chat-quality-doctor
100 / 100 · Low risk
Fine to try.
聊后调优门诊——用户和角色卡聊完不满意时的一级分诊台:太AI/机味/太假/出戏/OOC/小作文/太啰嗦/回复太短敷衍/讨好没脾气/降智/不记得我说过的/剧情推不动/状态栏不显示/被拒答/老替我说话(robotic / AI-like / OOC / too verbose / too short / forgot / refusal)。先分诊定位病灶域(文体/记忆/剧情/设定/渲染/模型/口味),文体类按「诊断→作用域→手术→验证」治,非文体类指路对应机制;附 8 份 per-model RP 症状档案与 AI 味套话词表。仅用于已有聊天结果不满意后的诊断调优;写新卡用 character-card-author。
Partially scanned — some files couldn't be read; we'll retry on the next scan
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/'chat-quality-doctor' ] || [ -L ~/.agents/skills/'chat-quality-doctor' ]; then echo 'A skill folder named chat-quality-doctor already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/foreverse-app/character-card-skills' "$d" && git -C "$d" checkout --quiet 'dab0da437810b2ea4b5eec414c10c8fa35e779f8' -- 'skills/chat-quality-doctor' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/chat-quality-doctor' ~/.agents/skills/'chat-quality-doctor' && 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/'chat-quality-doctor' ~/.claude/skills/'chat-quality-doctor' (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/foreverse-app/character-card-skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | dab0da4 | 100 |