prompting
100 / 100 · Low risk
Fine to try.
Write a document a model executes: a product prompt, a system prompt, a skill, a tool or agent description, a CLAUDE.md or AGENTS.md, a reference file behind a pointer. Use when authoring or revising any of those, when deciding what belongs in a prompt versus behind a pointer, when a prompt produces different behavior from run to run, or when a prompt makes the model take the wrong approach.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'prompting' ] || [ -L ~/.agents/skills/'prompting' ]; then echo 'A skill folder named prompting already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/bendrucker/claude' "$d" && git -C "$d" checkout --quiet '497d619eb22e6f93dd49c4d8f6ff4a52578e0949' -- 'plugins/prompting/skills/prompting' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/prompting/skills/prompting' ~/.agents/skills/'prompting' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'prompting' ~/.claude/skills/'prompting' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/bendrucker/claude/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-11 | 497d619 | 100 |
| 2026-11-08 | ebe6d12 | 100 |
| 2026-11-06 | be8a32e | 100 |