Production-ready Aider configuration with Gemini models, auto-linting, prompt caching, and optimized settings for professional development workflows.
This skill has safety concerns that you should review before use. Some patterns were detected that may pose a risk.Safety score: 60/100.
KillerSkills scans all public content for safety. Use caution before installing or executing flagged content.
A comprehensive Aider configuration optimized for professional development workflows with Gemini models, automatic linting, prompt caching, and clean git integration.
This configuration sets up Aider with:
Create `.aider.conf.yml` in your project root or home directory with the following content:
```yaml
model: gemini/gemini-2.5-pro-preview-03-25
weak-model: gemini/gemini-2.5-flash-preview-04-17
editor-model: gemini/gemini-2.5-pro-preview-03-25
auto-accept-architect: true
cache-prompts: true
input-history-file: .aider/.aider.input.history
chat-history-file: .aider/.aider.chat.history.md
aiderignore: .aider/.aiderignore
dark-mode: true
stream: true
notifications: true
auto-commits: false
auto-lint: true
test-cmd: "run tests"
```
Create the `.aider/` directory for organized history files:
```bash
mkdir -p .aider
```
Set your Gemini API key as an environment variable:
```bash
export GEMINI_API_KEY="your-api-key-here"
```
Or add it to your `.env` file in the project root:
```
GEMINI_API_KEY=your-api-key-here
```
Create `.aider/.aiderignore` to exclude files from Aider's context:
```
node_modules/
venv/
.venv/
dist/
build/
*.pyc
.vscode/
.idea/
```
Launch Aider with your configuration:
```bash
aider
```
The configuration will be automatically loaded from `.aider.conf.yml`.
`cache-prompts: true` speeds up responses by caching repetitive context like file contents and system prompts.
`auto-lint: true` automatically runs linters after AI changes to catch issues immediately.
`auto-commits: false` gives you control over when changes are committed, allowing you to review AI modifications before committing.
`notifications: true` triggers a terminal bell when responses are ready, useful for long-running operations.
Replace model names with your preferred AI providers:
```yaml
model: anthropic/claude-3-7-sonnet-20250219
weak-model: gpt-4o-mini
```
Configure language-specific linters:
```yaml
lint-cmd:
- "python: ruff check --fix"
- "javascript: eslint --fix"
- "typescript: eslint --fix"
```
For faster iteration, enable automatic commits:
```yaml
auto-commits: true
```
Adjust terminal colors for your theme:
```yaml
user-input-color: "#00cc00"
assistant-output-color: "#0088ff"
code-theme: monokai
```
Add files to context explicitly:
```bash
aider src/main.py tests/test_main.py
```
Include files for reference without allowing edits:
```bash
aider --read docs/API.md --file src/api.py
```
Enable voice coding (requires microphone):
```yaml
voice-format: wav
voice-language: en
```
Then use `/voice` command in Aider.
1. **Keep history files**: Don't delete `.aider/` - it contains useful conversation history
2. **Review before committing**: With `auto-commits: false`, always review changes with `/diff` before manually committing
3. **Use `/lint` command**: Manually trigger linting if auto-lint is disabled
4. **Leverage architect mode**: Let AI suggest file-level refactorings with `/architect`
5. **Monitor token usage**: Use `/tokens` to check context window usage
Leave a review
No reviews yet. Be the first to review this skill!
# Download SKILL.md from killerskills.ai/api/skills/aider-pro-configuration/raw