Prompting

by saffron-health

Prompting is an AI Engineering skill for Claude Code, published by saffron-health in libretto.

877 stars67 forkson saffron-health/librettoAdded 2026/08/22Repository updated 2026/08/21

View source on GitHub Download repo ZIP

automationbrowserclaude-codecodexrpa

Install in seconds

Install Prompting

Copy Prompting into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/saffron-health/libretto/tree/main/.agents/skills/prompting ~/.claude/skills/prompting

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/saffron-health/libretto.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: .agents/skills/prompting/SKILL.md in saffron-health/libretto
Installs to: ~/.claude/skills/prompting
Collection: One of 23 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Prompting does

Prompting guides writing effective system prompts for LLM agents. Use it when creating or editing prompts for applications, agent configurations, or development tools.

Prompting is cataloged under AI Engineering on DirSkills. Prompting comes from a repository tagged automation, browser, claude-code, codex and rpa.

Documentation

README

Excerpt

Prompting

Philosophy

LLMs are intelligent by default. System prompts set direction and impose constraints, not explain reasoning.

Start minimal. Observe failures. Add targeted fixes. Every instruction must justify its token cost by solving a real problem.

Do not explain existing capabilities, list obvious practices, add preventive instructions, or repeat information.

Frequently asked about Prompting

What else does saffron-health publish alongside Prompting?
Prompting is one of 23 skills that DirSkills catalogs from saffron-health/libretto, the repository it ships in. Its siblings there include Address Review, CLI Development and Errore. Each one is a separate skill with its own page in this directory, installs the same way Prompting does, and is maintained by saffron-health in that same repository. The rest of the collection is listed on the saffron-health/libretto page.
How does Prompting compare to other AI Engineering skills?
Prompting ranks #1504 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Prompting against them. Open each page to compare what they document and how they install.