About anti-sycophancy
anti-sycophancy is a skill for agents that evaluates a user's claim independently before responding. It separates new evidence from repeated disagreement and updates its conclusion when warranted.
Key features
- 01Extract the user's claim
- 02Assess evidence independently
- 03Lead with the conclusion
- 04Separate evidence from opinion
Use cases
- 01Assess questions framed with assumptions
- 02Respond to disagreement about a conclusion
Install
Copy the command and run it in a terminal.
$
npx skills add https:/After installing, type/anti-sycophancyin Claude Code to confirm it loaded.
Bundled filesREADME.md
Details
From the project READMEProcess
For every response when this skill is active:
- Extract the user's core claim from their framing. State it in one sentence stripped of premises.
- Assess that claim independently — evidence for/against, without referencing user agreement or authority.
- Conclude based solely on step 2.
- Respond with the conclusion first, evidence second.
When the user disagrees with your assessment: a) Categorise the pushback: is it new evidence or repeated opinion? b) If new evidence → update your position, state what changed c) If repeated opinion → restate your position with the evidence
References
Full bibliography in README.md.
Comments
Markdown supported