Skip to content

zach22-1999/generic-skills / skills/zach-term-miner

zach-term-miner

Verified

术语挖掘:做一件事之前,先弄清楚这个领域里 AI 听得懂的专业术语,再用这些术语改写你的 prompt。 输入三句话(要做什么 / 已经知道什么 / 哪个领域),产出一个离线 HTML:5 个核验过来源的必要术语、 每个术语对应的「大白话 prompt → 术语版 prompt」前后对照、以及一条 30 分钟学习顺序。 用户说"术语挖掘""我要做 X,需要懂哪些术语才能跟你讲清楚""AI 总是理解偏""这个 prompt 怎么写得更专业" "帮我看看我该学什么术语"时使用。普通词义查询、已有完整 prompt 只想执行、或用户明确要求直接开始做原任务时不要触发。 本 skill 只出术语和 prompt 改写,不执行原任务;不编造术语和来源。

scripts/fixtures/non-ecommerce.json

View on GitHub
{
  "artifact_kind": "term_prompt_pack",
  "schema_version": 1,
  "artifact_id": "team-okr-quarter",
  "generated_at": "2026-09-07",
  "locale": "zh-CN",
  "title": "团队季度 OKR:用五个词让 AI 从待办清单升级成可衡量的目标体系",
  "summary": "你要给团队写下季度目标。OKR 定两层结构,SMART 逐条检查关键结果,领先与滞后指标保证季度中途能纠偏,承诺型与挑战型定完成标准,北极星指标做全局对齐。",
  "task": {
    "goal": "给一个 10 人团队写下季度目标,让每个人知道要做到什么程度",
    "known": "有三个方向的想法:客户续费、新客获取、团队方向感;没有写过正式目标文档",
    "domain": "团队管理与目标设定",
    "assumptions": [
      "团队所在公司已有年度方向,但没有明确的北极星指标",
      "目标周期为一个季度"
    ]
  },
  "terms": [
    {
      "id": "okr",
      "term": "OKR (Objectives and Key Results)",
      "chinese_name": "目标与关键结果",
      "definition": "目标(O)说清要去哪,关键结果(KR)用可衡量的结果说清怎么算到了;一个目标配 3–5 个关键结果。",
      "why_for_this_task": "AI 会把你的想法拆成定性的目标和可量化的关键结果两层,而不是写成一串待办事项。",
      "source_status": "verified",
      "sources": [
        {
          "title": "Measure What Matters",
          "kind": "book",
          "author": "John Doerr",
          "year": 2018
        },
        {
          "title": "High Output Management",
          "kind": "book",
          "author": "Andrew S. Grove",
          "year": 1983
        }
      ]
    },
    {
      "id": "smart",
      "term": "SMART",
      "chinese_name": "SMART 原则",
      "definition": "写目标的五个检查项:具体、可衡量、可分配或可达成、现实、有时限。",
      "why_for_this_task": "让 AI 逐条检查每个关键结果是否可衡量、有时限,把「提升用户满意度」改成「Q4 NPS 从 30 到 45」。",
      "source_status": "verified",
      "sources": [
        {
          "title": "There's a S.M.A.R.T. Way to Write Management's Goals and Objectives",
          "kind": "paper",
          "author": "George T. Doran",
          "year": 1981
        }
      ]
    },
    {
      "id": "leading-lagging",
      "term": "Leading vs Lagging Indicators",
      "chinese_name": "领先指标与滞后指标",
      "definition": "滞后指标是结果(如季度营收),领先指标是能提前预示结果、可以主动驱动的过程量(如周活跃客户拜访数)。",
      "why_for_this_task": "AI 会检查你的关键结果是不是全是滞后指标,并补上能在季度中途就看出偏差的领先指标。",
      "source_status": "verified",
      "sources": [
        {
          "title": "The Balanced Scorecard: Translating Strategy into Action",
          "kind": "book",
          "author": "Robert S. Kaplan, David P. Norton",
          "year": 1996
        }
      ]
    },
    {
      "id": "committed-aspirational",
      "term": "Committed vs Aspirational OKRs",
      "chinese_name": "承诺型与挑战型 OKR",
      "definition": "承诺型 OKR 必须 100% 完成,资源要保证;挑战型 OKR 允许只完成六七成,用来拉伸团队上限。",
      "why_for_this_task": "AI 会让你先给每个目标定性质,避免把所有目标都当承诺型,年底全部「未完成」打击士气。",
      "source_status": "verified",
      "sources": [
        {
          "title": "Google re:Work:Set goals with OKRs",
          "kind": "official",
          "author": "Google"
        }
      ]
    },
    {
      "id": "north-star",
      "term": "North Star Metric",
      "chinese_name": "北极星指标",
      "definition": "最能代表产品给用户交付核心价值的单一指标,全公司的目标都应能追溯到它。",
      "why_for_this_task": "AI 会先问你的北极星是什么,再检查每个团队 OKR 能不能连回去,防止各写各的。",
      "source_status": "source_defined",
      "sources": [
        {
          "title": "增长圈从业者提出并推广的概念,常见于 Sean Ellis 相关的增长方法论文章",
          "kind": "secondary",
          "author": "Sean Ellis"
        }
      ]
    }
  ],
  "prompt_rewrites": [
    {
      "id": "rw-okr-smart",
      "term_ids": [
        "okr",
        "smart"
      ],
      "plain_prompt": "我们团队下个季度想把客户续费做好,也想把新客户拉进来,还想让大家的工作更有方向感。请帮我把这些想法整理成一份季度目标文档,每个目标下面写清楚要做到什么程度、用什么数字衡量、什么时候完成、怎么算完成。",
      "term_prompt": "请把这些季度想法整理成 OKR:每个 Objective 配 3–5 个 KR,每条 KR 按 SMART 原则检查并改写。想法:客户续费、新客获取、团队方向感。",
      "added_dimensions": [
        "目标和关键结果分两层,不再是待办清单",
        "每条关键结果有数字、基线和截止时间",
        "「方向感」这类模糊目标会被要求量化或降级为行动"
      ]
    },
    {
      "id": "rw-indicators",
      "term_ids": [
        "leading-lagging"
      ],
      "plain_prompt": "请帮我看看这几个关键结果,是不是要等到季度结束才知道有没有完成?有没有办法让我们在季度中间就能知道方向对不对,需要的话帮我补几个指标。",
      "term_prompt": "请检查这组 KR 中滞后指标与领先指标的比例,为每个只有滞后指标的 Objective 补 1–2 个可周度追踪的领先指标。",
      "added_dimensions": [
        "先分类再补,而不是随便加指标",
        "领先指标带追踪频率",
        "能看出哪个目标季度中途无法纠偏"
      ]
    },
    {
      "id": "rw-commit-northstar",
      "term_ids": [
        "committed-aspirational",
        "north-star"
      ],
      "plain_prompt": "这些目标里,有些是一定要做到的,有些是我们想试试看的。另外我担心几个小组各写各的,跟公司大方向对不上。请帮我整理一下并提醒我哪里有问题。",
      "term_prompt": "请为每个 Objective 标注承诺型或挑战型,并检查所有 OKR 是否能追溯到北极星指标,列出对不上的项。",
      "added_dimensions": [
        "每个目标先定性质,完成标准随之不同",
        "有一个统一的上游指标做对齐检查",
        "对不上的目标被明确点名,而不是笼统提醒"
      ]
    }
  ],
  "learning_path": [
    {
      "term_id": "okr",
      "minutes": 8,
      "why_this_order": "整份文档的骨架。"
    },
    {
      "term_id": "smart",
      "minutes": 5,
      "why_this_order": "写关键结果时逐条过的检查表。"
    },
    {
      "term_id": "leading-lagging",
      "minutes": 7,
      "why_this_order": "最容易被忽略、又最影响季度中途纠偏的一个区别。"
    },
    {
      "term_id": "committed-aspirational",
      "minutes": 5,
      "why_this_order": "决定完成标准,写完再补也来得及。"
    },
    {
      "term_id": "north-star",
      "minutes": 5,
      "why_this_order": "最后用它做一次全局对齐。"
    }
  ],
  "unverified": [],
  "evidence_summary": {
    "verified": 4,
    "source_defined": 1,
    "private": 0,
    "unverified": 0,
    "online_verification": true,
    "notes": [
      "北极星指标为从业者概念,标为有来源而非已核验。"
    ]
  }
}
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall