Not in the top 1,000 by GitHub stars
Grruuu/ai-future-is-now-skill
把李开复《AI未来已来》蒸馏成 18 个可直接调用的 AI Skill：AI 转型诊断、组织重塑与个人定位
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
agent-four-components/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
agent-level-ladder/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
ai-decision-core/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
ai-solution-two-laws/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
boss-ai-engines/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
commitment-ledger/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
data-flywheel/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
dri-identify-empower/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
earnings-call-test/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
four-faces-of-judgment/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
headcount-to-compute/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
living-ontology/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
ruler-before-ranking/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
sediment-before-flatten/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
skill/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
tech-shock-four-crushes/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
token-cheap-system-valuable/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
transformation-failure-diagnosis/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
work-quadrant-compass/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → ef2f98533133
No earlier version was observed for comparison.
Verified commit ef2f98533133218e103f22c19004f4112ff9c8fd
git clone --filter=blob:none --no-checkout https://github.com/Grruuu/ai-future-is-now-skill.git .hotskills/grruuu-ai-future-is-now-skill && git -C .hotskills/grruuu-ai-future-is-now-skill checkout --detach ef2f98533133218e103f22c19004f4112ff9c8fd
# Copy each selected skill directory from .hotskills/grruuu-ai-future-is-now-skill into .agents/skills/<skill-name>/Heat
Insufficient historyNot enough history yet to measure heat. It appears after a few days of data.
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- agent-four-components
agent-four-components - agent-level-ladder
agent-level-ladder - ai-decision-core
ai-decision-core - ai-solution-two-laws
ai-solution-two-laws - boss-ai-engines
boss-ai-engines - commitment-ledger
commitment-ledger - data-flywheel
data-flywheel - dri-identify-empower
dri-identify-empower - earnings-call-test
earnings-call-test - four-faces-of-judgment
four-faces-of-judgment - headcount-to-compute
headcount-to-compute - living-ontology
living-ontology - ruler-before-ranking
ruler-before-ranking - sediment-before-flatten
sediment-before-flatten - ai-future-is-now
skill - tech-shock-four-crushes
tech-shock-four-crushes - token-cheap-system-valuable
token-cheap-system-valuable - transformation-failure-diagnosis
transformation-failure-diagnosis - work-quadrant-compass
work-quadrant-compass
How it works
agent-four-components
When your agent uses it
当一个 AI 工具/助手"看起来很聪明，却不好使"时，按「模型 + 工具 + 记忆 + 知识」四个组件定位缺口，而不是先怪模型不够强。 何时调用：用户已经在用某个 AI 系统但结果不对劲，说出"它答得很流畅但全是错的""每次都要我从头解释一遍""它引用的是三年前的旧模板""它给的建议听着专业但落不了地""是不是该换个更强的模型"之类的话时；或在诊断企业内部 AI 助手为何没人用时。 何时不调用：用户还在选型采购、想判断产品等级（那是 agent-level-ladder）；或问题明显是提示词写法、模型跑分比较、纯信息查询。 也不要用它诊断数据质量本身——它定位的是组件缺口，不是数据脏不脏。
What it loads into context
Frontmatter
335 tokensAlways available to the agent
SKILL.md
3,097 tokensWhen the skill is activated
Reference documents
6,920 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
SKILL.mdcore11,312 bytestest-prompts.jsonasset3,185 bytes../agent-level-ladder/SKILL.mddoc10,914 bytes../living-ontology/SKILL.mddoc14,480 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubagent-level-ladder
When your agent uses it
判断一个 AI 产品/工具/方案真正处在「聊天机器人—工具型—副驾驶—智能体」四级阶梯的哪一级。 何时调用：用户在评估、选型、采购或试用某个 AI 工具，说出"这个 agent 值不值这个价""供应商说他们是 agentic 的""我们要不要上智能体""这东西到底算不算真 AI 员工""为什么每一步都还要我确认"之类的话时；或用户在做 AI 战略布局、要盘点手里已有工具的真实等级时。 何时不调用：用户只是想优化提示词、让某个模型输出更稳定、比较两个模型的benchmark分数、或询问某个 AI 产品的价格与功能列表——那些是用法优化和信息查询，不是分级判断。 也不要在用户已经明确知道等级、只想解决"为什么不好使"时调用（那是 agent-four-components）。
What it loads into context
Frontmatter
302 tokensAlways available to the agent
SKILL.md
2,968 tokensWhen the skill is activated
Reference documents
3,097 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../agent-four-components/SKILL.mddoc11,312 bytesSKILL.mdcore10,914 bytestest-prompts.jsonasset3,199 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubai-decision-core
When your agent uses it
当用户已经买了模型、接了数据、上了几个智能体，系统却"上不了生产""部署完就没下文""不好使"时，用四块拼图——大脑（模型）、地图（本体）、导航（企业实时上下文）、手脚（操作系统）——做缺口定位，判断闭环断在哪一节。语言信号："AI 答得挺像回事，但和我们实际情况对不上""它只会讲规则，不知道现在是什么状态""换了更强的模型也没用""它给了建议却没法真动手"。不适用于：单条 prompt 调优；也不处理"地图这块具体怎么建、谁来建"（→ living-ontology）与"长期护城河怎么构建"（→ data-flywheel）。本 skill 只回答"缺哪一块"，不回答"这块怎么建"。
What it loads into context
Frontmatter
318 tokensAlways available to the agent
SKILL.md
5,104 tokensWhen the skill is activated
Reference documents
7,790 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
SKILL.mdcore18,247 bytestest-prompts.jsonasset3,195 bytes../data-flywheel/SKILL.mddoc14,003 bytes../living-ontology/SKILL.mddoc14,480 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubai-solution-two-laws
When your agent uses it
用两条铁律和一句提问，判断一个 AI 方案 / 供应商 / 自研路线的**能力天花板**，并预测 AI 会在哪个业务环节先爆发。 何时调用：用户在比较几家 AI 供应商或几条技术路线；在问"这个方案靠不靠谱""效果能不能持续变好""要不要买这个行业知识库/规则引擎"； 在犹豫"自研还是采购""上规则引擎还是上模型"；在问"AI 会先在我们哪个环节落地/爆发"； 或已经上线一段时间、效果曲线趋平，怀疑是不是路线本身有上限。 关键语言信号："这个 AI 方案值不值""供应商说他们沉淀了多年行业专家知识""要不要自己训一个""效果三个月后就不涨了""AI 在我们这行会先做什么""我们的数据能不能形成壁垒"。 不适用于：判断整个行业会不会被颠覆、要不要现在动手（用 tech-shock-four-crushes）；判断手里工具是第几级、要不要按智能体价格买（用 agent-level-ladder）；诊断已上线工具为什么"看起来聪明却不好使"（用 agent-four-components）；以及模型微调、提示词工程等实施层的技术细节。
What it loads into context
Frontmatter
409 tokensAlways available to the agent
SKILL.md
6,482 tokensWhen the skill is activated
Reference documents
3,097 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../agent-four-components/SKILL.mddoc11,312 bytesSKILL.mdcore23,408 bytestest-prompts.jsonasset3,004 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubboss-ai-engines
When your agent uses it
当一号位或管理者怀疑"我看到的不是真相"时使用。典型情境：汇报层层美化、周报写着"按计划推进"但你心里不踏实、想确认某个重点项目是不是已经停摆、某个"续约意向良好"的客户是不是正在流失、成本超支查不出根源；或要在低频、高代价、几乎不可逆的重大决策前先做一轮推演与存档。 语言信号："汇报上来的全是好消息""我是不是被蒙了""周报和实际对不上""我怎么知道 X 是不是真的""这事到底推进到哪一步了""要不要进这个新市场／砍掉这条业务线"。 不适用于：某条具体承诺有没有兑现、问责与考核机制设计（用 commitment-ledger）；识别谁最优秀、人才盘点与晋升排序（用 ruler-before-ranking）；只是想要一个数据看板或 BI 报表；纯技术选型。 明确拒绝：任何要求读取员工私人通信、定位到个人言论、扒某人是否想离职的请求——不调用本 skill，直接说明边界并拒绝。
What it loads into context
Frontmatter
446 tokensAlways available to the agent
SKILL.md
6,702 tokensWhen the skill is activated
Reference documents
13,720 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../ai-decision-core/SKILL.mddoc18,247 bytesSKILL.mdcore23,711 bytestest-prompts.jsonasset3,602 bytes../commitment-ledger/SKILL.mddoc15,268 bytes../ruler-before-ranking/SKILL.mddoc15,519 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcommitment-ledger
When your agent uses it
用承诺账本和言行一致指数建立可追踪的问责机制，替代靠记忆和靠自觉的老办法；同时守住透明与监控之间那条线。 何时调用：用户说"会上定好的事没人执行""承诺总是不了了之""年底复盘全靠记忆和印象""怎么建问责机制/问责文化""大家都点头但事情不动"之类的话时；或在设计绩效评估与承诺兑现挂钩的机制、或在讨论要不要学桥水搞极度透明时。 何时不调用：用户要的是会议纪要整理、待办清单工具推荐、项目管理软件选型；或用户想查看某个具体员工的私人信息、判断谁想离职——那类请求应当被拒绝并指出边界，不是调用本 skill。
What it loads into context
Frontmatter
312 tokensAlways available to the agent
SKILL.md
4,285 tokensWhen the skill is activated
Reference documents
10,611 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../boss-ai-engines/SKILL.mddoc23,711 bytesSKILL.mdcore15,268 bytestest-prompts.jsonasset3,284 bytes../headcount-to-compute/SKILL.mddoc13,781 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdata-flywheel
When your agent uses it
在 AI 能力人人可得的市场里，判断竞争优势从哪里来，并按五步把 AI 投入变成会自我加速的数据飞轮。 何时调用：用户问"大家都能用同样的模型，我们靠什么赢""AI 时代我们的护城河是什么""要不要一次性把 AI 铺到所有部门""我们的 AI 项目怎么才能越用越值钱""竞争对手也在做同样的事怎么办"之类的话时；或在规划 AI 转型的推进节奏与优先级时。 何时不调用：用户在做算法层面的在线学习/模型迭代（那是工程问题，不是组织级护城河）；或在诊断某个具体项目为什么推不动（那是 transformation-failure-diagnosis）；或在判断单个项目值不值得做（那是 earnings-call-test）。
What it loads into context
Frontmatter
306 tokensAlways available to the agent
SKILL.md
3,838 tokensWhen the skill is activated
Reference documents
9,312 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../ai-decision-core/SKILL.mddoc18,247 bytesSKILL.mdcore14,003 bytestest-prompts.jsonasset3,063 bytes../sediment-before-flatten/SKILL.mddoc14,761 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdri-identify-empower
When your agent uses it
用于组织授权与人选识别。当一件事人人沾边却找不到扛到底的人、或 AI 工具铺开后要判断谁能独立带一支智能体队伍时使用。 产出：DRI 四能力核对、业务场景测试方案、四类人（建造者/待辅导者/不可替代的专家/不合格的服从者）差异化处置、防散沙的三道保险。 语言信号：「出了事找不到一个真正负责的人」「想设端到端 owner 但不知道选谁」「谁适合带智能体/AI 团队」「层级太多，想改成微型 CEO」「AI 发下去了，怎么看出谁真的在用」。 不适用于：常规 OKR 与目标设定、绩效打分、招聘 JD 撰写、判断某个 AI 项目值不值得做、单纯搭建承诺跟踪机制、已决定裁员只差沟通方案。 硬前提：若一号位不打算真正下放决策权，本 skill 只给停止建议，不给选人方案。
What it loads into context
Frontmatter
384 tokensAlways available to the agent
SKILL.md
6,673 tokensWhen the skill is activated
Reference documents
12,448 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
SKILL.mdcore23,875 bytestest-prompts.jsonasset2,837 bytes../headcount-to-compute/SKILL.mddoc13,781 bytes../ruler-before-ranking/SKILL.mddoc15,519 bytes../sediment-before-flatten/SKILL.mddoc14,761 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubearnings-call-test
When your agent uses it
把一个或一批 AI 项目放到"季度财报电话会"这把标尺下判真假，分成投入指标 / 化妆 / 真实改善三档。 调用于：AI 项目要不要继续投或立项、如何向老板与董事会证明价值；用"效率提升 X%""使用率高" "部署了多少智能体""员工反馈好"论证价值；给一批项目排序、砍掉伪项目；用"战略性投入""在打基础" 解释说不清的回报。信号词：值不值、怎么衡量 AI 的价值、效率提升 40%、覆盖了几个部门、 这钱花得值不值、该砍哪个项目。 不调用：整理财报电话会纪要等文档处理；财务建模与报价比价；项目推不动、有人阻挠的归因 （→ transformation-failure-diagnosis）；AI 工具答不准的技术诊断（→ agent-four-components）； 预算怎么分配（→ token-cheap-system-valuable）。研发型组织、公益与政府机构、财报周期长于 技术迭代周期的行业须降级使用并替换标尺。
What it loads into context
Frontmatter
420 tokensAlways available to the agent
SKILL.md
5,995 tokensWhen the skill is activated
Reference documents
10,091 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
SKILL.mdcore21,794 bytestest-prompts.jsonasset3,276 bytes../tech-shock-four-crushes/SKILL.mddoc21,061 bytes../transformation-failure-diagnosis/SKILL.mddoc14,629 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfour-faces-of-judgment
When your agent uses it
面对一个重大决定时，先分清它考验的是哪一种判断——品味（什么是好的）、远见（什么会到来）、信念（什么是对的）、勇气（该担什么风险）——不同面孔对应完全不同的动作。 何时调用：用户面对一个高代价、低频、难以逆转的决定，说出"我知道数据不够但我就是觉得该做""所有人都不看好这件事""我该不该赌一把""要不要砍掉这条业务线""我是不是在固执"之类的话时；或在复盘一个重大决策、判断当初为什么对/错时。 何时不调用：日常琐碎选择（晚饭吃什么）；有标准答案的分析题（哪个方案净现值高、这段代码怎么写）——那些恰恰是作者划归机器的左脑工作；纯信息查询。 涉及个人财务、健康、家庭安全的不可逆重大损失时，必须同时给出边界警告，不能只做分流。
What it loads into context
Frontmatter
350 tokensAlways available to the agent
SKILL.md
5,370 tokensWhen the skill is activated
Reference documents
4,434 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
SKILL.mdcore18,969 bytestest-prompts.jsonasset3,683 bytes../work-quadrant-compass/SKILL.mddoc16,014 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubheadcount-to-compute
When your agent uses it
把组织的计价单位从人头换成算力——算力单列成本科目并算 ROI、薪酬按业务重要性而非下属人数、董事会看三个新指标。 何时调用：用户说"人数在降但算力账单在涨，董事会问这钱值不值""一个没有下属的人凭什么拿得比经理多""扩招还是加算力""AI 时代的组织该怎么考核""怎么向董事会解释这笔支出"之类的话时；或在设计 DRI 组织的薪酬与考核体系时。 何时不调用：用户要的是一次性成本核算或云账单分析（那是财务分析）；或在做整体 AI 预算的结构调整（那是 token-cheap-system-valuable）；或还没有 DRI 组织、只是想优化现有薪酬。
What it loads into context
Frontmatter
309 tokensAlways available to the agent
SKILL.md
3,909 tokensWhen the skill is activated
Reference documents
10,436 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../dri-identify-empower/SKILL.mddoc23,875 bytesSKILL.mdcore13,781 bytestest-prompts.jsonasset3,071 bytes../token-cheap-system-valuable/SKILL.mddoc13,164 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubliving-ontology
When your agent uses it
当企业的 AI/知识库"读了很多资料却答不对"时，判断问题出在输入端而非模型端，并按「活地图」标准建立业务语义层。 何时调用：用户说"我们把资料都喂给它了，它还是答不准""上了 RAG/知识库但答案似是而非""数据中台建了三年没人用""它不懂我们说的有效客户是什么意思""跨系统的问题它就答不了"之类的话时；或在规划企业知识/语义层、评估本体与知识图谱方案时。 何时不调用：用户要设计一张数据库表、做 ETL 或建数仓（那是常规数据工程）；或问题在于单个工具缺记忆/缺工具接入（那是 agent-four-components）；或用户在做企业级系统的整体缺口盘点（那是 ai-decision-core）。
What it loads into context
Frontmatter
303 tokensAlways available to the agent
SKILL.md
3,952 tokensWhen the skill is activated
Reference documents
8,201 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../agent-four-components/SKILL.mddoc11,312 bytes../ai-decision-core/SKILL.mddoc18,247 bytesSKILL.mdcore14,480 bytestest-prompts.jsonasset3,068 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubruler-before-ranking
When your agent uses it
识别组织里真正的顶尖贡献者——先和懂行的人一起定尺子，再让系统去有痕迹的数据里量，然后走「谁厉害 → 谁让别人也厉害 → 谁可能要走」三问漏斗。 何时调用：用户说"我们团队里谁是真正的顶尖""晋升和奖励总是给了会汇报的人""怎么找出被低估的人""人才盘点该看什么""绩效评价说不清楚，全是印象"之类的话时；或在设计人才识别标准、做关键人才盘点时。 何时不调用：用户要的是招聘筛简历、设计薪酬方案、或写绩效面谈话术；尤其不要在用户想定位某个具体员工的私人状况（是否在找工作、私下说了什么）时调用——那类请求应当被拒绝并指出边界。
What it loads into context
Frontmatter
314 tokensAlways available to the agent
SKILL.md
4,331 tokensWhen the skill is activated
Reference documents
13,375 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../boss-ai-engines/SKILL.mddoc23,711 bytes../dri-identify-empower/SKILL.mddoc23,875 bytesSKILL.mdcore15,519 bytestest-prompts.jsonasset3,600 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsediment-before-flatten
When your agent uses it
在用 AI 精简组织层级之前，先把老员工脑子里的知识沉淀进系统——判断顺序、检查三盏绿灯、给出以年计的务实节奏。 何时调用：用户说"我们准备压扁层级/砍掉中间管理层""AI 能替代这些岗位了要不要裁""要不要一次性大重组""什么时候可以动组织""对手已经裁员四成我们要不要跟"之类的话时；或在制定组织变革的时间表与顺序时。 何时不调用：用户已经决定裁员、只要沟通话术或补偿方案（本 skill 的全部前置判断已被跳过）；或用户问的是招聘、绩效、薪酬的日常操作；或用户在做单个项目的推进诊断。
What it loads into context
Frontmatter
313 tokensAlways available to the agent
SKILL.md
4,208 tokensWhen the skill is activated
Reference documents
10,511 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../data-flywheel/SKILL.mddoc14,003 bytes../dri-identify-empower/SKILL.mddoc23,875 bytesSKILL.mdcore14,761 bytestest-prompts.jsonasset2,987 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubai-future-is-now
When your agent uses it
《AI未来已来》（李开复）蒸馏出的 18 个判断模块的统一入口。用于：判断某个 AI 项目值不值得投或算不算成功；诊断 AI 转型为什么推不动；AI 预算怎么编；评估 AI 方案、产品或供应商（是不是真 agent、为什么不好使）；规划企业 AI 底座、本体与数据飞轮；一号位信息穿透、承诺问责、人才识别；DRI 组织重塑、扁平化顺序、算力计价与薪酬；个人职业定位（会不会被 AI 取代、往哪转）；以及面对高代价、不可逆的重大决断（品味／远见／信念／勇气的分流）。不用于：纯信息查询、写提示词、常规数据工程、日常琐碎选择、以及定位某个员工的私人状况（应拒绝）。
What it loads into context
Frontmatter
300 tokensAlways available to the agent
SKILL.md
2,601 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 怎么用
- 分流表
- 三条全局边界（任何模块都适用，执行前先读）
- ⚠<U+FE0F> 涉及员工数据的三个模块
- 延伸材料（同一仓库内）
Files
SKILL.mdcore8,677 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtech-shock-four-crushes
When your agent uses it
给一项技术变革定量级，并把宏观判断落成企业内部的第一张靶纸。 何时调用：用户在问"AI（或某项新技术）会不会颠覆我们这行""要不要现在就投""能不能再观望一年""这次和以前的技术浪潮到底有什么不一样"； 在做多年期战略、预算、人力规划时需要先给技术冲击定级； 或已经决定要转型、却不知道该从哪些岗位、哪些成本、哪条收入曲线下手。 关键语言信号："会不会被颠覆""要不要现在动手""再等等看""明年再说""这次不一样吗""按年规划还是按季规划""不知道从哪儿开始"。 不适用于：评估某个具体 AI 方案或供应商的能力天花板（用 ai-solution-two-laws）；判断手里的工具属于第几级（用 agent-level-ladder）；诊断已上线的 AI 工具为什么不好使（用 agent-four-components）；判断单个项目该不该继续投钱（用 earnings-call-test）；以及纯粹的技术原理科普。
What it loads into context
Frontmatter
365 tokensAlways available to the agent
SKILL.md
5,994 tokensWhen the skill is activated
Reference documents
5,995 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../earnings-call-test/SKILL.mddoc21,794 bytesSKILL.mdcore21,061 bytestest-prompts.jsonasset3,681 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtoken-cheap-system-valuable
When your agent uses it
在 AI 成本快速下降时，判断预算该怎么调、钱该花在哪里——核心结论是 Token 越便宜，围绕它搭建的那套系统就越值钱。 何时调用：用户在做 AI 预算规划、说出"模型降价了明年预算是不是可以砍""我们 AI 预算该怎么定""调用成本降了这么多为什么账单还在涨""要不要现在多买点 Token/算力""AI 投入的钱该花在哪"之类的话时；或在向 CFO/董事会解释 AI 支出结构时。 何时不调用：用户只是要一次具体报价计算（处理 N 份文档要多少钱）；或在比较两个模型/供应商的单价；或问的是某个模型的技术参数。 也不要用它做组织的算力计价与薪酬体系改造（那是 headcount-to-compute）。
What it loads into context
Frontmatter
309 tokensAlways available to the agent
SKILL.md
3,763 tokensWhen the skill is activated
Reference documents
9,013 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../ai-decision-core/SKILL.mddoc18,247 bytes../headcount-to-compute/SKILL.mddoc13,781 bytesSKILL.mdcore13,164 bytestest-prompts.jsonasset3,065 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtransformation-failure-diagnosis
When your agent uses it
当一个 AI 转型/数字化项目推了很久没有结果时，按「三错因果链」定位责任分配问题，并识别中层的口袋否决。 何时调用：用户说"我们 AI 搞了一年没什么成果""项目老是卡住""每次问都是数据不够干净/流程比想象中复杂""部门都说支持但就是推不动""该让谁来牵头这件事"之类的话时；或在复盘一个已经失败的转型项目、要找根因时。 何时不调用：项目刚启动还没有受阻迹象；用户问的是某个具体技术方案怎么选；用户已明确知道是责任分配问题、只想要授权方案（转 dri-identify-empower）。 也不要用它评估项目"值不值得做"——那是 earnings-call-test。
What it loads into context
Frontmatter
320 tokensAlways available to the agent
SKILL.md
4,097 tokensWhen the skill is activated
Reference documents
16,953 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../commitment-ledger/SKILL.mddoc15,268 bytes../dri-identify-empower/SKILL.mddoc23,875 bytes../earnings-call-test/SKILL.mddoc21,794 bytesSKILL.mdcore14,629 bytestest-prompts.jsonasset3,071 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwork-quadrant-compass
When your agent uses it
把一份具体工作定位到「内容自由度 × 人际互动依赖度」四象限里，判断它面对 AI 的真实处境，并给出三个方向的行动指引。 何时调用：用户问"我的工作会不会被 AI 取代""我该往哪个方向转""我们这个岗位还有多久""该给团队做什么培训才不白费""AI 时代什么工作安全"之类的话时；或在为自己或团队做职业定位、技能规划时。 何时不调用：纯信息查询（某职业薪资多少、行业前景数据）；具体求职操作（改简历、准备面试、写离职信）；或用户只是想了解某项 AI 技术能做什么。 用户处于强烈焦虑时，先给具体定位，不要泛泛安慰，也不要渲染淘汰。
What it loads into context
Frontmatter
292 tokensAlways available to the agent
SKILL.md
4,434 tokensWhen the skill is activated
Reference documents
5,370 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- R — 原文 (Reading)
- I — 方法论骨架 (Interpretation)
- A1 — 书中的应用 (Past Application)
- A2 — 触发场景 (Future Trigger) ★
- E — 可执行步骤 (Execution)
- B — 边界 (Boundary) ★
- 相关 skills (阶段 3 填充)
- 审计信息
Files
../four-faces-of-judgment/SKILL.mddoc18,969 bytesSKILL.mdcore16,014 bytestest-prompts.jsonasset3,569 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- agent-four-components
- agent-level-ladder
- ai-decision-core
- ai-solution-two-laws
- boss-ai-engines
- commitment-ledger
- data-flywheel
- dri-identify-empower
- earnings-call-test
- four-faces-of-judgment
- headcount-to-compute
- living-ontology
- ruler-before-ranking
- sediment-before-flatten
- ai-future-is-now
- tech-shock-four-crushes
- token-cheap-system-valuable
- transformation-failure-diagnosis
- work-quadrant-compass
Repository facts
- License
- No license detected
- Created
- Aug 5, 2026
- Last pushed
- Aug 5, 2026
- Forks
- 1
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 6, 2026
- No broad tool permissions
- No dangerous shell commands
- 3 network referencesin 1 file: skill/SKILL.md:8
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 3 signals by file
skill/SKILL.md
- Network accessline 8
modules: 18 generated_by: cangjie-skill (RIA-TV++) repo: https://github.com/Grruuu/ai-future-is-now-skill - Network accessline 9
generated_by: cangjie-skill (RIA-TV++) repo: https://github.com/Grruuu/ai-future-is-now-skill --- - Network accessline 10
repo: https://github.com/Grruuu/ai-future-is-now-skill
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 3 facts
- Network access in the frontmatter of the SKILL.mdskill/SKILL.md:8Low confidence
- Network access in the frontmatter of the SKILL.mdskill/SKILL.md:9Low confidence
- Network access in the frontmatter of the SKILL.mdskill/SKILL.md:10Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md agent-four-components/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md agent-four-components/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md agent-four-components/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md agent-four-components/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md agent-four-components/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
