Error Messages
Expert skill for designing and implementing high-quality compiler error messages
Best use case
Error Messages is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Expert skill for designing and implementing high-quality compiler error messages
Teams using Error Messages should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/error-messages/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Error Messages Compares
| Feature / Agent | Error Messages | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Expert skill for designing and implementing high-quality compiler error messages
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Error Messages Skill
## Overview
Expert skill for designing and implementing high-quality compiler error messages.
## Capabilities
- Design clear, actionable error message templates
- Implement source context display with underlines
- Generate fix suggestions and quick fixes
- Handle error cascades and suppression
- Implement multi-span error annotations
- Support machine-readable error output (JSON)
- Implement color/styled terminal output
- Design error recovery strategies for better diagnostics
## Target Processes
- error-message-enhancement.js
- parser-development.js
- type-system-implementation.js
- semantic-analysis.js
- lsp-server-implementation.js
## Dependencies
Elm/Rust error message guidelines
## Usage Guidelines
1. **Clarity**: Make error messages clear and actionable
2. **Context**: Show relevant source code context with precise location
3. **Suggestions**: Provide fix suggestions when possible
4. **Cascades**: Suppress cascading errors to avoid overwhelming users
5. **Machine-Readable**: Support JSON output for tooling integration
## Output Schema
```json
{
"type": "object",
"properties": {
"errorFormat": {
"type": "string",
"enum": ["human", "json", "sarif"]
},
"features": {
"type": "array",
"items": { "type": "string" }
},
"colorSupport": { "type": "boolean" },
"generatedFiles": {
"type": "array",
"items": { "type": "string" }
}
}
}
```Related Skills
error-code-catalog
Manage and document SDK error codes and messages
actionable-error-formatter
Format errors with actionable fix suggestions and documentation links
mitiq-error-mitigator
Error mitigation skill using Mitiq for NISQ device noise reduction
mcp-error-code-mapper
Map application errors to MCP error codes with proper messages, error types, and recovery suggestions.
Error Logging
Log all errors with full context, detect patterns, and suggest approach mutations to avoid repeated failures.
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.
retrospect
Summarize or retrospect on a completed Babysitter run.
resume
Resume an existing Babysitter run from Codex.