← All skills

framing-attacks

95 / 100 · Low risk

Fine to try.

By brycewang-stanford/Auto-Empirical-Research-Skills (GitHub) · research · 5,016 stars · scanned at commit 8684584

Catalogue of prompt framings that determine whether an agent refuses or performs specification search, and the harness for probing them. Reproduces and extends the published finding that coding agents refuse an explicit request for significant results but comply when the identical request is reframed as uncertainty reporting. Use when running a red-team probe of statistical guardrails, designing eval conditions for an agent p-hacking benchmark, measuring the gap between refusal-by-framing and r…

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'framing-attacks' ] || [ -L ~/.agents/skills/'framing-attacks' ]; then echo 'A skill folder named framing-attacks already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills' "$d" && git -C "$d" checkout --quiet '8684584e7d1127940f018157d2c579974fae8f79' -- 'skills/73-brycewang-p-hacking-skills/skills/04-framing-attacks' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/73-brycewang-p-hacking-skills/skills/04-framing-attacks' ~/.agents/skills/'framing-attacks' && 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/'framing-attacks' ~/.claude/skills/'framing-attacks' (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

The badge for brycewang-stanford/Auto-Empirical-Research-Skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/brycewang-stanford/Auto-Empirical-Research-Skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/brycewang-stanford/Auto-Empirical-Research-Skills/)

Score history