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 skills add muyuhill/100books-to-skills --skill influencegit clone --depth 1 https://github.com/muyuhill/100books-to-skillsWrote 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/muyuhill/100books-to-skills/influence)<a href="https://agentmods.dev/skills/muyuhill/100books-to-skills/influence"><img src="https://agentmods.dev/badge/skills/muyuhill/100books-to-skills/influence/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.
<a href="https://agentmods.dev/skills/muyuhill/100books-to-skills/influence"><img src="https://agentmods.dev/badge/skills/muyuhill/100books-to-skills/influence.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00048 | $0.03676 |
| Opus 5 | $0.00024 | $0.01838 |
| Sonnet 5 | $0.00010 | $0.00735 |
| Haiku 4.5 | $0.00005 | $0.00368 |
Grade A, and why
影响力-influence 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
《影响力》— 六大说服原则,让你不再被人牵着走
"影响力的武器"——有些固定的行为模式一旦被触发,人们就会不假思索地照做。西奥迪尼称之为"咔嗒,哗"(click, run):就像磁带按下播放键,自动走完一整段程序。
全书核心论点
人类生活在信息过载的世界中,不可能对每一个决策都深思熟虑。于是大脑进化出了"捷径"——少数关键线索触发自动反应。这套机制在多数时候高效且正确,但也被"顺从专家"(compliance professionals)系统性地利用。六大原则就是这六条最常被触发的自动反应通道。
框架一:互惠 Reciprocity
- 一句话:别人给了你什么,你会想还回去——哪怕你不想要那个东西,哪怕你不喜欢那个人。
- 触发机制:先给予(免费样品、让步、小恩惠、人情)→对方产生亏欠感→不等你开口,对方就想回报你→更容易答应你的请求。关键:亏欠感让人不舒服,还债是消除不适最快的方式。
- 经典实验:1985年埃塞俄比亚饥荒,墨西哥在该国最困难时向埃塞俄比亚捐助了5000美元——因为1935年埃塞俄比亚曾在意大利入侵时援助过墨西哥。跨越50年的互惠债。
- 进阶应用——拒绝-退让策略(Door-in-the-Face):先提一个对方几乎肯定会拒绝的大要求→被拒绝后再退到一个小要求(你真正想要的)→对方在退让中感受到"互惠的让步"→更可能同意小要求。这个策略比直接提小要求的成功率高出3倍。
- 防御方法:识别对方最初的给予是真诚的礼物还是操纵策略。如果是后者,心理上将其重新定义为"销售手段"而非"恩惠"——你就不欠对方任何东西。互惠原则说"善意回报善意",但操纵不配得到回报。
- 应用场景:免费试用(SaaS行业标配)、超市试吃、先给用户提供有价值的免费内容再推销付费产品、"买一送一"让你觉得占了便宜所以必须买。
框架二:承诺一致 Commitment & Consistency
- 一句话:人一旦做了选择或表明立场,就会遭遇来自内心和环境的双重压力,迫使我们言行一致。
- 触发机制:让对方先做一个小承诺(写下来、说出来、公开表态)→后续行为会自动跟这个小承诺对齐→因为不一致会带来认知失调(cognitive dissonance)的痛苦。一旦书面或口头承诺过,改变立场的心理成本急剧升高。
- 经典实验:研究者假装调查员请居民在院子里立一块写有"小心驾驶"的大广告牌。直接请求时只有17%同意;但如果两周前先请对方签了一份"保持加州美丽"的请愿书(几乎100%都签了),再请求立广告牌时同意率飙升到76%。
- 关键要素:承诺必须是主动的、公开的、付出努力的、发自内心的才会产生最强的一致压力。被强迫的承诺无效。
- 进阶陷阱——低球策略(Low-Ball):先给一个诱人的价格让对方做出购买决定,在决定做出后、实际成交前悄悄取消优惠条件。因为承诺已经形成,多数人仍然会买。
- 防御方法:当直觉告诉你"这事不对"时,问自己一个关键问题——「如果回到当初,什么都不知道的时候,我还会做同样的选择吗?」如果答案是否定的,就果断退出。不要因为"已经承诺了"而继续往坑里跳。
- 应用场景:让客户先填一个小问卷→再推销产品;销售请客户自己动手填写合同或勾选选项;健身打卡群利用公开承诺机制;众筹项目先让用户投1元→后续追加金额的概率大幅提升。
框架三:社会认同 Social Proof
- 一句话:不知道怎么做时,看别人怎么做——特别是看"跟我们相似的人"怎么做。
- 触发机制:展示「大家都在用/买/做」→降低决策焦虑→跟随行为。在不确定、模糊、或紧急情境下,社会认同的效力达到峰值——因为我们没有时间去独立判断,只能把别人的行为当作正确的替代信号。
- 经典案例:电视台播放的罐头笑声(canned laughter)——即使观众知道那是假的,研究仍然显示人们在有罐头笑声时会笑得更多、持续时间更长,尤其是在笑话本身质量不高时。另一种典型:夜总会门口的排队,制造"这里很火"的假象。
- 关键变量——相似性(Similarity):我们更容易模仿与自己相似的人。这也是为什么广告喜欢用"普通人"而非名人来展示效果。"他跟我一样,他能做到,我也能。"
- 冷知识——多元无知(Pluralistic Ignorance):在人多的公共场合,大家都看着别人没反应,结果每个人都以为"别人知道情况而我不知道",于是都不采取行动——这就是为什么街头暴力发生时围观者越多、出手相助的人越少的真正原因。
- 防御方法:警惕人为制造的"虚假社会证据";问自己「这些人的行为和判断,在当下这个特定情境下,真的是基于更多、更好的信息吗?」如果只是随大流——从众行为本身不构成正确性的证据。
- 应用场景:用户评价/评分系统、销量数据展示、「x万人已订阅」的实时计数器、电商页面「同时有x人在浏览」、餐厅门口故意排队制造稀缺和社会认同的双重效应、B2B案例中的"标杆客户墙"。
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.
- 12d ago First seen · 110 lines · 48 tokens per session scan A a56983a1ef11
影响力-influence is a skill published in the GitHub repository muyuhill/100books-to-skills (12 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 3,676 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…