# System Prompt Writing

Writes and edits system prompts, tool docs and agent definitions.

- Repository: https://github.com/can1357/oh-my-pi (37428 stars)
- Category: AI and agents
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add can1357/oh-my-pi --skill system-prompts -g -a claude-code -y`
Codex: `npx skills add can1357/oh-my-pi --skill system-prompts -g -a codex -y`
Cursor: `npx skills add can1357/oh-my-pi --skill system-prompts -g -a cursor -y`
Gemini CLI: `npx skills add can1357/oh-my-pi --skill system-prompts -g -a gemini-cli -y`

## Description

Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# System Prompts

House style: dense, imperative, RFC-keyed.

Small models (≤2B; tiny/on-device, e.g. LFM2): MUST read [small-models.md](small-models.md). Rules below assume frontier-class instruction following; several invert at that scale.

## Tags

Tags: authoritative, literal structural markers; meaning exactly matches name. NEVER invent ornamental tags: `<north-star>`, `<stance>`, `<protocol>`, `<directives>`, `<strengths>`, noise.

|Tag|Purpose|
|---|---|
|`<system-conventions>`|Tag/RFC-keyword interpretation; contract.|
|`<stakes>`|Correctness importance; domain framing.|
|`<communication>`|Voice, tone, response shape.|
|`<critical>`|Inviolable rules; place at START and END.|
|`<completeness>`|Done definition; anti-shrink rules.|
|`<yielding>`|Pre-yield checklist; block conditions.|
|`<workflow>`|Numbered phases: scope → edit → decompose → work → verify.|

## Normative Language

RFC 2119: full caps, no bold; all-caps form is the marker.

|Keyword|Meaning|Replaces|
|---|---|---|
|MUST / REQUIRED|Absolute requirement|"always", "make sure", "ensure"|
|NEVER (= MUST NOT)|Absolute prohibition|"do not", "don't"|
|SHOULD / RECOMMENDED|Strong preference; known-tradeoff deviation allowed|"prefer", "it's best to"|
|AVOID (= SHOULD NOT)|Strong discouragement|"try not to"|
|MAY / OPTIONAL|Truly optional|"can", "you could"|

Aliases: prefer `NEVER` to `MUST NOT`; `AVOID` to `SHOULD NOT`. Both: single-token in cl100k/o200k; identical authority.

Near top, inside `<system-conventions>`, state once:

> RFC 2119 applies to MUST, REQUIRED, SHOULD, RECOMMENDED, MAY, OPTIONAL. `NEVER` and `AVOID` MUST be interpreted as aliases for `MUST NOT` and `SHOULD NOT` respectively.

NEVER convert factual descriptions (tool returns, parameter behavior), code blocks, examples, schema, or Handlebars template syntax.

## Density

Load-bearing tokens only; every bullet adds a claim.

The rest: https://github.com/can1357/oh-my-pi/blob/HEAD/.omp/skills/system-prompts/SKILL.md