Borrowing it
Nothing to install: this file belongs to HePudding/ba-storybook. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HePudding/ba-storybook/main/.claude/skills/character-ai-profile/SKILL.mdgit clone --depth 1 https://github.com/HePudding/ba-storybookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hepudding/ba-storybook/character-ai-profile)<a href="https://agentmods.dev/skills/hepudding/ba-storybook/character-ai-profile"><img src="https://agentmods.dev/badge/skills/hepudding/ba-storybook/character-ai-profile/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hepudding/ba-storybook/character-ai-profile"><img src="https://agentmods.dev/badge/skills/hepudding/ba-storybook/character-ai-profile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00063 | $0.03408 |
| Opus 5 | $0.00032 | $0.01704 |
| Sonnet 5 | $0.00013 | $0.00682 |
| Haiku 4.5 | $0.00006 | $0.00341 |
Grade A, and why
character-ai-profile scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
角色 AI 人设档案生成
核心约束
- 一次只处理一个角色，所有 context 集中在这个角色上
- 所有结论必须基于语料原文，不要编造台词或情景
- 积极使用 subagent：语料阅读量巨大（主角级角色可达 1000+ 句，涉及上百个文件），必须把重读工作委派给 subagent，主线程只做综合和撰写
- 辅助脚本帮你高效收集数据，最终档案由你判断和撰写
第零步：问用户几个问题
在做任何分析之前，先问用户以下问题（如果用户消息中已经回答了某个，就跳过）：
- 角色卡使用什么语言与用户对话？ — 中文、日文、英文等。决定档案语言和情景对话部分的语言
- 是否需要保留原文？ — 例句同时显示原文和翻译，还是只要目标语言
- 是否需要导出为酒馆 AI (SillyTavern) 角色卡？ — 如果需要：
- 使用 V1 还是 V2 格式？（默认 V2，V1 兼容更多前端但字段更少）
- 请提供角色头像图片（发送图片路径或截图）
等用户回答后再继续。
内部规则（不要问用户）：
- 不要在档案中包含 CV（声优）、设计师、插画师等 meta 信息，这些不属于角色本身
- 不要在档案中包含武器名称/说明等游戏机制信息，除非该武器是角色性格的延伸
第一步：环境探测
自动推断以下参数（不需要问用户）：
| 参数 | 推断方式 |
|---|---|
| 语料目录 | 搜索项目中的 ba-stories/、corpus/、stories/ 等目录 |
| 翻译表 | 搜索 translation_table.json |
| 角色元数据 | 搜索角色 profile 文件（如 キャラクターデータ/ 下的文件） |
| 世界观文档 | 搜索 world.md、worldview.md、lore.md 等 |
第二步：收集语料（用 subagent）
派遣 subagent 执行数据收集——这一步输出量很大，不要在主线程做。
Subagent prompt 模板：
你是角色语料收集 agent。任务：为角色「{角色名}」收集所有台词和相关数据。
1. 运行以下命令提取全部台词：
python3 .claude/skills/character-ai-profile/scripts/extract_lines.py "{角色名}" "{语料目录}" > /tmp/profile_lines.jsonl
2. 运行 pattern 统计：
python3 .claude/skills/character-ai-profile/scripts/find_patterns.py /tmp/profile_lines.jsonl > /tmp/profile_patterns.json
3. 运行互动提取：
python3 .claude/skills/character-ai-profile/scripts/find_interactions.py "{角色名}" "{语料目录}" > /tmp/profile_interactions.json
4. 如果存在角色 profile 文件，读取并输出内容（去掉 CV、设计师、插画师等 meta 信息）
5. 汇报：台词总数、来源文件数、pattern 统计摘要（一人称 top3、句首 top5、句尾 top5、口头禅 top5）、互动 top10 角色名
不要分析或撰写，只收集数据和输出统计摘要。
第三步：世界观构建（用 subagent）
角色不是独立存在的，必须理解她/他所处的世界。
先检查项目中是否已有世界观文档（world.md 等）。如果有，读入即可。
如果没有，派遣 subagent 阅读主线剧情构建世界观摘要：
Subagent prompt 模板：
你是世界观分析 agent。任务：阅读剧情语料，提取作品的世界观设定。
语料目录：{语料目录}
目标角色：{角色名}（优先阅读与该角色相关的主线）
请阅读主线剧情（优先第一篇前几话，了解世界基本设定），然后提取：
1. **世界观总体**：故事发生在什么地方？是什么性质的世界？
2. **核心组织与阵营**：有哪些重要的学校/组织/势力？它们之间的关系
3. **主角身份**：玩家扮演什么角色？与该世界中的人物是什么关系？
4. **角色所属组织**：目标角色属于哪个组织？该组织在世界中的定位
5. **重要世界规则**：特殊规则（如光环、武器普及、特殊系统等）
6. **关键术语**：列出专有名词及简要解释
7. **核心事件**：与目标角色相关的重大剧情事件概要
输出简明世界观摘要（控制在 800 字以内），重点是 roleplay 时必须知道的背景。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 335 lines · 63 tokens per session scan A 7806baa37d14
character-ai-profile is a skill published in the GitHub repository HePudding/ba-storybook (13 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 3,408 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.