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.
npx agentmods add skills/ace3000chao/book2startup/coaching-returnsnpx skills add ace3000chao/book2startup --skill coaching-returnsgit clone --depth 1 https://github.com/ace3000chao/book2startupWrote 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.
[](https://agentmods.dev/skills/ace3000chao/book2startup/coaching-returns)<a href="https://agentmods.dev/skills/ace3000chao/book2startup/coaching-returns"><img src="https://agentmods.dev/badge/skills/ace3000chao/book2startup/coaching-returns.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00140 | $0.02688 |
| Opus 5 | $0.00070 | $0.01344 |
| Sonnet 5 | $0.00028 | $0.00538 |
| Haiku 4.5 | $0.00014 | $0.00269 |
Grade A, and why
coaching-returns 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coaching Returns（一流人才需要教练）
R — 原文 (Reading)
"No one has ever achieved peak performance without a coach."
— Verne Harnish, Scaling Up, 第5章
I — 方法论骨架 (Interpretation)
Harnish的教练原则基于一个反直觉但普遍成立的洞察：越优秀的人越需要教练。
普通人需要教练来弥补短板；一流人才需要教练来突破盲点、维持巅峰状态、并有一个安全的反思空间。
为什么CEO/高管/顶尖人才特别需要教练？
- 信息真空：顶尖人才身边缺乏敢说真话的人——下属不敢挑战老板，同级竞争者不会给你真实反馈
- 认知盲点：一个人的优势往往也是他的盲点来源（乔布斯的暴躁创造了iPhone也差点毁了苹果）
- 巅峰状态的维持成本：维持高绩效需要定期reset，否则压力累积导致决策质量下降
- 外部视角：教练提供的是"组织内部看不到的视角"，这是内部反馈无法替代的
教练 vs 导师 vs 培训 vs 咨询：
| 角色 | 核心功能 | 典型场景 |
|---|---|---|
| 教练（Coach） | 激发潜能、行为改变 | 绩效突破、人际领导力 |
| 导师（Mentor） | 经验传承、职业导航 | 职业发展、角色转型 |
| 培训（Trainer） | 技能传授、知识转移 | 硬技能、标准化流程 |
| 咨询（Consultant） | 问题诊断、方案提供 | 战略设计、系统问题 |
教练的核心价值： 不给答案，而是用提问帮助你找到自己的答案——这与"给建议"完全不同。
A1 — 书中的应用 (Past Application)
案例 1: Michael Jordan 与 Phil Jackson
- 问题: Michael Jordan是公认的史上最佳球员，但禅师Phil Jackson仍然是他不可或缺的教练
- 方法论的使用: Phil Jackson的角色不是"教Jordan投篮"（没人能教他），而是：
- 维持团队化学反应的平衡（管理其他超级巨星的自尊）
- 在压力下提供心理框架（禅学、冥想式的心理调整）
- 在Jordan自我怀疑时给予确认
- 结论: 越顶尖的球员越需要教练——不是因为技术，而是因为心理和团队维度
- 结果: 公牛队两个三连冠王朝
案例 2: 某科技公司CTO的技术领导力转型
- 问题: 公司CTO技术能力顶级，但被提升为CTO后开始带团队，3个月内3个核心技术骨干离职
- 方法论的使用: CEO安排CTO接受外部高管教练（Executive Coach）
- 诊断：CTO习惯性"自己写代码更高效"——微观管理抑制了团队成长
- 教练介入：通过16周一对一教练，CTO从"技术执行者"转向"技术领导力"
- 关键转变：学会"通过他人完成技术工作"而非"自己完成技术工作"
- 结论: 顶级技术人才的成长需要教练帮助突破"能力陷阱"（因为擅长技术而被提升，但提升后的角色需要不同能力）
- 结果: 12个月后核心团队稳定，新产品上线速度提升2倍
案例 3: 某连锁企业CEO的"战略教练"
- 问题: CEO经营企业20年，业绩稳定但增长停滞，董事会认为CEO能力碰到天花板
- 方法论的使用: 引入"战略教练"（非咨询、非导师）：
- 每季度2次2小时一对一教练会话
- 教练不问"你打算怎么做"，而是问"你的假设是什么？竞争对手在这个局面下会怎么做？"
- 6个月后，CEO主动提出公司战略方向需要调整——这是他自己得出的结论，而非教练给的建议
- 结论: 教练的价值在于帮助CEO重新框架问题，而不是给出答案
- 结果: CEO在教练支持下制定了"B2B转型"战略，3年后营收增长4倍
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 一流人才成长停滞 — 某核心高管绩效优秀但突然没有进步，陷入"舒适区"
- CEO/创始人领导力瓶颈 — 企业到了一定规模创始人的管理能力出现瓶颈，但自己意识不到
- 高管团队协作问题 — 高管之间存在人际摩擦，但没有人愿意主动说破，需要第三方介入
- 引进外部人才的融合期 — 空降高管需要教练帮助快速融入，同时保护其不被内部政治过早消耗
- 重大决策前的独立声音 — CEO在做重大战略决策时身边全是"yes-man"，需要一个敢说"你的假设可能有问题的"人
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 177 lines · 140 tokens per session scan A 9f029108d8be
coaching-returns is a skill published in the GitHub repository ace3000chao/book2startup (75 stars, last pushed 4mo ago), licensed MIT. It adds 140 tokens to every session and 2,688 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
give-developmental-feedback
Use when a manager needs to deliver specific, in-the-moment developmental feedback to a direct report — separate from a formal performance review — to improve a behavior or reinforce a strength using observable evidence.
rep-performance-analyzer
Cross-rep metrics analysis with benchmarking and coaching priorities per rep.
interview-simulator
Simulate role-specific mock interviews, score each answer, and provide concrete feedback and model responses for interview preparation.
call-kpi-scoring
Use this skill after a sales call — coaching a rep, judging whether a call moved the deal forward, or producing a scorecard on how the conversation actually went — call scoring, call quality, call coaching, call KPIs, talk ratio, question rate, monologue length, engagement score. Different from a behavior-based…
instructional-coaching-conversation-guide
Generate a coaching conversation guide with questions, protocols, and follow-up actions for a teaching focus. Use when preparing for coaching sessions, mentoring, or peer feedback conversations.
apply-coaching-habit
Use when a manager wants to shift their default interaction style from advice-giving to question-asking — so that direct reports build self-sufficiency rather than dependence, and the manager's time is freed from problems the team can solve themselves.