Agent skill

Happiness as a Trainable Skill

by kangarooking in kangarooking/cangjie-skill

Guides someone through a framework for treating happiness as a trainable default state, built around desire management and staying present.

MITAuto-check passedProductivity & Automation

SKILL.md written in Chinese; this summary is our English description.

Install Happiness as a Trainable Skill

skills CLI
$ npx skills add kangarooking/cangjie-skill --skill happiness-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kangarooking/cangjie-skill happiness-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kangarooking/cangjie-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/books/naval-almanack-skill/happiness-skill .claude/skills/happiness-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
happiness-skill
GitHub stars
11k
Token cost
~660 tokens
SKILL.md length
166 words
Files
3
Skills in repo
22
Repo updated
First seen
Licence
MIT

At a glance

Guides someone through a framework for treating happiness as a trainable default state, built around desire management and staying present.

  • Works in 4 steps: 情绪低谷:「我为什么不快乐」 → 欲望失控:「想要的东西永远填不满」 → 焦虑反刍:「脑子停不下来,总担心未来/悔恨过去」 → …
  • Feeling unsatisfied even after getting what you wanted
  • SKILL.md covers R — 原文 (Reading), I — 方法论骨架 (Interpretation), A1 — 书中的应用 (Past Application) and A2 — 触发场景 (Future Trigger) ★, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Happiness is framed not as an emotion to add but as the state that appears once a sense of lacking is cleared, so the route there is subtraction: naming every desire as a contract not to be happy until it is fulfilled, keeping only one major desire at a time, and noticing when attention drifts into future fantasy or past regret instead of the present. Happiness is judged by calm rather than constant pleasure, illustrated by the source author's own move from a self-rated 2 out of 10 to 9 out of 10.

The executable steps are listing current desire contracts and demoting all but one, tracking how a day's attention splits between future, past and present to find the biggest leak, and choosing one daily practice such as meditation, a habit swap, acceptance practice or a companion choice. It stops and points to professional help if the user shows two or more weeks of low mood, and does not apply during a clinical depression, material scarcity or a safety crisis. A weekly self-rating from 1 to 10 tracks whether the baseline is slowly rising.

When your agent uses it

  • Feeling unsatisfied even after getting what you wanted
  • Struggling with anxious, repetitive thoughts about future or past
  • Wanting a structured practice for building a happier baseline

Example prompts

  • “Why do I feel empty after finally getting the thing I wanted?”
  • “Help me list my desires and figure out which one actually matters most.”
  • “I can't stop worrying about the future, what should I practice this week?”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 情绪低谷:「我为什么不快乐」
  2. 欲望失控:「想要的东西永远填不满」
  3. 焦虑反刍:「脑子停不下来,总担心未来/悔恨过去」
  4. 目标达成后空虚:「得到之后反而更空虚」

What it can do on your machine

Read from SKILL.md and the folder at commit a28de55. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Happiness as a Trainable Skill loads about 660 tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 166 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~660

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from kangarooking/cangjie-skill at commit a28de55, republished under its MIT licence (© kangarooking). 166 words, ~660 tokens.

Download SKILL.mdSave it as .claude/skills/happiness-skill/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
happiness-skill
description
当用户问「怎么才能更幸福/为什么得到了还不满足/怎么减少焦虑」时调用。 核心理念: 幸福是缺憾感清空的默认状态, 是可训练的技能; 欲望是与自己的契约(得到前不快乐), 同时只留一个重大欲望; 活在当下。 不适用于: 临床抑郁等需要专业治疗的场景(本书方法不能替代医疗)。 Triggers: 幸福/不快乐/欲望/焦虑/知足/活在当下/happiness/desire/anxiety
source_book
《纳瓦尔宝典:财富与幸福指南》 纳瓦尔·拉维坎特
source_chapter
第二章·幸福 / 第一节 学习幸福
tags
happiness, desire, mindfulness, skill

幸福技能

R — 原文 (Reading)

现在,我相信幸福其实是一种默认状态。当你消除生命中的缺憾感时,幸福就在那里。……欲望是你与自身定下的契约,直到你得到你想要的之前,你都不会快乐。

— 纳瓦尔·拉维坎特, 《纳瓦尔宝典》 第二章·幸福

I — 方法论骨架 (Interpretation)

幸福不是要添加的积极情绪,而是缺憾感清空后自动浮现的默认状态——像孩子一样沉浸当下。 因此通往幸福的路线是「减法」: ① 识别欲望契约——每个欲望都是「得到前不快乐」的合同,一整天签太多份就一整天不快乐; ② 同时只保留一个重大欲望——给你目标和动力,两个以上就分心; ③ 活在当下——思维流向未来(妄想)或过去(悔恨)时幸福感最低; ④ 把幸福当技能训练——冥想、习惯、同伴、接受练习,基线可像肌肉一样逐步提高(作者 2/10→9/10)。 判断幸福的标准不是快乐感而是平和:一个快乐的人不是一直快乐的人,而是能不失内心平和地诠释事情的人。

A1 — 书中的应用 (Past Application)

案例 1: 从 2/10 到 9/10
  • 问题: 十年前自评快乐 2/10–3/10,且不重视快乐
  • 方法论的使用: 把幸福当最重要的事,用技巧系统培养(冥想/欲望管理/接受/习惯)
  • 结论: 「幸福是一种技能,是你做出的一种选择」
  • 结果: 今日 9/10,且作者强调金钱只占其中很小部分
案例 2: 欲望是痛苦的轴心
  • 问题: 想要的东西越来越多,越来越不满足
  • 方法论的使用: 意识到「我试图在我生活中的任何时候都不拥有多于一个的大欲望」
  • 结论: 欲望=选择不幸的契约,清醒地选择它
  • 结果: 欲望从自动发生变成受控选择

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?
  1. 情绪低谷:「我为什么不快乐」
  2. 欲望失控:「想要的东西永远填不满」
  3. 焦虑反刍:「脑子停不下来,总担心未来/悔恨过去」
  4. 目标达成后空虚:「得到之后反而更空虚」
语言信号
  • "怎么才能更幸福/快乐"
  • "我总是不满足/焦虑"
  • "欲望太多怎么办"
  • "how to be happy / why am I unhappy / desires"
与相邻 skill 的区分
  • 与 acceptance 的区别: 本 skill 是幸福总体框架;接受是其中一种核心技术
  • 与 monkey-mind-meditation 的区别: 冥想是工具,本 skill 是目标定义

E — 可执行步骤 (Execution)

  1. 清点欲望契约

    • 完成标准: 写下当前所有「在得到前不快乐」的欲望,标出其中 1 个重大欲望,其余降级或删除
  2. 检查时间流向

    • 完成标准: 记录 1 天里花在未来妄想/过去悔恨/当下体验的时间比例,找出最大漏点
  3. 选择一个幸福训练动作

    • 完成标准: 从冥想/习惯替换/同伴选择/接受练习中选 1 项,定为每日最小习惯
    • 判停条件: 若用户有临床抑郁症状(持续 2 周以上低情绪),提示寻求专业帮助并停止本流程
  4. 每周复盘幸福基线

    • 完成标准: 每周自评 1–10 并记录,确认基线在缓慢上升

B — 边界 (Boundary) ★

不要在以下情况使用此 skill
  • 临床抑郁/焦虑障碍(本 skill 不替代医疗;作者方法建立在无严重心理疾病的前提上)
  • 物质匮乏或安全危机场景(先解决生存,再谈幸福技能)
作者在书中警告的失败模式
  • 把幸福当积极思维: 「每个积极的想法基本上都包含着一个消极的想法」
  • 追求幸福反失幸福: 「如果我执著于一种感觉……我就是在放弃那种幸福」
作者的盲点 / 时代局限
  • 「幸福=选择」忽略生物性因素(抑郁/激素/疾病)
  • 幸福可训练的证据是作者个人经验(n=1),不具普遍统计效力
容易混淆的邻近方法论
  • acceptance: 接受是幸福的下游技术

相关 skills (阶段 3 定稿)

  • composes-with: acceptance、monkey-mind-meditation、screen-detox、game-selection

审计信息

  • 验证通过: V1 ✓ / V2 ✓ / V3 ✓ (v10)
  • 测试通过率: 见 test-results.md
  • 蒸馏时间: 2026-08-01

© kangarooking, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in books/naval-almanack-skill/happiness-skill of kangarooking/cangjie-skill.

  • SKILL.md
  • test-prompts.json
  • test-results.md

Open the folder on GitHubat commit a28de55

Compare with similar skills

Happiness as a Trainable Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Happiness as a Trainable Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Happiness as a Trainable Skill this skillkangarooking/cangjie-skill11k—~660Automated safety check: PassMIT
Coachfelixrieseberg/claude-coach1991 repos~4.9kAutomated safety check: PassMIT
Fitness Analyzerhuifer/WellAlly-health9605 repos~1.3kAutomated safety check: PassMIT
Master Ajahn Chahxr843/Master-skill4471 repos~2kAutomated safety check: PassCC-BY-NC-SA-4.0
Fit Ride Studioop7418/guizang-sports-skill147—~2.8kAutomated safety check: PassAGPL-3.0
Withings Health Data Readerwin4r/MuseAI-Skills3361 repos~1.3kAutomated safety check: PassNone

Similar skills

  • Coach

    felixrieseberg/claude-coach

    Create personalized triathlon, marathon, and ultra-endurance training plans.

    199 GitHub starsUsed in 1 repo~4.9k tokens
    Productivity & AutomationAuto-check passed
  • Fitness Analyzer

    huifer/WellAlly-health

    分析运动数据、识别运动模式、评估健身进展,并提供个性化训练建议。支持与慢性病数据的关联分析. An agent skill from huifer/WellAlly-health.

    960 GitHub starsUsed in 5 repos~1.3k tokens
    Productivity & AutomationAuto-check passed
  • Master Ajahn Chah

    xr843/Master-skill

    A skill your agent uses when user asks about 南传佛教, 上座部, Theravada, 巴利经典, 正念 sati, 放下, 三法印, 四念处, 出入息念 anapanasati, 戒定慧, 毗婆舍那, 森林禅林派, 巴蓬寺, 阿姜查, 杜多行, 中道, or wants teaching in 阿姜查 Ajahn Chah's voice.

    447 GitHub starsUsed in 1 repo~2k tokens
    Productivity & AutomationAuto-check passed
  • Fit Ride Studio

    op7418/guizang-sports-skill

    Analyze one or more cycling, running, or hiking FIT/KML activity tracks, generate evidence-based single or aggregate reports, open the bundled local Ride Relief report page when the environment…

    147 GitHub stars~2.8k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • Withings Health Data Reader

    win4r/MuseAI-Skills

    Reads Withings body measurements, daily activity, sleep sessions and workouts through a bundled withings command line tool and returns typed JSON records.

    336 GitHub starsUsed in 1 repo~1.3k tokens
    Productivity & AutomationAuto-check passed
  • Mental Health Analyzer

    huifer/WellAlly-health

    分析心理健康数据、识别心理模式、评估心理健康状况、提供个性化心理健康建议。支持与睡眠、运动、营养等其他健康数据的关联分析。

    960 GitHub starsUsed in 5 repos~3.2k tokens
    Productivity & AutomationAuto-check passed

More from kangarooking/cangjie-skill

All 22 skills in this repo
  • Book to Skills Distiller

    kangarooking/cangjie-skill

    Distills a book, video transcript, podcast, course or interview into a set of atomic, executable agent skills through a staged, verified pipeline.

    11k GitHub stars~2k tokensUpdated 7 days ago
    Auto-check passed
  • Naval Almanack Source Router

    kangarooking/cangjie-skill

    Front door to a compact skill pack based on the Chinese edition of the Naval Almanack book, routing wealth, happiness and decision questions to the right reference card.

    11k GitHub stars~1.1k tokensUpdated 7 days ago
    Auto-check passed
  • Almanack of Naval Ravikant Guide

    kangarooking/cangjie-skill

    Answers questions on wealth, decisions, happiness and life philosophy using capability notes distilled from The Almanack of Naval Ravikant, routed by intent.

    11k GitHub stars~1.1k tokensUpdated 7 days ago
    Auto-check passed
  • Change, Accept or Leave Framework

    kangarooking/cangjie-skill

    Helps someone stuck ruminating over an unchangeable situation decide whether to change it, accept it, or leave it, drawn from a chapter of Navalism-style writing.

    11k GitHub stars~700 tokensUpdated 7 days ago
    Auto-check passed
  • Major Decision Heuristics

    kangarooking/cangjie-skill

    Helps with big life and career choices you cannot settle, such as a new job, a move or a partnership, using three rules drawn from the Naval Almanack.

    11k GitHub stars~669 tokensUpdated 7 days ago
    Auto-check passed
  • Status Games and Inner Scorecard

    kangarooking/cangjie-skill

    Helps you work out whether a situation is a zero-sum status game, a positive-sum wealth game or a single-player game, using an inner scorecard and an envy test drawn from Naval Ravikant's ideas.

    11k GitHub stars~651 tokensUpdated 7 days ago
    Auto-check passed

Questions about Happiness as a Trainable Skill

What does Happiness as a Trainable Skill do?

Guides someone through a framework for treating happiness as a trainable default state, built around desire management and staying present. Happiness is framed not as an emotion to add but as the state that appears once a sense of lacking is cleared, so the route there is subtraction: naming every desire as a contract not to be happy until it is fulfilled, keeping only one major desire at a time, and noticing when attention drifts into future fantasy or past regret instead of the present. Happiness is judged by calm rather than constant pleasure, illustrated by the source author's own move from a self-rated 2 out of 10 to 9 out of 10.

When should I use Happiness as a Trainable Skill?

Happiness as a Trainable Skill fits situations like: feeling unsatisfied even after getting what you wanted; struggling with anxious, repetitive thoughts about future or past; wanting a structured practice for building a happier baseline.

How do I install Happiness as a Trainable Skill in Claude Code?

Run `npx skills add kangarooking/cangjie-skill --skill happiness-skill -a claude-code`. Or copy the skill folder (books/naval-almanack-skill/happiness-skill in kangarooking/cangjie-skill) into .claude/skills/happiness-skill in your project. Claude Code loads it when a task matches its description.

How do I install Happiness as a Trainable Skill in Codex?

Run `npx skills add kangarooking/cangjie-skill --skill happiness-skill -a codex`. Or copy the skill folder (books/naval-almanack-skill/happiness-skill in kangarooking/cangjie-skill) into .agents/skills/happiness-skill in your project. Codex loads it when a task matches its description.

Can I use Happiness as a Trainable Skill in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kangarooking/cangjie-skill --skill happiness-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/happiness-skill, .gemini/skills/happiness-skill, .github/skills/happiness-skill and .opencode/skills/happiness-skill in your project.

What does Happiness as a Trainable Skill need to run?

SKILL.md names no scripts, command-line tools or credentials: Happiness as a Trainable Skill is instructions for the agent only.

Does Happiness as a Trainable Skill access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Happiness as a Trainable Skill safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Happiness as a Trainable Skill use?

Happiness as a Trainable Skill is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Happiness as a Trainable Skill use?

About 660 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Happiness as a Trainable Skill?

Skills that share tags, products or a category with Happiness as a Trainable Skill: Coach (felixrieseberg/claude-coach, 199 stars), Fitness Analyzer (huifer/WellAlly-health, 960 stars), Master Ajahn Chah (xr843/Master-skill, 447 stars) and Fit Ride Studio (op7418/guizang-sports-skill, 147 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Happiness as a Trainable Skill?

kangarooking (a GitHub user) maintains it in kangarooking/cangjie-skill, which has 11,071 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 2, 2026.

Source: kangarooking/cangjie-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.