temp-files

Guidelines for creating temporary files in system temp directory. Use when agents need to create reports, logs, or progress files without cluttering the repository.

830 stars

Best use case

temp-files is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Guidelines for creating temporary files in system temp directory. Use when agents need to create reports, logs, or progress files without cluttering the repository.

Teams using temp-files 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

$curl -o ~/.claude/skills/temp-files/SKILL.md --create-dirs "https://raw.githubusercontent.com/llama-farm/llamafarm/main/.claude/skills/temp-files/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/temp-files/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How temp-files Compares

Feature / Agenttemp-filesStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Guidelines for creating temporary files in system temp directory. Use when agents need to create reports, logs, or progress files without cluttering the repository.

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

# 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.

Related Skills

wt

830
from llama-farm/llamafarm

Manage LlamaFarm worktrees for isolated parallel development. Create, start, stop, and clean up worktrees.

DevOps & Infrastructure

typescript-skills

830
from llama-farm/llamafarm

Shared TypeScript best practices for Designer and Electron subsystems.

server-skills

830
from llama-farm/llamafarm

Server-specific best practices for FastAPI, Celery, and Pydantic. Extends python-skills with framework-specific patterns.

runtime-skills

830
from llama-farm/llamafarm

Universal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving. Covers device management, model loading, memory optimization, and performance tuning.

reflect

830
from llama-farm/llamafarm

Analyze the current session and propose improvements to skills. **Proactively invoke this skill** when you notice user corrections after skill usage, or at the end of skill-heavy sessions. Also use when user says "reflect", "improve skill", or "learn from this".

react-skills

830
from llama-farm/llamafarm

React 18 patterns for LlamaFarm Designer. Covers components, hooks, TanStack Query, and testing.

rag-skills

830
from llama-farm/llamafarm

RAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers. Covers ingestion, retrieval, embeddings, and performance.

python-skills

830
from llama-farm/llamafarm

Shared Python best practices for LlamaFarm. Covers patterns, async, typing, testing, error handling, and security.

go-skills

830
from llama-farm/llamafarm

Shared Go best practices for LlamaFarm CLI. Covers idiomatic patterns, error handling, and testing.

generate-subsystem-skills

830
from llama-farm/llamafarm

Generate specialized skills for each subsystem in the monorepo. Creates shared language skills and subsystem-specific checklists for high-quality AI code generation.

fix-ci

830
from llama-farm/llamafarm

Fetch GitHub CI failure information, analyze root causes, reproduce locally, and propose a fix plan. Use `/fix-ci` for current branch or `/fix-ci <run-id>` for a specific run.

config-skills

830
from llama-farm/llamafarm

Configuration module patterns for LlamaFarm. Covers Pydantic v2 models, JSONSchema generation, YAML processing, and validation.