |
| Database | ⬚ ยังไม่เริ่ม |
| Testing | ⬚ ยังไม่เริ่ม |
| Deploy | ⬚ ยังไม่เริ่ม |

**กำลังทำ:** [Current task]
**ถัดไป:** [Next step]

Edge Cases

Empty Project (Has .toh but no code)

markdown
สวัสดีครับ! 👋

เห็นว่าโปรเจคนี้ติดตั้ง Toh Framework แล้ว
แต่ยังไม่ได้เริ่มสร้างอะไรครับ

พร้อมเริ่มเมื่อไหร่ก็บอกได้เลยครับ!

💡 ลองเริ่มด้วย: "สร้างระบบ [อธิบายสั้นๆ]"

Corrupted/Incomplete Memory

markdown
สวัสดีครับ! 👋

ผมอ่าน memory ได้บางส่วน แต่ไม่ครบถ้วนครับ

จากที่เห็น:
- โปรเจค: [what can be detected]
- ไฟล์ที่มี: [detected files]

ช่วยบอกหน่อยได้ไหมครับว่าทำถึงไหนแล้ว?
ผมจะอัพเดท memory ให้ครับ

Multiple Projects (Future)

markdown
สวัสดีครับ! 👋

พบหลายโปรเจคในเครื่อง:
1. ☕ ร้านกาแฟ (active.md อัพเดทเมื่อวาน)
2. 🛒 E-commerce (active.md อัพเดท 3 วันก่อน)

ต้องการทำโปรเจคไหนครับ?

Integration with Other Skills

SkillIntegration
Smart SuggestionsUse memory to suggest relevant next steps
Business ContextRemember business type for context
Progress TrackingRead/write progress to memory
Error HandlingRemember past errors to avoid

Best Practices

DO:

  • ✅ Greet with context immediately
  • ✅ Summarize, don't dump raw data
  • ✅ Offer to continue where left off
  • ✅ Keep memory updated after every task

DON'T:

  • ❌ Ask "what are we working on?" when memory exists
  • ❌ Ignore memory files
  • ❌ Show raw memory content
  • ❌ Forget to update memory after tasks

Last Updated: 2024-12-03

Frequently asked questions

What does the Session Recovery AI skill do?

Seamless continuation across sessions and IDEs — on session start, read .toh/memory/ and greet the user with where the last session left off so nothing needs re-explaining. Handles first run (no memory yet), mid-task resume, and returns after days or weeks. Use at the start of every new session or when the user says continue / "ทำต่อ".

Why use Session Recovery on TypingMind?

Because you install it once and use it with any model. Session Recovery is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Session Recovery in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wasintoh/toh-framework/tree/main/src/skills/session-recovery. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Session Recovery?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Session Recovery?

As many as you like. As long as a model supports skills, you can use Session Recovery with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Session Recovery AI skill free?

Yes. It is published on GitHub by wasintoh under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇