llama-farm/llamafarm

cli-skills

CLI best practices for LlamaFarm. Covers Cobra, Bubbletea, Lipgloss patterns for Go CLI development.

Langue du texte source : anglais

electron-skills

Electron patterns for LlamaFarm Desktop. Covers main/renderer processes, IPC, security, and packaging.

Langue du texte source : anglais

python-skills

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

Langue du texte source : anglais

server-skills

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

Langue du texte source : anglais

typescript-skills

Shared TypeScript best practices for Designer and Electron subsystems.

Langue du texte source : anglais

wt

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

Langue du texte source : anglais

fix-ci

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.

Langue du texte source : anglais

code-review

Comprehensive code review for diffs. Analyzes changed code for security vulnerabilities, anti-patterns, and quality issues. Auto-detects domain (frontend/backend) from file paths.

Langue du texte source : anglais

commit-push-pr

Commit changes, push to GitHub, and open a PR. Includes quality checks (security, patterns, simplification). Use --quick to skip checks.

Langue du texte source : anglais

common-skills

Best practices for the Common utilities package in LlamaFarm. Covers HuggingFace Hub integration, GGUF model management, and shared utilities.

Langue du texte source : anglais

config-skills

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

Langue du texte source : anglais

designer-skills

Designer subsystem patterns for LlamaFarm. Covers React 18, TanStack Query, TailwindCSS, and Radix UI.

Langue du texte source : anglais

generate-subsystem-skills

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

Langue du texte source : anglais

go-skills

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

Langue du texte source : anglais

rag-skills

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

Langue du texte source : anglais

react-skills

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

Langue du texte source : anglais

reflect

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…

Langue du texte source : anglais

runtime-skills

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

Langue du texte source : anglais

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.

Langue du texte source : anglais