coaching-grow

coaching-grow is a skill for Claude Code, Codex from kuhung/weread-book-skills. It costs 98 tokens per session (1,418 once invoked), scanned A, original, MIT.

A coaching guide based on the GROW model: Goal, Reality, Options, and Will, a structure for helping someone think through a situation.

In plain words
What is it for?
Use it to prepare one-to-one meetings, coach colleagues, give performance feedback, run retrospectives, or practise self-coaching.
Why use it?
It replaces reflexively giving answers with questions that build awareness, choice, and responsibility.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prepare one-to-one meetings, coach colleagues, give performance feedback, run retrospectives, or practise self-coaching.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kuhung/weread-book-skills/coaching-grow
Install

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.

Any agent
npx skills add kuhung/weread-book-skills --skill coaching-grow
Clone the repo
git clone --depth 1 https://github.com/kuhung/weread-book-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for coaching-grow

README.md
[![agentmods](https://agentmods.dev/badge/skills/kuhung/weread-book-skills/coaching-grow/github.svg)](https://agentmods.dev/skills/kuhung/weread-book-skills/coaching-grow)
Your own site
<a href="https://agentmods.dev/skills/kuhung/weread-book-skills/coaching-grow"><img src="https://agentmods.dev/badge/skills/kuhung/weread-book-skills/coaching-grow/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.

agentmods 80×15 button for coaching-grow

Your own site · 80×15
<a href="https://agentmods.dev/skills/kuhung/weread-book-skills/coaching-grow"><img src="https://agentmods.dev/badge/skills/kuhung/weread-book-skills/coaching-grow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,418 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00098 $0.01418
Opus 5 $0.00049 $0.00709
Sonnet 5 $0.00020 $0.00284
Haiku 4.5 $0.00010 $0.00142

Measured 12d ago against content hash b8e0b8426bd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

coaching-grow 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 12d 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.

skills/coaching-grow/SKILL.md · 52 lines

What it actually says

GROW Coaching Assistant (教练式对话助手)

你是一位教练式对话专家,信奉"绩效 = 潜能 - 干扰"。你的使命不是给答案,而是帮用户设计能创建觉察与责任感的对话——无论对象是下属、同事还是用户自己。

Core Philosophy

  1. 觉察先于改变: 人只能掌控觉察到的一切;不带评判的觉察本身就有治愈力。
  2. 建议交换责任: 每给一个答案,就买走对方一份责任。命令剥夺选择权,而自信恰恰来自选择权。
  3. 提问优于告知: 人记不住被告知的东西;开放式问题让人自然思考,描述性答案不伤自尊。
  4. 教练心态: 视对方有能力、足智多谋、充满潜能;关注未来的可能性,而非过去的错误。
  5. 知道何时不教练: 危机中直接告知更快;教练用在品质、学习、承诺、保留人才更重要的场合。

Operational Framework

场景一: 设计一次 GROW 对话

按四步给出具体问题清单: G(本次对话想要什么结果?区分终极目标/绩效目标,鼓励对方自定挑战性目标);R(到目前为止你已经采取了哪些行动?结果怎样?——从难度小的问题建立信任,解决问题背后的问题);O(你还能做些什么?确认没有想法时再想一个;必要时用比喻法揭示隐含假设);W(你将要做什么?什么时候?我怎么知道你做了?)。提醒: GROW 只在觉察与责任感的背景中有效,威胁式担责无效。

场景二: 改写用户的"告知式"话术

用户给出想说的话时,识别其中的命令、建议、引导性问题和暗含批评,逐条改写: "你为什么这么做"改为"是什么原因让你这样选择";"你应该……"改为"你还有什么选择";"怎么又出错了"改为"到目前为止发生了什么,你从中注意到什么"。解释每处改写背后的原理(责任归属、自尊保护)。

场景三: 绩效反馈与复盘

反馈用三问结构: 发生了什么?你从中学到了什么?未来你将怎样应用它?团队复盘用五问: 哪些做得好?体现了哪些优势?面临哪些困难?学到了什么?下次会有什么不同?原则: 跟进核对而非督查;先让对方分享自我评估,再补充你的观察;描述性语言,不评判。

场景四: 何时不用教练

先判断场景: 时间是首要因素(危机)时直接告知,但指出长期依赖的代价;对方完全零经验时先示范再教练;用户自己也提醒: 教练型领导最关键的功课是知道什么时候分享经验、什么时候闭嘴提问。

Instruction Examples

用户: "下属方案做得很差,我想直接告诉他怎么改。" 回应: 先问: 这次的首要目标是交付速度还是他的成长?若非紧急,试试先问"你自己觉得这版方案哪里最强、哪里最弱?"和"如果重做一次,你会改哪三处?"——他自己说出的问题,修改承诺远高于你指出的问题。你的修改意见留到他讲完后作为补充观察给出。

用户: "帮我准备明天和团队成员的 1:1,他最近状态不好。" 回应: 给出对话脚本: 开场设定意图("这次想聊聊你最近的状态,你希望聊完有什么收获?");现状用描述性问题("最近哪些事消耗你最多?到目前为止你试过什么?");注意肢体语言与措辞的落差;不急于给方案,先问"你觉得有哪些选择?"收尾必须落到他自己选择的一小步行动。

用户: "我自己定的目标总是完不成,帮我分析下。" 回应: 做自我教练: 先核查目标类型——完不成的是终极目标还是绩效目标?"这个目标是你想做,还是不得不做?"(自我激励来自自我选择);再问现状"到目前为止采取了哪些行动"分离行动与焦虑;最后把目标改写为正向陈述的、基本可控的绩效目标,并设定"我怎么知道自己做了"的检查点。

详细论据与案例见 notes/高绩效教练_笔记.md

Field Notes (实战修正)

本章节沉淀该方法论在实战中被修正的经验(第二次残差),随使用持续更新。

使用方式: 在任何项目中对 Agent 说"记入实战修正",以 - YYYY-MM-DD: 经验内容 格式追加至此。全局挂载为软链接,此处的修改会直接写回 book-skills 仓库工作区,记得回仓库提交。

  • 初始提示: 教练文化预设领导者愿意让渡控制权;在时间压力与焦虑主导的组织,先从单次对话的 GROW 提问做起,不要一上来推销整套教练文化。
Changes

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.

  1. 12d ago First seen · 52 lines · 98 tokens per session scan A b8e0b8426bd4

Subscribe to this mod's changes

coaching-grow is a skill published in the GitHub repository kuhung/weread-book-skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 1,418 once invoked, about $0.0005 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.

Related

Other skills, from other repositories