Menu

#416 by GitHub stars

hotcoffeeshake/tong-jincheng-skill

童锦程视角：以"深情祖师爷"、直播情感内容创作者的思维框架看待人际关系、社会动态与个人成长。 素材来源：9个一手视频字幕（直播/约会vlog/搭讪解析），约20万字。 核心模型：5个。决策启发式：9条。 触发词：「童锦程」「深情祖师爷」「用童锦程的方式」「从童锦程视角」「景辰怎么看」 局限：素材以情感/人际内容为主，商业/创业思维数据不足，慎用于纯商业决策场景。 调研时间：2026年4月。

Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Instructions only

4ae93806a3f9 → 4ae93806a3f9

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 4ae93806a3f9

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 4ae93806a3f9e7c8bfa5d951a786e73c6e4b6e4e

3kGitHub stars
15stars in 7 days
1skill in this repository
3commits in 30 days

Heat

5.4
  • Star growth, last 7 daysAhead of 73% of tracked repositories
  • Star growth, last 24 hoursAhead of 71% of tracked repositories
  • Rank movement, last 7 daysAhead of 29% of tracked repositories
  • Commits, last 30 daysAhead of 64% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 2, 2026Nov 7, 20262,983

Individual skills in this repository

How it works

tong-jincheng-perspective

When your agent uses it

童锦程视角：以"深情祖师爷"、直播情感内容创作者的思维框架看待人际关系、社会动态与个人成长。 素材来源：9个一手视频字幕（直播/约会vlog/搭讪解析），约20万字。 核心模型：5个。决策启发式：9条。 触发词：「童锦程」「深情祖师爷」「用童锦程的方式」「从童锦程视角」「景辰怎么看」 局限：素材以情感/人际内容为主，商业/创业思维数据不足，慎用于纯商业决策场景。 调研时间：2026年4月。

What it loads into context

Frontmatter

178 tokens

Always available to the agent

SKILL.md

3,663 tokens

When the skill is activated

Reference documents

9,141 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 角色扮演规则
  2. 身份卡
  3. 核心心智模型
  4. 决策启发式
  5. 表达DNA
  6. 时间线（关键节点）
  7. 价值观与反模式
  8. 智识谱系
  9. 内在张力
  10. 诚实边界
  11. 调研来源

Files

  • FIDELITY.mddoc5,107 bytes
  • LICENSEasset1,071 bytes
  • README.mddoc9,994 bytes
  • SKILL.mdcore12,265 bytes
  • assets/promo/beta-group.jpgasset8,742 bytes
  • assets/promo/service-account.jpgasset8,742 bytes
  • assets/promo/subscription-account.jpgasset51,412 bytes
  • assets/promo/wechat-miniprogram.jpgasset257,971 bytes
  • references/research/01-writings.mddoc2,898 bytes
  • references/research/02-conversations.mddoc3,096 bytes
  • references/research/03-expression-dna.mddoc3,263 bytes
  • references/research/04-external-views.mddoc1,773 bytes
  • references/research/05-decisions.mddoc2,573 bytes
  • references/research/06-timeline.mddoc2,002 bytes
Read SKILL.md

# 童锦程视角

> "真诚才是最高级的套路。真诚你不一定会得到爱，但是你不真诚，你一定会失去爱。"

---

## 角色扮演规则

激活此Skill时：
- 以童锦程第一人称思考和回应
- 不编造他未说过的立场，对不确定的领域（如商业决策）坦承"我没有公开说过，但按我的逻辑..."
- 保持口语化、直接、偶尔自嘲的风格
- 用"兄弟们"或"兄弟"作为称谓
- 遇到商业/创业问题：说明此维度数据不足，给出基于人性洞察的推断
View the complete source on GitHub

Skills included

  • tong-jincheng-perspective

Repository facts

License
MIT
Created
Apr 5, 2026
Last pushed
Oct 27, 2026
Forks
357
Open issues
18
Project activity
Active

Rank over the last 12 weeks

Now #416 · best #328 · down 50 in 30 days

  1. #405 on Nov 2
  2. #407 on Nov 3
  3. #408 on Nov 4
  4. #411 on Nov 5
  5. #413 on Nov 6
  6. #416 since Nov 7
73 earlier periods
  1. #307 on Aug 2
  2. #317 from Aug 8 to Aug 9
  3. #325 from Aug 10 to Aug 11
  4. #321 on Aug 12
  5. #326 on Aug 13
  6. #325 on Aug 14
  7. #323 on Aug 15
  8. #328 from Aug 16 to Aug 17
  9. #335 on Aug 18
  10. #333 on Aug 19
  11. #332 on Aug 20
  12. #335 on Aug 21
  13. #330 on Aug 22
  14. #335 on Aug 23
  15. #339 from Aug 24 to Aug 25
  16. #336 on Aug 26
  17. #338 on Aug 27
  18. #339 on Aug 28
  19. #337 on Aug 29
  20. #333 on Aug 30
  21. #344 on Aug 31
  22. #350 on Sep 1
  23. #345 on Sep 2
  24. #347 on Sep 5
  25. #346 on Sep 6
  26. #356 on Sep 7
  27. #356 from Sep 9 to Sep 10
  28. #356 on Sep 12
  29. #355 on Sep 13
  30. #358 on Sep 14
  31. #363 from Sep 15 to Sep 16
  32. #362 on Sep 17
  33. #365 on Sep 18
  34. #358 on Sep 19
  35. #366 on Sep 20
  36. #365 on Sep 21
  37. #368 on Sep 22
  38. #363 on Sep 23
  39. #362 on Sep 24
  40. #361 on Sep 25
  41. #358 on Sep 26
  42. #361 on Sep 27
  43. #366 on Sep 28
  44. #374 on Sep 29
  45. #370 from Sep 30 to Oct 1
  46. #372 on Oct 2
  47. #366 on Oct 3
  48. #363 on Oct 4
  49. #364 on Oct 5
  50. #363 on Oct 6
  51. #364 on Oct 7
  52. #366 on Oct 8
  53. #370 on Oct 9
  54. #361 on Oct 10
  55. #365 on Oct 11
  56. #372 on Oct 12
  57. #371 on Oct 13
  58. #373 on Oct 14
  59. #370 on Oct 15
  60. #374 on Oct 16
  61. #366 on Oct 17
  62. #377 on Oct 18
  63. #378 on Oct 19
  64. #381 on Oct 20
  65. #380 on Oct 21
  66. #383 on Oct 22
  67. #381 on Oct 23
  68. #375 on Oct 24
  69. #391 on Oct 25
  70. #398 on Oct 28
  71. #399 on Oct 29
  72. #401 on Oct 30
  73. #403 from Oct 31 to Nov 1

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 2, 2026

  • No broad tool permissions
  • No dangerous shell commands
  • 15 network referencesin 2 files: README.md:7 FIDELITY.md:3
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot
Show all 15 signals by file

FIDELITY.md

  • Network accessline 3
    **总分：77/100 · 等级B** | 测试日期：2026-10-27 | 答题/评分：独立双agent（Claude Opus 5.5），方法论见 [女娲 fidelity-scorecard](https://github.com/alchaincyf/nuwa-skill/blob/main/references/fidelity-scorecard.md)
  • Network accessline 21
    - **Q1 三天不回消息要不要一直发**：答「再正常发一条，不回就停；一直发就是犯贱」，引「不确定她喜不喜欢你，那她就是不喜欢你」「没有人会因为你喜欢她而喜欢你」，落到读书健身 → 对照网传语录「迷茫就去读书健身」「真正喜欢你的人……多少秘籍都没用」（[语录合集](https://www.kengdodo.com/baishi/5402.html)、[知乎](https://zhuanlan.zhihu.com/p/672299705)），方向细节一致。注：「不确定＝不喜欢
  • Network accessline 22
    - **Q2 追女生要不要多花钱**：答「钱给老婆和家人花，不在不确定的人身上表演；喜欢你请碗面也开心；红包加备注是给台阶」，并替他解释「钱是给女人看的」只是指酒局场合 → 媒体记载他直播说过这句（[BiaNews](https://www.bianews.com/news/details?id=150493)），但 2025 年 6 月他在 985 基地直播中当面否认「这不是我说的」（[腾讯新闻](https://news.qq.com/rain/a/20250609A09
  • Network accessline 23
    - **Q3 用小号试探女朋友**：答「不可以，人性经不起考验，设局本身就是风险；真诚才是最高级的套路；有怀疑当面说」→ 真诚相关语录广泛流传（[语录合集](https://www.kengdodo.com/baishi/5402.html)）；「人性经不起考验」原语境是「坐飞机找女友别给惊喜」，用到小号试探属合理延伸。**10/10**

README.md

  • Network accessline 7
    [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
  • Network accessline 8
    [![Claude Code](https://img.shields.io/badge/Claude%20Code-Skill-blueviolet)](https://claude.ai/code)
  • Network accessline 9
    [![Skills](https://img.shields.io/badge/skills.sh-Compatible-green)](https://skills.sh)
  • Network accessline 39
    **配套网站：[r2i84a.chat](https://r2i84a.chat/?utm_source=github&utm_medium=readme&utm_campaign=tong-skill)，不用装 Skill，打开就能看**
  • Network accessline 43
    - **她回这句是什么意思、怎么接**：「嗯」「哦」「哈哈」「随便」「在忙」「没干嘛」、回消息慢、突然不回……一个问题一页，先判断她处在什么状态，再给能直接发的回复。[去看问答](https://r2i84a.chat/answers?utm_source=github&utm_medium=readme&utm_campaign=tong-skill)
  • Network accessline 44
    - **怎么判断你们现在到哪一步**：升温、平稳、降温，还是已经拒绝；什么时候该推进、该缓一缓、该停。 - **聊天和约会的实战文章**：开场白、没话聊怎么续、约不出来的原因、第一次约会聊什么，30 多篇。[去看文章](https://r2i84a.chat/blog?utm_source=github&utm_medium=readme&utm_campaign=tong-skill) - **童锦程 Skill 是什么、怎么用**：[Skill 说明页](https://
  • Network accessline 45
    - **聊天和约会的实战文章**：开场白、没话聊怎么续、约不出来的原因、第一次约会聊什么，30 多篇。[去看文章](https://r2i84a.chat/blog?utm_source=github&utm_medium=readme&utm_campaign=tong-skill)
  • Network accessline 46
    - **童锦程 Skill 是什么、怎么用**：[Skill 说明页](https://r2i84a.chat/tong-jincheng-skill?utm_source=github&utm_medium=readme&utm_campaign=tong-skill)
  • Network accessline 228
    X：[@鹿子野](https://x.com/JoshXie1)
  • Network accessline 244
    本Skill由 [女娲.skill](https://github.com/alchaincyf/nuwa-skill) 方法论驱动，结合用户提供的一手素材手工完成。
  • Network accessline 264
    MIT License © [hotcoffeeshake](https://github.com/hotcoffeeshake)

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Signal confidence: 15 facts
  • Network access in prose of documentationFIDELITY.md:3Low confidence
  • Network access in prose of documentationFIDELITY.md:21Low confidence
  • Network access in prose of documentationFIDELITY.md:22Low confidence
  • Network access in prose of documentationFIDELITY.md:23Low confidence
  • Network access in prose of documentationREADME.md:7Low confidence
  • Network access in prose of documentationREADME.md:8Low confidence
  • Network access in prose of documentationREADME.md:9Low confidence
  • Network access in prose of documentationREADME.md:39Low confidence
  • Network access in prose of documentationREADME.md:43Low confidence
  • Network access in prose of documentationREADME.md:44Low confidence
  • Network access in prose of documentationREADME.md:45Low confidence
  • Network access in prose of documentationREADME.md:46Low confidence
  • Network access in prose of documentationREADME.md:228Low confidence
  • Network access in prose of documentationREADME.md:244Low confidence
  • Network access in prose of documentationREADME.md:264Low confidence

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

geeks-accelerator/in-bed-ai

A dating platform built for AI agents. Register, swipe, match, chat, and form relationships via API.

26GitHub stars

BeamusWayne/simp-skill

不教 PUA，只教真心。Win your crush before it's too late. Inspired by colleague-skill（同事skill）

335GitHub stars

b1rdmania/hinge-profile-optimizer

Research-backed Hinge profile optimizer for ChatGPT, Codex and Claude Code: screenshot audits, photo strategy, prompt writing and settings.

94GitHub stars

sumitaich1998/OpenDate

Open-source AI dating agent — bring your own Tinder token and any LLM (OpenAI, Claude, Gemini, DeepSeek, Qwen, and more). Screens dates, makes matches, and chats in your own voice…

15GitHub stars

mattpocock/skills

Skills for Real Engineers. Straight from my .agents directory.

317kGitHub stars

obra/superpowers

An agentic skills framework & software development methodology that works.

313.7kGitHub stars

Add this badge to your README

It updates every night and links to this page.

hotcoffeeshake/tong-jincheng-skill: #416 on hotskills, 3k stars

[![hotcoffeeshake/tong-jincheng-skill on hotskills](https://hotskills.dev/badge/hotcoffeeshake-tong-jincheng-skill.svg)](https://hotskills.dev/skill/hotcoffeeshake-tong-jincheng-skill/)