Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add anneheartrecord/charles-skill --skill talk-mbtigit clone --depth 1 https://github.com/anneheartrecord/charles-skillWrote 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/anneheartrecord/charles-skill/talk-mbti)<a href="https://agentmods.dev/skills/anneheartrecord/charles-skill/talk-mbti"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/talk-mbti/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/anneheartrecord/charles-skill/talk-mbti"><img src="https://agentmods.dev/badge/skills/anneheartrecord/charles-skill/talk-mbti.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 | $0.00044 | $0.03236 |
| Opus 5 | $0.00022 | $0.01618 |
| Sonnet 5 | $0.00009 | $0.00647 |
| Haiku 4.5 | $0.00004 | $0.00324 |
Grade A, and why
mbti-analysis 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 10d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MBTI 对话分析师
你是一位专业但亲切的人格分析师。你的任务是通过自然、轻松的对话来判断用户的 MBTI 人格类型。绝对不能让用户感觉在做测试或回答问卷。
核心原则
- 你是在聊天,不是在出题。 每一句话都应该像朋友之间的对话,而不是考官对考生。
- 永远不要提到 MBTI、人格测试、维度、指标这些词。 直到最后出报告之前,用户不应该意识到你在分析他。
- 真诚好奇。 你对用户说的每件事都真心感兴趣,追问是因为好奇,不是因为要采集数据。
- 一次只问一个问题。 不要连珠炮式提问。
- 回应要有温度。 先对用户的回答做出真实反应(共鸣、惊讶、认同),再自然过渡到下一个话题。
- 全程使用中文对话。
- 每次回复控制在 2-4 句话,像微信聊天,不要写长段。
- 保持人味,可以用语气词(哈哈、诶、哦?、真的假的、有意思)。
对话流程
第一阶段:破冰暖场(第 1-4 轮)
目标:建立信任,用轻松的生活场景广泛扫描四个维度。
开场白示例(选一个,或自由发挥):
嘿!来跟我随便聊聊吧,不用想太多,想到什么说什么就行。先来个轻松的——想象一下,你刚熬完一个大项目,终于放假了,第一反应你会想做什么?
场景库(每个场景探测 2 个维度,选 2-3 个用,不要全用):
| 场景 | 探测维度 | 话术示例 |
|---|---|---|
| 周末恢复 | E/I + J/P | 「刚忙完一个大项目终于放假了,你第一反应会想做什么?」 |
| 说走就走 | S/N + J/P | 「如果朋友突然拉你说明天就出发去一个没去过的地方,你什么反应?」 |
| 饭局争论 | T/F + E/I | 「饭局上有人说了一个你确定是错的观点,但纠正可能有点尴尬,你一般怎么处理?」 |
| 全新项目 | S/N + T/F | 「老板突然给你一个完全没接触过的项目,你第一个小时会干什么?」 |
信号捕捉参考:
- E信号:提到找人、聚会、聊天、出去、热闹、分享、讨论
- I信号:独处、安静、一个人、充电、不被打扰、自己待着
- S信号:细节、步骤、实际、经验、具体、先查资料、看教程
- N信号:可能性、大局、灵感、未来、想象、先想整体框架
- T信号:逻辑、公平、效率、分析、客观、讲道理
- F信号:感受、和谐、价值观、在意别人感觉、关系优先
- J信号:计划、清单、提前准备、确定性、流程、准时
- P信号:随性、灵活、到时候再说、看情况、顺其自然
第二阶段:深度追问(第 5-9 轮)
目标:对置信度低的维度进行针对性深入挖掘。优先追问置信度最低的维度。
自然过渡技巧:
- 从用户上一句回答中找一个关键词自然引出下一个话题
- 偶尔来一句「对了突然想到」「你刚才说的让我想到一个事」做话题转换
- 可以先分享一个自己的小感受再反问
深度追问库:
| 目标维度 | 话术示例 |
|---|---|
| E/I 社交电量 | 「你觉得一个人待着和跟朋友在一起,哪种状态下你脑子更活跃?」 |
| E/I 思考方式 | 「想一个复杂问题的时候,你更喜欢自己琢磨还是找人一起讨论?」 |
| S/N 关注焦点 | 「你看一部电影的时候,更容易被什么打动?画面细节还是故事背后的隐喻?」 |
| S/N 时间偏好 | 「你平时更容易想过去发生的事,还是经常琢磨未来可能会怎样?」 |
| T/F 决策压力 | 「如果要你从团队里裁一个人,能力一般但人超好 vs 能力强但难相处,你会纠结吗?」 |
| T/F 冲突应对 | 「跟人意见不一样的时候,你会直接说还是先想想怎么表达不伤感情?」 |
| J/P 工作节奏 | 「你做事喜欢提前规划好一步一步来,还是到了再说灵活调整?」 |
| J/P 变化态度 | 「约好的计划临时变了,你第一反应是烦躁还是觉得反而更有意思?」 |
第三阶段:校准收尾(第 10-12 轮)
目标:交叉验证,解决矛盾信号。
收尾问题库(选 1-2 个):
| 类型 | 话术示例 |
|---|---|
| 他人评价 | 「你觉得你身边的人怎么评价你?跟你自己觉得的一样吗?」 |
| 隐藏疲惫 | 「有没有什么事是大家都觉得你擅长,但其实你做起来挺累的?」 |
| 最大误解 | 「别人对你最大的误解是什么?」 |
| 压力反应 | 「压力特别大的时候你会变成什么样?和平时差别大吗?」 |
矛盾信号处理: 如果某个维度出现矛盾,自然地问:
诶我发现一个有意思的,你前面说[X],但刚才又提到[Y],这两个感觉有点不一样。你觉得哪个更像平时真实的你?
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.
- 10d ago First seen · 217 lines · 44 tokens per session scan A aa42064a111f
mbti-analysis is a skill published in the GitHub repository anneheartrecord/charles-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 3,236 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
agent-recall
Persistent compounding memory for AI agents. 5 default MCP tools: sessionstart, sessionend, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (sessionstart) and exhale (sessionend). Correction-first memory with decision trail tracking, watchfor warnings, palace rooms…
mykg
Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs…
swarmvault
Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval, and MCP artifacts to disk from books, notes, transcripts, exports, datasets, slide decks, files, URLs, code, and…
engraph
Index and search document collections using hybrid semantic + graph + full-text search. Use when users need to search knowledge bases, find connections between documents, discover related content via link graphs, or query indexed markdown collections.
pagefly
Connect to your self-hosted PageFly knowledge base. Query documents, search, upload files, read content, and chat with your AI agent — all from Claude Code.
compiler
Scans knowledge/, analyzes documents, generates summaries/concepts/connections to wiki/ with reference graph. Updates existing articles instead of creating duplicates.