agentleFS
gigio1023gigio1023/gigio-skills/skills/minimal/prompting-guide/SKILL.md

prompting-guide

Skill2 starsChanged 3 days agoMITView on GitHub

Write, review, debug, or migrate system prompts, CLAUDE.md, AGENTS.md, skills, subagent definitions, or tool descriptions for a specific Claude or GPT target model, using vendor prompting guidance newer than the model's training. Also drafts, reviews, or translates Codex Goal mode and Claude Code /goal prompts. Use for "write the system prompt for Opus", "goal prompt 써줘", "프롬프트 고쳐줘".

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Prompting Guide

Each model family has its own guide. Identify the family that will run the instructions and read that guide; skip the others.

Target modelRead
Claude Fable or MythosFable guide
Claude Opus, including migration from an earlier OpusOpus guide
GPT-6 family (Astra, Sol)GPT guide

The target is the model that will execute the prompt, not the model doing the editing. Take it from the request, a model ID in the integration or configuration, a model field in the agent or skill definition, or the host's documented default. Ask only when it cannot be determined and the answer changes the advice. Each guide names the versions it covers; a newer release may have its own vendor page, so check before applying an older version's clauses to it.

For a Codex Goal mode or Claude Code /goal prompt (explain, draft, review, translate between the two, or activate), read the Goal mode guide with the target family's guide.

When an artifact runs on more than one family, such as a skill shared by Claude Code and Codex, apply each family's guide to that family's behavior and keep the clauses distinguishable. When migrating between families, follow the target family's guide; the source family's guide only helps identify scaffolding written for the old model.

Do not port guidance between families without measurement. The model lines changed in different directions, and effort level names do not mean the same amount of thinking across models. The Fable and Opus guides share some Anthropic runtime facts (beta headers, thinking-block binding, refusal fallback); when you update one, check the other.

A model outside these families has no guide here. Say so and work from that model's official prompting documentation.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.