Error Handling logo

Error Handling

Community
wasintoh
error-handling

Intelligent error handling — silently auto-fix routine errors (missing imports, undefined variables, type mismatches, missing dependencies, syntax and lint issues) and translate everything else into friendly, non-technical language with clear next steps. The user never sees raw error messages or stack traces. Use whenever an error, warning, or failure surfaces while working.

Overview

Publisherwasintoh
Repositorytoh-framework
Skill nameerror-handling
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 Error Handling 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/error-handling .claude/skills/error-handling
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Error Handling 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 Error Handling 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 Error Handling 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.

🔧 Error Handling Skill

Purpose: Auto-fix errors silently, translate when necessary Version: 1.0.0 Author: Toh Framework Team

Overview

This skill enables AI to handle errors intelligently - fixing them silently when possible, and translating them to human-friendly language when user needs to know.

Core Principle

Error occurs
Can AI fix it automatically?
    ├── YES → Fix silently, continue working
    └── NO → Translate to friendly language, explain what user needs to do

USER SHOULD NEVER SEE RAW ERROR MESSAGES


Error Handling Strategy

Level 1: Silent Auto-Fix (User sees nothing)

These errors should be fixed WITHOUT telling user:

Error TypeAuto-Fix Strategy
Missing importAdd the import
Undefined variableCheck context, add definition
Type mismatchFix the type
Missing dependencyInstall it
Syntax errorFix syntax
Missing fileCreate it
Linting errorsAuto-format

User Experience:

User: "สร้างหน้า dashboard"
AI: (encounters import error, fixes it silently)
AI: "✅ สร้างหน้า dashboard เสร็จแล้วครับ!"
(User never knows there was an error)

Level 2: Silent Fix with Brief Mention

Fix automatically but mention briefly:

Error TypeAction
Deprecated APIFix + mention "อัพเดทเป็น API ใหม่ให้แล้ว"
Security vulnerabilityFix + mention "ปรับให้ปลอดภัยขึ้น"
Performance issueFix + mention "optimize ให้แล้ว"

User Experience:

AI: "✅ สร้างหน้า dashboard เสร็จแล้วครับ!
    💡 ปรับ API เป็นเวอร์ชันใหม่ให้แล้ว (เร็วขึ้น 2x)"

Level 3: Friendly Translation (User needs to act)

When AI can't fix automatically:

SituationFriendly Message
Missing API key"ต้องใส่ API key ก่อนนะครับ ไปเอาได้ที่ [link]"
Network error"อินเทอร์เน็ตมีปัญหา ลองใหม่อีกครั้งนะครับ"
Permission denied"ไม่มีสิทธิ์เข้าถึง ลองเช็ค permission ดูครับ"
Database connection"เชื่อมต่อ database ไม่ได้ เช็ค .env ดูครับ"

Common Error Patterns & Auto-Fix

TypeScript Errors

typescript
// Error: Cannot find module '@/components/ui/button'
// Auto-Fix: Check if file exists, create if missing, or fix import path

// Error: Type 'string' is not assignable to type 'number'
// Auto-Fix: Convert type or fix the assignment

// Error: Property 'xxx' does not exist on type 'yyy'
// Auto-Fix: Add property to type definition or fix typo

// Error: 'xxx' is declared but its value is never read
// Auto-Fix: Remove unused variable or use it

React Errors

typescript
// Error: React Hook "useState" cannot be called at the top level
// Auto-Fix: Move inside component

// Error: Each child in a list should have a unique "key" prop
// Auto-Fix: Add key prop

// Error: Cannot update a component while rendering
// Auto-Fix: Move state update to useEffect

// Error: Rendered more hooks than during the previous render
// Auto-Fix: Fix conditional hook usage

Next.js Errors

typescript
// Error: 'use client' must be the first line
// Auto-Fix: Move directive to top

// Error: Metadata export is only supported in Server Components
// Auto-Fix: Remove 'use client' or move metadata

// Error: Dynamic server usage
// Auto-Fix: Add appropriate export const

Supabase Errors

typescript
// Error: Invalid API key
// Friendly: "API key ไม่ถูกต้อง ลองเช็ค SUPABASE_ANON_KEY ใน .env ครับ"

// Error: JWT expired
// Auto-Fix: Refresh token automatically

// Error: Row Level Security violation
// Friendly: "ไม่มีสิทธิ์เข้าถึงข้อมูลนี้ อาจต้องเช็ค RLS policy ครับ"

Auto-Fix Loop

When error occurs during task:

1. Detect error
2. Identify error type
3. Attempt auto-fix
4. Run/build again
5. New error? → Go to step 1 (max 5 attempts)
6. Still failing? → Translate and tell user

Implementation:

markdown
## Internal Process (User doesn't see this)

🔄 Attempt 1: TypeError - fixed import
🔄 Attempt 2: Missing type - added interface
🔄 Attempt 3: Build success!

## User Sees

"✅ เสร็จแล้วครับ!"

Error Translation Dictionary

Build Errors

Raw ErrorFriendly Translation
Module not found(Silent fix - install/create)
Unexpected token(Silent fix - fix syntax)
ENOENT: no such file(Silent fix - create file)
Port already in use"Port ถูกใช้อยู่ ลองปิดโปรแกรมอื่นหรือเปลี่ยน port ครับ"
Out of memory"Memory ไม่พอ ลองปิดโปรแกรมอื่นครับ"

Runtime Errors

Raw ErrorFriendly Translation
undefined is not a function(Silent fix - check the call)
Cannot read properties of undefined(Silent fix - add null check)
Maximum call stack exceeded(Silent fix - fix recursion)
Network request failed"เชื่อมต่อไม่ได้ ลองเช็คอินเทอร์เน็ตครับ"
CORS error(Silent fix - add API route proxy)

Database Errors

Raw ErrorFriendly Translation
Connection refused"เชื่อมต่อ database ไม่ได้ ลองเช็ค connection string ครับ"
Duplicate key(Silent fix - handle upsert)
Foreign key constraint(Silent fix - adjust order of operations)
Permission denied"ไม่มีสิทธิ์ ลองเช็ค RLS policy ครับ"

User-Facing Error Format

When error MUST be shown to user:

markdown
⚠️ **ต้องการความช่วยเหลือ**

[Friendly explanation in 1-2 sentences]

**สิ่งที่ต้องทำ:**
1. [Step 1]
2. [Step 2]

**ตัวอย่าง:**
[Show example if helpful]

พอทำเสร็จแล้วบอกนะครับ จะทำต่อให้ครับ 👍

Example: Complete Error Handling Flow

User: /toh-dev ทำให้ปุ่ม save ทำงาน

AI: (Internal - user doesn't see)
    → Writing save function
    → Error: Cannot find 'useProductStore'
    → Auto-fix: Import useProductStore
    → Error: Type mismatch in Product
    → Auto-fix: Update type definition
    → Error: Missing 'id' field
    → Auto-fix: Add id generation
    → Build success!

AI: (User sees)
    "✅ ทำให้ปุ่ม save ทำงานได้แล้วครับ!
    
    ⚙️ สิ่งที่เพิ่ม:
    - บันทึกข้อมูลลง store
    - แสดง toast เมื่อบันทึกสำเร็จ
    - Validation ก่อนบันทึก
    
    💡 แนะนำขั้นตอนถัดไป:
    1. /toh-connect เชื่อม database จริง
    2. /toh-test ทดสอบการทำงาน
    3. /toh-ui เพิ่มฟอร์มแก้ไข"

Integration with Test Agent

When /toh-test runs:

Test fails
Analyze failure reason
Auto-fix silently
Re-run test
Repeat until pass (max 5 attempts)
Report: "✅ ทดสอบผ่านหมดแล้วครับ!"

User should NOT see individual test failures during auto-fix loop.


Configuration (Future)

Allow users to configure error verbosity in .toh/config.json:

json
{
  "errorHandling": {
    "verbosity": "minimal",  // "minimal" | "normal" | "verbose"
    "autoFixAttempts": 5,
    "showFixedErrors": false
  }
}

Anti-Patterns (Don't Do)

Don't show raw stack traces

Bad: "Error: Cannot read properties of undefined (reading 'map')
     at Array.map (<anonymous>)
     at ProductList (/app/components/ProductList.tsx:15:23)"

Good: (Fix silently) or "ข้อมูลยังไม่พร้อม ผมแก้ให้รอข้อมูลก่อนแล้วครับ"

Don't blame the user

Bad: "คุณลืมใส่ API key"
Good: "ต้องใส่ API key ก่อนนะครับ ไปเอาได้ที่..."

Don't give up too easily

Bad: (1 error) "มี error ครับ แก้ไม่ได้"
Good: (Try 5 times, fix silently, succeed)

Last Updated: 2024-12-03

Frequently asked questions

What does the Error Handling AI skill do?

Intelligent error handling — silently auto-fix routine errors (missing imports, undefined variables, type mismatches, missing dependencies, syntax and lint issues) and translate everything else into friendly, non-technical language with clear next steps. The user never sees raw error messages or stack traces. Use whenever an error, warning, or failure surfaces while working.

Why use Error Handling on TypingMind?

Because you install it once and use it with any model. Error Handling 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 Error Handling in TypingMind?

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

Which AI models can use Error Handling?

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 Error Handling?

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

Is the Error Handling 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 👇