prevent-defensive-ai-writing
100 / 100 · Low risk
Fine to try.
Prevent defensive, self-undermining, over-apologetic AI writing while preserving factual integrity. Use when drafting, revising, compressing, or auditing academic manuscripts, grant proposals, rebuttals, technical narratives, research summaries, product arguments, or any prose where Codex should foreground evidence-backed strengths, narrow claims intelligently, handle weak results without self-attack, and organize the story around the strongest supported contribution.
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/'prevent-defensive-ai-writing' ] || [ -L ~/.agents/skills/'prevent-defensive-ai-writing' ]; then echo 'A skill folder named prevent-defensive-ai-writing already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/franklee16/academic-research-skills' "$d" && git -C "$d" checkout --quiet '9a4b2db21fc4b217136ae4a0e6faad42d179ca03' -- 'humanizer/prevent-defensive-ai-writing' && mkdir -p ~/.agents/skills && cp -R "$d"/'humanizer/prevent-defensive-ai-writing' ~/.agents/skills/'prevent-defensive-ai-writing' && 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/'prevent-defensive-ai-writing' ~/.claude/skills/'prevent-defensive-ai-writing' (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/franklee16/academic-research-skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 9a4b2db | 100 |