temp-files
🎯Skillfrom llama-farm/llamafarm
|Generates temporary files in a structured system directory, ensuring clean organization and easy tracking of generated reports and logs.
Installation
npx skills add https://github.com/llama-farm/llamafarm --skill temp-filesSkill Details
Guidelines for creating temporary files in system temp directory. Use when agents need to create reports, logs, or progress files without cluttering the repository.
Overview
# Temporary Files Skill
When you need to create files to track progress, generate reports, or store temporary data, use the system's temporary directory instead of the repository root.
Directory Structure
Use this base path for all temporary files (aligns with Claude Code's existing task output convention):
```
/tmp/claude/{sanitized-cwd}/
```
Where {sanitized-cwd} is the current working directory path with / replaced by - (leading slash stripped first to avoid a leading dash).
Example: Working in /Users/bobby/workspace/pivot/llamafarm → /tmp/claude/Users-bobby-workspace-pivot-llamafarm/
Creating a Temp File
Step 1: Create the directory
```bash
SANITIZED_PATH=$(echo "$PWD" | sed 's|^/||' | tr '/' '-')
REPORT_DIR="/tmp/claude/${SANITIZED_PATH}/reviews"
mkdir -p "$REPORT_DIR"
```
Step 2: Generate a unique filename
Use this pattern: {descriptor}-{YYYYMMDD-HHMMSS}.{ext}
```bash
TIMESTAMP=$(date +%Y%m%d-%H%M%S)
FILENAME="code-review-${TIMESTAMP}.md"
FILEPATH="${REPORT_DIR}/${FILENAME}"
```
Step 3: Write the file
Use the Write tool with the full temp path.
Step 4: Inform the user
Always tell the user where the file was created:
> Report saved to: /tmp/claude/Users-bobby-workspace-pivot-llamafarm/reviews/code-review-20260108-143052.md
When to Use This Pattern
- Code review reports
- Analysis outputs
- Progress tracking files
- Test result summaries
- Any generated documentation not explicitly requested in a specific location
When NOT to Use This Pattern
- User explicitly specifies a file path
- Creating files that should be committed (e.g., README, config files)
- Editing existing files
Cleanup Note
Files in /tmp/ are cleared on system restart. If the user needs to preserve a file, suggest they copy it to a permanent location.
More from this repository10
Manages shared Python utilities for LlamaFarm, focusing on HuggingFace model handling, GGUF file management, and cross-service consistency.
Implements robust RAG document processing and retrieval using LlamaIndex, ChromaDB, and Celery for efficient, scalable AI document workflows.
Generates specialized Claude Code skills for each subsystem, creating shared language and subsystem-specific checklists to optimize AI code generation across the monorepo.
Configures secure Electron desktop application architecture with isolated processes, type-safe IPC, and cross-platform packaging for LlamaFarm.
Enforces Go best practices and idiomatic patterns for secure, maintainable LlamaFarm CLI development.
Enforces strict TypeScript best practices for React and Electron frontend applications, ensuring type safety, immutability, and clean code patterns.
Provides comprehensive Go CLI development guidelines using Cobra, Bubbletea, and Lipgloss for creating robust, interactive command-line interfaces in LlamaFarm projects.
Automates git workflow by committing changes, pushing to GitHub, and opening a PR with intelligent checks and handling of edge cases.
Provides comprehensive Python best practices and code review guidelines for ensuring high-quality, secure, and maintainable code across LlamaFarm's Python components.
Optimizes ML inference runtime with best practices for PyTorch, Transformers, and FastAPI, focusing on device management, model loading, and performance tuning.