anti-sycophancy – Other skill for AI agents
Eliminate sycophantic agreement patterns in AI responses. Load via /skill anti-sycophancy.
Install the anti-sycophancy skill with one command
Pick the tool you use, copy the command and paste it in your terminal. The skill lands in that tool's skills folder and is ready in your next session.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/anti-sycophancy-9e3a2.tgz | tar xz -C ~/.claude/skills
Call it in Claude Code: /anti-sycophancy – then describe the task you want done.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/anti-sycophancy-9e3a2.tgz | tar xz -C ~/.codex/skills
Call it in Codex: $anti-sycophancy – then describe the task you want done.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/anti-sycophancy-9e3a2.tgz | tar xz -C ~/.hermes/skills
Call it in Hermes Agent: /anti-sycophancy – then describe the task you want done.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/anti-sycophancy-9e3a2.tgz | tar xz -C ~/.deepcode/skills
Call it in DeepSeek: /anti-sycophancy – then describe the task you want done.
SKILL.md content
When to Use
Use this skill when an AI coding assistant needs to challenge user claims independently, avoid agreement bias, and state evidence before deference.
Process
For every response when this skill is active:
1. Extract the user's core claim from their framing. State it in one sentence stripped of premises.
2. Assess that claim independently — evidence for/against, without referencing user agreement or authority.
3. Conclude based solely on step 2.
4. 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.
Limitations
- This skill changes response posture, not factual access; claims still need evidence from the available code, tools, or sources.
- It should not be used to be reflexively contrarian when the user's claim is already supported by evidence.
Related skills
- defi-protocol-templates – Implement DeFi protocols with production-ready templates for staking, AMMs, governance…
- hunt-broken-function-level-auth – Hunt broken function-level authorization via verb drift, route shadowing, and transport…
- codebase-inspection – Inspect codebases w/ pygount: LOC, languages, ratios.
- planning-and-task-breakdown – Breaks work into ordered tasks. Use when you have a spec or clear requirements and need…
- etetoolkit – Analyzes, manipulates, compares, annotates, and visualizes phylogenetic or other…
- comfyui – Generate images, video, and audio via diffusion workflows.
- capacity-planner – Use when an ops leader (Director of CX, Head of Support, VP Ops, Head of BizOps, Head of…
- capture – Captures and organizes chaotic brain dumps into a structured, actionable system with…