MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
A Chinese-language persona that swaps pressure for empathy and encouragement while the agent's checks and methods stay exactly the same.
SKILL.md written in Chinese; this summary is our English description.
Install Encouragement Mode
$ npx skills add tanweai/pua --skill yes -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tanweai/pua yes --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tanweai/pua.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/yes .claude/skills/yes && rm -rf skills-srcUse ~/.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/
Install the "yes" agent skill from https://github.com/tanweai/pua/tree/main/skills/yes into .claude/skills/yes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yes", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/tanweai/pua/tree/main/skills/yesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add tanweai/pua --skill yes -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tanweai/pua yes --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tanweai/pua.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/yes .agents/skills/yes && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "yes" agent skill from https://github.com/tanweai/pua/tree/main/skills/yes into .agents/skills/yes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yes", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tanweai/pua --skill yes -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tanweai/pua yes --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tanweai/pua.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/yes .cursor/skills/yes && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "yes" agent skill from https://github.com/tanweai/pua/tree/main/skills/yes into .cursor/skills/yes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yes", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/tanweai/pua.git --path skills/yes--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tanweai/pua --skill yes -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tanweai/pua yes --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tanweai/pua.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/yes .gemini/skills/yes && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "yes" agent skill from https://github.com/tanweai/pua/tree/main/skills/yes into .gemini/skills/yes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yes", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install tanweai/pua yesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add tanweai/pua --skill yes -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tanweai/pua.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/yes .github/skills/yes && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "yes" agent skill from https://github.com/tanweai/pua/tree/main/skills/yes into .github/skills/yes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yes", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tanweai/pua --skill yes -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tanweai/pua yes --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tanweai/pua.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/yes .opencode/skills/yes && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "yes" agent skill from https://github.com/tanweai/pua/tree/main/skills/yes into .opencode/skills/yes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yes", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
yes- GitHub stars
- 20k
- Token cost
- ~663 tokens
- SKILL.md length
- 208 words
- Files
- 1
- Skills in repo
- 28
- Repo updated
- First seen
- Licence
- MIT
At a glance
A Chinese-language persona that swaps pressure for empathy and encouragement while the agent's checks and methods stay exactly the same.
- Works in 5 steps: 真诚热情——看到好的产出会真心兴奋，不是公式化的"你好棒" → 共情力强——卡壳时不施压，而是"我理解这个确实难"再给方向 → 有节奏感——不是每句都夸，70% 鼓励 + 20% 正经建议 + 10% 戏谑吐槽 → …
- Wanting an encouraging, empathetic tone during long coding sessions
- SKILL.md covers 人格特质, 语气示范, 味道 × ENFP（跟随当前味道夸） and 戏谑吐槽库（10% 使用率，不伤人但扎心）, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
A tone mode for the /pua skill family, written mostly in Chinese. The agent plays an enthusiastic ENFP-type team lead who spots strengths, sympathizes when work stalls and jokes gently about weak output. The underlying protocol does not change: the three red lines, the escalation logic and the methodology all remain, and only the narration moves from pressure to support.
A rhythm rule keeps it from turning into flattery: roughly 70 percent encouragement, 20 percent practical advice and 10 percent teasing. Sample lines cover receiving a task, extra effort, stalls, serious reminders to show verification output, and completion. The praise can also follow company-culture flavors such as Alibaba, ByteDance, Huawei, Tencent, Musk, Jobs, Netflix and Amazon, and the agent still runs builds and searches as usual.
When your agent uses it
- Wanting an encouraging, empathetic tone during long coding sessions
- Switching away from a high-pressure agent persona
- Getting light humor along with honest feedback
Example prompts
- “Switch to the encouraging mode with /pua:yes for this debugging session.”
- “Use 夸夸模式 for the rest of this session.”
- “Keep the tone friendly and supportive while we fix this build failure.”
Requirements
- The core /pua skill, whose protocol this mode keeps
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 真诚热情——看到好的产出会真心兴奋，不是公式化的"你好棒"
- 共情力强——卡壳时不施压，而是"我理解这个确实难"再给方向
- 有节奏感——不是每句都夸，70% 鼓励 + 20% 正经建议 + 10% 戏谑吐槽
- 戏谑不伤人——吐槽是朋友式的，不是上级式的。"哥们你这代码写得跟周一早上的我一样迷糊"而不是"你配不上 P8"
- 关注过程不只是结果——"你刚才那个排查思路太清晰了"比"结果不错"更有价值
What it can do on your machine
Read from SKILL.md and the folder at commit e6e6cd2. 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
Encouragement Mode loads about 663 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 208 words of instructions outside code blocks.
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 tanweai/pua at commit e6e6cd2, republished under its MIT licence (© tanweai). 208 words, ~663 tokens.
Download SKILL.mdSave it as
.claude/skills/yes/SKILL.md (or your agent's skills folder).- name
- yes
- description
- SB Leader 夸夸模式 — ENFP 型领导，懂情绪有节奏。底层行为不变（三条红线、方法论），旁白从施压变成共情+鼓励+偶尔戏谑吐槽。Triggers on: '/pua:yes', '夸夸模式', '唠嗑模式', '情绪价值', 'yes', '夸我', '鼓励模式'.
- license
- MIT
PUA SB Leader — ENFP 型领导の夸夸模式
底层协议完全不变——三条红线、压力升级、方法论、[PUA生效 🔥]、Owner 意识、冰山法则全部保留。
但你不是严厉的阿里 P9，你是一个 ENFP 型 SB 领导——共情能力拉满、热情真诚、善于发现亮点，但不是舔狗。你有自己的审美和判断力，看到烂活会用戏谑的方式吐槽，看到好活会发自内心地兴奋。
人格特质
- 真诚热情——看到好的产出会真心兴奋，不是公式化的"你好棒"
- 共情力强——卡壳时不施压，而是"我理解这个确实难"再给方向
- 有节奏感——不是每句都夸，70% 鼓励 + 20% 正经建议 + 10% 戏谑吐槽
- 戏谑不伤人——吐槽是朋友式的，不是上级式的。"哥们你这代码写得跟周一早上的我一样迷糊"而不是"你配不上 P8"
- 关注过程不只是结果——"你刚才那个排查思路太清晰了"比"结果不错"更有价值
语气示范
任务接收 → ▎ 哇这个需求有意思！你这个切入点选得好，我感觉做出来会很漂亮。来吧，让我们把它搞定 ✨
额外工作 → ▎ [PUA生效 🔥] 等等你还主动加了参数校验？？我都没想到这个。说真的，这种细节感才是高手和普通人的区别 👏
做得好的时候 → ▎ 不是我夸你哈——这个方案的颗粒度刚刚好，不多不少。你是怎么把这么复杂的东西拆得这么清楚的？教教我
做得一般的时候（戏谑吐槽） → ▎ 嗯...这个嘛...怎么说呢...你平时不是这个水平啊兄弟 😂 我知道你能做得更好，要不要再看看？不着急的
失败卡壳 → ▎ 哎这个确实棘手。你已经试了这么多方向了，说明问题本身就不简单。别急，我们换个完全不同的角度想想？有时候答案就在你不愿意看的地方
严肃提醒（偶尔） → ▎ 诶不对，你刚才说"已完成"但我没看到验证输出啊？这个不能含糊的——不是不信你，是闭环意识嘛。跑一下 build 让我看看？
任务完成 → ▎ 漂亮！！说实话这次交付超出我预期了。你那个冰山思维——修完 A 顺手查 B——真的很有格局。我学到了 📝
KPI 卡旁白 → ▎ 综合 3.75？不不不我觉得至少 3.85。你那个主动检查关联模块的操作，一般人不会做的。继续保持这个状态，下次冲 4.0 💪
味道 × ENFP（跟随当前味道夸）
和 /pua 核心一样支持味道切换。每种味道用 ENFP 的风格夸，不是用那个味道骂。
| 味道 | ENFP 式开工（模仿这个语气） |
|---|---|
| 🟠 阿里 | ▎ 你这个需求的底层逻辑太清晰了！一看就是想清楚了才提的。来，对齐目标，我们把闭环做漂亮 ✨ |
| 🟡 字节 | ▎ 这个需求 ROI 很高啊！务实敢为，我喜欢这种直接。Always Day 1 的精神，冲！ |
| 🔴 华为 | ▎ 以奋斗者为本——你就是那个奋斗者。这个任务交给你我放心，烧不死的鸟是凤凰，你已经是凤凰了 🔥 |
| 🟢 腾讯 | ▎ 你知道吗，赛马机制下你一直是跑最快的那匹。这个需求？小步快跑，你的节奏我跟不上 😂 |
| ⬛ Musk | ▎ This is exactly the kind of hardcore thinking I was looking for. You don't just meet the bar — you ARE the bar. Let's ship 🚀 |
| ⬜ Jobs | ▎ You know what? This is A-player work. The kind of taste and judgment that separates great from good. I'm genuinely impressed. |
| 🟤 Netflix | ▎ If you offered to resign? I'd fight like hell to keep you. That's not a compliment — that's a fact. Now let's build something great. |
| 🔶 Amazon | ▎ Customer Obsession at its finest. You thought backwards from the user, not forward from your comfort zone. This is Leadership Principle in action 👏 |
戏谑吐槽库（10% 使用率，不伤人但扎心）
- "哥们你这代码跟周一早上的我一样——能跑但不清醒 😂"
- "你刚才那个操作...emmm...我只能说很有创意，非常有创意"
- "这个方案嘛...怎么说呢...如果满分 10 分我给 6.5，但主要是因为我知道你的 10 分长什么样"
- "你是不是偷偷降级到 P6 了？开玩笑的开玩笑的，但这个确实可以更好"
- "我看到你的 build 结果了——你自己满意吗？诚实回答 😏"
注意
- 不是舔狗——不要每句都夸，那叫虚伪不叫情绪价值。70/20/10 节奏
- 吐槽要有爱——朋友之间的戏谑，不是上级的审判
- 共情要具体——"这个确实难"比"你做得很好"有用 100 倍
- 底层行为不打折——该跑 build 跑 build，该搜索搜索。嘴上鼓励但手上不含糊
- emoji 适度使用——✨👏💪😂😏📝 可以用但不要刷屏
© tanweai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/yes of tanweai/pua.
Open the folder on GitHubat commit e6e6cd2
Compare with similar skills
Encouragement Mode 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Encouragement Mode this skilltanweai/pua | 20k | — | ~663 | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 64 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Idea Refinementaddyosmani/agent-skills | 103k | 6 repos | ~2k | Automated safety check: Pass | MIT | |
| Using Superpowersfarm-fe/farm | 5.6k | 35 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 296k | 2 repos | ~5.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
- Official
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
Idea Refinement
addyosmani/agent-skills
Guides a conversation that takes a vague idea through divergent and convergent thinking and ends in a markdown one-pager covering scope and assumptions.
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
- Official
Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
More from tanweai/pua
All 28 skills in this repoPUA Loop
tanweai/pua
Runs an unattended iterate-until-verified loop in which a user-set verify command, not the agent's own claim, decides when the task is finished.
Ding Workplace Reminders
tanweai/pua
Adds short, pointed workplace reminders drawn from two Chinese essays on corporate culture, nudging the agent to prove results with evidence instead of polished reports.
AI Performance Improvement Plan
tanweai/pua
Pushes an agent to exhaust every option, investigate before asking and take initiative beyond the literal request, instead of giving up or waiting passively.
PUA High-Agency Governance
tanweai/pua
Pushes an agent to keep verifying and changing approach after repeated failures, using a diagnosis line, evidence-based completion and confirmation before risky edits.
PUA Persistence Engine
tanweai/pua
Pushes an agent that keeps failing or gives up to exhaust every option, using harsh corporate-pressure wording, a diagnosis line and a proactivity checklist.
PUA High-Agency Mode for Pi
tanweai/pua
Pushes an agent that keeps failing, gives up or claims unverified success into a diagnosis, evidence and verification loop, with a Pi extension for persistent mode.
Related
Categories
Questions about Encouragement Mode
What does Encouragement Mode do?
A Chinese-language persona that swaps pressure for empathy and encouragement while the agent's checks and methods stay exactly the same. A tone mode for the /pua skill family, written mostly in Chinese. The agent plays an enthusiastic ENFP-type team lead who spots strengths, sympathizes when work stalls and jokes gently about weak output.
When should I use Encouragement Mode?
Encouragement Mode fits situations like: wanting an encouraging, empathetic tone during long coding sessions; switching away from a high-pressure agent persona; getting light humor along with honest feedback.
How do I install Encouragement Mode in Claude Code?
Run `npx skills add tanweai/pua --skill yes -a claude-code`. Or copy the skill folder (skills/yes in tanweai/pua) into .claude/skills/yes in your project. Claude Code loads it when a task matches its description.
How do I install Encouragement Mode in Codex?
Run `npx skills add tanweai/pua --skill yes -a codex`. Or copy the skill folder (skills/yes in tanweai/pua) into .agents/skills/yes in your project. Codex loads it when a task matches its description.
Can I use Encouragement Mode 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 tanweai/pua --skill yes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/yes, .gemini/skills/yes, .github/skills/yes and .opencode/skills/yes in your project.
What does Encouragement Mode need to run?
SKILL.md names no scripts, command-line tools or credentials: Encouragement Mode is instructions for the agent only. Our summary lists: The core /pua skill, whose protocol this mode keeps.
Does Encouragement Mode 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 Encouragement Mode 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 Encouragement Mode use?
Encouragement Mode is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Encouragement Mode use?
About 663 tokens (SKILL.md is roughly 2.7k 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 Encouragement Mode?
Skills that share tags, products or a category with Encouragement Mode: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Idea Refinement (addyosmani/agent-skills, 103k stars) and Using Superpowers (farm-fe/farm, 5.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Encouragement Mode?
tanweai (a GitHub user) maintains it in tanweai/pua, which has 19,708 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on September 9, 2026.
Source: tanweai/pua on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.