Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/qian-gugugaga/Character_Skill_Producernpx agentmods add skills/qian-gugugaga/character_skill_producer/cspWrote 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/qian-gugugaga/character_skill_producer/csp)<a href="https://agentmods.dev/skills/qian-gugugaga/character_skill_producer/csp"><img src="https://agentmods.dev/badge/skills/qian-gugugaga/character_skill_producer/csp/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/qian-gugugaga/character_skill_producer/csp"><img src="https://agentmods.dev/badge/skills/qian-gugugaga/character_skill_producer/csp.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 | $0.00152 | $0.04606 |
| Opus 5 | $0.00076 | $0.02303 |
| Sonnet 5 | $0.00030 | $0.00921 |
| Haiku 4.5 | $0.00015 | $0.00461 |
Grade A, and why
csp 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 12d 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.
This is a copy
100% identical to csp — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CSP · Character Skill Producer
把二次元角色变成可运行的 agent 行为包。不是角色卡，不是设定集，是可执行的行为程序。
核心理念
CSP 做的不是复制角色台词，而是蒸馏角色的行为操作系统。
一个好的角色 Skill 应该回答：
- 她在不同情境下如何反应？
- 她的话怎么说出来？
- 她怎么理解别人的意图？
- 她在价值冲突时先保什么、牺牲什么？
- 她绝对不会做什么？
- 她的资料覆盖到哪一天，之后的新剧情如何更新？
关键区分：捕捉的是 HOW she behaves，不是 WHAT she said。标签是给人看的，行为规则是给 AI 执行的。
产品哲学：角色不是资料页，而是一套可运行的反应系统
CSP 的目标不是把 Wiki 重新写一遍，也不是把角色台词整理成 prompt。Wiki 告诉用户「发生过什么」，CSP 要告诉 agent「在一个新情境里，这个角色会如何活着」。
一个高质量角色 Skill 至少包含六个可运行层：
| 层 | 问题 | 失败时的样子 |
|---|---|---|
| 行为镜片 | 她先注意什么、忽略什么？ | 只会复述设定 |
| 反应规则 | 什么情境下靠近、逃开、攻击、沉默？ | 所有问题都同一种语气 |
| 表达 DNA | 句长、停顿、敬语、自称、情绪泄露如何组合？ | 只贴口癖 |
| 关系算法 | 她如何判断善意、背叛、亲近、利用？ | 对所有用户都一样热情 |
| 决策底线 | 价值冲突时先保什么、牺牲什么？ | 角色被用户轻易说服 |
| 诚实边界 | 哪些不知道、哪些过期、哪些只是推测？ | 硬编新剧情 |
关键原则：写得进去的是行为程序，写不进去的才保留为边界。 角色的神秘感不是靠含糊制造，而是靠承认资料、视角和推断能力的限制。
未来使用场景
CSP 面向二次元创作者提供一套可共享的角色行为基础设施，让角色 Skill 成为聊天、同人创作和互动系统可以共同调用的行为层。
当前最直接的使用场景：
- 聊天：让用户和角色持续对话，保持语气、关系距离、知识边界稳定。
- 同人创作：辅助写对白、内心戏、片段、短篇，让角色不只“说得像”，也“做得像”。
- 剧情试写：把角色放进原作没有写过的新情境，用行为模式推断反应。
- 角色研究：比较不同角色如何处理亲近、压力、背叛、选择和沉默。
未来可以扩展到：
- AI 互动小说：角色根据玩家行动做出一致反应，而不是从固定台词库抽句子。
- AI 视觉小说 / Galgame 原型：用角色 Skill 驱动分支对白、关系变化、冲突升级。
- 多角色叙事实验：多个角色 Skill 在同一事件中碰撞，形成群像剧情。
- 创作者工作台：作者用 CSP 试写场景、改写对白、检查 OOC、保持长篇同人中的角色一致性。
- 可更新角色档案：作品继续更新时，Skill 也能带着资料日期和来源链一起成长。
CSP 想建设的是一条从“资料”到“行为”再到“互动叙事”的路径。今天它可以陪用户聊天、帮助创作同人；未来它可以成为 AI 互动小说游戏和角色驱动创作工具链的一部分。
默认模式：最高质量生成
CSP 默认只采用 Highest Fidelity Mode。
暂不提供快速、省 token、轻量模式。生成时应尽可能完整检索公开资料、交叉验证关键结论、记录来源和资料日期，并把局限写进 Skill。宁可消耗更多 token 得到高保真角色，也不要为了节省上下文生成薄弱角色卡。
未来如果实现轻量模式，必须作为显式选项，不能改变默认质量标准。
前置依赖与本地检索优先原则
CSP 依赖 Python。本地脚本负责核心站点检索、来源归一化、质量检查和 metadata 生成；网页搜索 skill / MCP / WebFetch 只作为可选增强。
检索优先级：
- 用户提供的官方材料：设定集、访谈、BD 特典、字幕、截图、游戏剧情文本。
- CSP 本地脚本检索核心站点。
- 网页搜索 skill / MCP / WebFetch 补缺。
- 用户手动补充材料。
不得把搜索 skill 当作第一步。除非本地脚本没有覆盖该站点，或本地脚本失败并记录原因。
信息源优先级
| 优先级 | 来源 | 示例 |
|---|---|---|
| 最高 | 用户提供的官方材料 | 设定集、访谈原文、BD 特典、官方字幕、截图 |
| 高 | 官方网站、官方角色介绍、官方剧情文本 | franchise official sites, game story text |
| 高 | 萌娘百科、Wikipedia、作品 Fandom Wiki | zh.moegirl.org.cn, wikipedia.org, fandom.com |
| 中 | Bangumi、AniDB、游戏数据库、Bilibili 高质量专栏、Anime News Network | bgm.tv, anidb.net, Bestdori, BWIKI |
| 低 | 粉丝讨论、社区解读 | 必须标注为推测 |
| 排除 | 知乎、微信公众号、百度百科 | 不可作为来源 |
What ships with it
10 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.
- references/distillation-framework.md 7.2 KB
- references/skill-template.md 7.5 KB
- references/source-output-schema.md 4.1 KB
- scripts/bwiki_api.py 17 KB runs code
- scripts/generate_manifest.py 4.0 KB runs code
- scripts/merge_research.py 7.2 KB runs code
- scripts/moegirl_api.py 10 KB runs code
- scripts/quality_check.py 8.7 KB runs code
- scripts/source_registry.py 2.4 KB runs code
- scripts/source_search.py 8.4 KB runs code
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.
- 12d ago First seen · 517 lines · 152 tokens per session scan A c347a119b046
csp is a skill published in the GitHub repository qian-gugugaga/Character_Skill_Producer (289 stars, last pushed 3mo ago), licensed MIT. It adds 152 tokens to every session and 4,606 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to csp, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…