Agent Browser CLI
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
Helps you decide who to spend time with, using the five-chimpanzees idea that your behavior follows the five people you see most.
SKILL.md written in Chinese; this summary is our English description.
Install Peer Selection
$ npx skills add kangarooking/cangjie-skill --skill peer-selection -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kangarooking/cangjie-skill peer-selection --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/kangarooking/cangjie-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/books/naval-almanack-skill/peer-selection .claude/skills/peer-selection && 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 "peer-selection" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/peer-selection into .claude/skills/peer-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "peer-selection", 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/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/peer-selectionType 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 kangarooking/cangjie-skill --skill peer-selection -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kangarooking/cangjie-skill peer-selection --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kangarooking/cangjie-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/books/naval-almanack-skill/peer-selection .agents/skills/peer-selection && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "peer-selection" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/peer-selection into .agents/skills/peer-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "peer-selection", 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 kangarooking/cangjie-skill --skill peer-selection -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kangarooking/cangjie-skill peer-selection --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kangarooking/cangjie-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/books/naval-almanack-skill/peer-selection .cursor/skills/peer-selection && 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 "peer-selection" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/peer-selection into .cursor/skills/peer-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "peer-selection", 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/kangarooking/cangjie-skill.git --path books/naval-almanack-skill/peer-selection--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 kangarooking/cangjie-skill --skill peer-selection -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kangarooking/cangjie-skill peer-selection --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kangarooking/cangjie-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/books/naval-almanack-skill/peer-selection .gemini/skills/peer-selection && 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 "peer-selection" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/peer-selection into .gemini/skills/peer-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "peer-selection", 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 kangarooking/cangjie-skill peer-selectionInstalls 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 kangarooking/cangjie-skill --skill peer-selection -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kangarooking/cangjie-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/books/naval-almanack-skill/peer-selection .github/skills/peer-selection && 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 "peer-selection" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/peer-selection into .github/skills/peer-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "peer-selection", 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 kangarooking/cangjie-skill --skill peer-selection -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kangarooking/cangjie-skill peer-selection --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kangarooking/cangjie-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/books/naval-almanack-skill/peer-selection .opencode/skills/peer-selection && 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 "peer-selection" agent skill from https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/peer-selection into .opencode/skills/peer-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "peer-selection", 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
peer-selection- GitHub stars
- 11k
- Token cost
- ~666 tokens
- SKILL.md length
- 154 words
- Files
- 3
- Skills in repo
- 22
- Repo updated
- First seen
- Licence
- MIT
At a glance
Helps you decide who to spend time with, using the five-chimpanzees idea that your behavior follows the five people you see most.
- Works in 4 steps: 换城市/换工作后的交友 → 被朋友拖累：「朋友总在抱怨，我也变消极了」 → 择偶/亲密关系选择 → …
- Deciding whether to distance yourself from a draining friend
- 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
The skill takes an idea from Naval Ravikant's almanack: you can predict a person from the five people they spend the most time with, so friends and partners should be chosen on purpose, not because they live nearby or share an office. Three principles apply: choose actively by values, set the mix by context (more successful people at work, happier ones for leisure), and keep away from cynical, pessimistic or conflict-prone people. The skill text is written in Chinese.
The agent walks through four steps: list your five closest contacts and mark each positive, negative or neutral; name what your work and leisure circles lack and pick one concrete way to add it; for each negative relationship choose between a direct conversation, firmer limits or leaving; and write a short list of three to five core values to screen new people. It advises limits rather than cutting off relatives or colleagues you must see, and the five-chimpanzees idea is flagged as a metaphor, not rigorous psychology.
When your agent uses it
- Deciding whether to distance yourself from a draining friend
- Building a new social circle after moving city or changing jobs
- Choosing a partner by checking for shared values
- Wanting to meet more successful or more upbeat people
Example prompts
- “My close friends complain constantly and I feel more negative around them. What should I do?”
- “I moved to a new city and want to build friendships that match my values.”
- “Help me audit the five people I spend the most time with.”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- 换城市/换工作后的交友
- 被朋友拖累：「朋友总在抱怨，我也变消极了」
- 择偶/亲密关系选择
- 想改变圈子：「我想认识更优秀/更快乐的人」
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
Peer Selection loads about 666 tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 154 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 kangarooking/cangjie-skill at commit a28de55, republished under its MIT licence (© kangarooking). 154 words, ~666 tokens.
Download SKILL.mdSave it as
.claude/skills/peer-selection/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- peer-selection
- description
- 当用户纠结交朋友/选伴侣/换圈子、感觉被周围人拖累、问「该不该疏远某人」时调用。 核心理念: 五只黑猩猩理论(你的行为由最常接触的5人预测); 同伴是主动选择而非巧合; 只与价值观一致者深交, 远离愤世嫉俗者/愤怒者。 不适用于: 职场必须共事的同事关系(可先设边界)。 Triggers: 朋友/圈子/伴侣/该不该疏远/被拖累/五只黑猩猩/peer/friends/circle/values
- 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 / 习惯造就幸福
- tags
- relationship, happiness, values, community
同伴选择：五只黑猩猩
R — 原文 (Reading)
有个“五只黑猩猩的理论”，你可以通过它最常接触的五个黑猩猩来预测一个黑猩猩的行为。……你不应该随意地选择你的朋友，仅仅是因为你们住的比较近或者碰巧在一起工作。选择了正确的五只黑猩猩的人，是最快乐和最乐观的人。
— 纳瓦尔·拉维坎特, 《纳瓦尔宝典》 第二章·幸福
I — 方法论骨架 (Interpretation)
你的行为、情绪和成就由最常接触的五个人预测——所以同伴选择是人生最重要的主动决策之一。 三个原则： ① 主动选择——朋友不是地理/巧合的产物，而是价值观筛选的结果； ② 按场景配置——「工作时，身边要有比你更成功的人；玩乐时，身边要有比你更快乐的人」； ③ 远离负向者——愤世嫉俗者/悲观主义者会传染负面预期；处理冲突的第一规则是「不要和那些经常发生冲突的人在一起」；「如果你不能看到你与某人一起工作一辈子，那么连一天也不要和他共事」。 判断信号：总说自己诚实的人多半不诚实；花很多时间谈论价值观的人可能在掩盖什么； 价值观一致时小事不重要，价值观冲突才是争吵的根源。
A1 — 书中的应用 (Past Application)
案例 1: 贝赫扎德的「哇」
- 问题: 如何保持对生活的感恩与乐观
- 方法论的使用: 学习热爱生活、不浪费时间在不快乐的人身上
- 结论: 他的诀窍是「停止询问为什么，开始说哇」
- 结果: 成为作者心中选择正确同伴的样板
案例 2: 从生活中剔除负面者
- 问题: 有人做损害他人的事
- 方法论的使用: 第一次提醒，不改就保持距离、从生活中切割
- 结论: 「越想靠近我的，你的价值观必须要更好」
- 结果: 圈子成为价值观过滤后的结果
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 换城市/换工作后的交友
- 被朋友拖累：「朋友总在抱怨，我也变消极了」
- 择偶/亲密关系选择
- 想改变圈子：「我想认识更优秀/更快乐的人」
语言信号
- "我该交什么样的朋友"
- "要不要疏远某人"
- "怎么认识优秀的人/换圈子"
- "who should I surround myself with / toxic friends"
与相邻 skill 的区分
- 与
long-term-compounding的区别: 本 skill 选「和谁生活」；复利 skill 选「和谁做生意」 - 与
honesty-communication的区别: 诚实是自我标准，本 skill 是外部筛选标准
E — 可执行步骤 (Execution)
盘点你的五只黑猩猩
- 完成标准: 列出最常接触的 5 人，逐个标「积极/消极/中性」，评估他们预测了你的什么行为
按场景调整配置
- 完成标准: 明确工作圈和玩乐圈分别缺什么（更成功/更快乐），列出 1 个具体加入动作（活动/社群/项目）
处理负向关系
- 完成标准: 对每个消极关系选一：改造（明确沟通）、边界（减少接触频次）、或切割（退出）
- 判停条件: 若对方是亲属/同事无法切割，改为设置接触边界并补齐正向外圈
建立价值观检查
- 完成标准: 写下一份 3–5 条核心价值观清单，用来判断新朋友是否「小事不重要、大事一致」
B — 边界 (Boundary) ★
不要在以下情况使用此 skill
- 必须共事的同事/家人（先边界，再切割）
- 用户自身处于低谷、把责任全推给环境（先自我负责再选圈）
作者在书中警告的失败模式
- 随意选友: 「仅仅是因为你们住的比较近或者碰巧在一起工作」
- 与经常冲突的人在一起: 冲突是低质量关系的信号，不是性格磨合
作者的盲点 / 时代局限
- 「远离不快乐的人」在家庭/社群文化中的执行成本高，且可能滑向同温层
- 五只黑猩猩是预测性比喻，非严谨心理学结论
容易混淆的邻近方法论
long-term-compounding: 生意伙伴选「能共事一辈子」；生活同伴选「价值观一致+积极」
相关 skills (阶段 3 定稿)
- composes-with:
happiness-skill、long-term-compounding、honesty-communication
审计信息
- 验证通过: V1 ✓ / V2 ✓ / V3 ✓ (v15)
- 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/peer-selection of kangarooking/cangjie-skill.
- SKILL.md
- test-prompts.json
- test-results.md
Open the folder on GitHubat commit a28de55
Compare with similar skills
Peer Selection 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 |
|---|---|---|---|---|---|---|
| Peer Selection this skillkangarooking/cangjie-skill | 11k | — | ~666 | Automated safety check: Pass | MIT | |
| Agent Browser CLIvercel-labs/agent-browser | 44k | 24 repos | ~864 | Automated safety check: Pass | Apache-2.0 | |
| Agent Browserquran/quran.com-frontend-next | 1.9k | 41 repos | ~3.3k | Automated safety check: Pass | None | |
| Web Access via Browser CDPeze-is/web-access | 9.1k | 4 repos | ~2.2k | Automated safety check: Pass | MIT | |
| Process Inboxtelegramdesktop/tdesktop | 33k | 2 repos | ~4.5k | Automated safety check: Pass | GPL-3.0 | |
| Dev Browser AutomationMemTensor/MemOS | 12k | 3 repos | ~1.7k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Agent Browser
quran/quran.com-frontend-next
Automates browser interactions for web testing, form filling, screenshots, and data extraction.
Web Access via Browser CDP
eze-is/web-access
Routes every web task, from searching to logged-in browsing, through a tiered choice of search, fetch, curl or a real Chrome or Edge session driven over CDP.
Process Inbox
telegramdesktop/tdesktop
Process the local ignored ai-tdesktop inbox into durable, independently testable Telegram Desktop task records while task execution worktrees remain active.
Dev Browser Automation
MemTensor/MemOS
Automates a real browser through short TypeScript scripts that keep page state between runs, for navigating, filling forms, taking screenshots and extracting data.
Tavily Web Search
allenpeng0705/EnvoyMesh
Searches the web through the Tavily API with LLM-friendly output: clean structured results, optional AI-written answers, domain filters, news mode, images and raw content.
More from kangarooking/cangjie-skill
All 22 skills in this repoBook 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.
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.
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.
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.
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.
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.
Related
Categories
Questions about Peer Selection
What does Peer Selection do?
Helps you decide who to spend time with, using the five-chimpanzees idea that your behavior follows the five people you see most. The skill takes an idea from Naval Ravikant's almanack: you can predict a person from the five people they spend the most time with, so friends and partners should be chosen on purpose, not because they live nearby or share an office. Three principles apply: choose actively by values, set the mix by context (more successful people at work, happier ones for leisure), and keep away from cynical, pessimistic or conflict-prone people.
When should I use Peer Selection?
Peer Selection fits situations like: deciding whether to distance yourself from a draining friend; building a new social circle after moving city or changing jobs; choosing a partner by checking for shared values; wanting to meet more successful or more upbeat people.
How do I install Peer Selection in Claude Code?
Run `npx skills add kangarooking/cangjie-skill --skill peer-selection -a claude-code`. Or copy the skill folder (books/naval-almanack-skill/peer-selection in kangarooking/cangjie-skill) into .claude/skills/peer-selection in your project. Claude Code loads it when a task matches its description.
How do I install Peer Selection in Codex?
Run `npx skills add kangarooking/cangjie-skill --skill peer-selection -a codex`. Or copy the skill folder (books/naval-almanack-skill/peer-selection in kangarooking/cangjie-skill) into .agents/skills/peer-selection in your project. Codex loads it when a task matches its description.
Can I use Peer Selection 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 peer-selection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/peer-selection, .gemini/skills/peer-selection, .github/skills/peer-selection and .opencode/skills/peer-selection in your project.
What does Peer Selection need to run?
SKILL.md names no scripts, command-line tools or credentials: Peer Selection is instructions for the agent only.
Does Peer Selection 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 Peer Selection 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 Peer Selection use?
Peer Selection 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 Peer Selection use?
About 666 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 Peer Selection?
Skills that share tags, products or a category with Peer Selection: Agent Browser CLI (vercel-labs/agent-browser, 44k stars), Agent Browser (quran/quran.com-frontend-next, 1.9k stars), Web Access via Browser CDP (eze-is/web-access, 9.1k stars) and Process Inbox (telegramdesktop/tdesktop, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Peer Selection?
kangarooking (a GitHub user) maintains it in kangarooking/cangjie-skill, which has 10,988 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.