Token导航 LogoToken导航

Agent Skill · 研究检索

philosophy-of-language(语言哲学)

philosophy-of-language 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

philosophy-of-language 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,674 个 Skill 里排第 69,087。

总安装 220周安装 9GitHub Stars 1下载 71核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:philosophy-of-language(语言哲学)
来源仓库:https://github.com/chrislemke/stoffy
仓库路径:skills/philosophy-of-language
安装命令:
npx skills add https://github.com/chrislemke/stoffy --skill philosophy-of-language
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/chrislemke/stoffy --skill philosophy-of-language

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词定位候选结果。通过 npx skills add 命令从指定仓库安装,需确认权限和维护状态。使用前建议核验是否会触发联网、命令执行或文件读写操作。

philosophy-of-language 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/philosophy-of-language

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/chrislemke/stoffy --skill philosophy-of-langua…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

philosophy-of-language 怎么安装?

在终端执行 npx skills add https://github.com/chrislemke/stoffy --skill philosophy-of-language。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

philosophy-of-language 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

philosophy-of-language 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

philosophy-of-language 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

philosophy-of-language 用的人多吗?

公开数据是累计安装 220 次,近一周安装 9 次,下载 71 次,GitHub 1 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

philosophy-of-language 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
philosophy-of-language

语言哲学 · 本页

2201只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Philosophy of Language Skill

Master the philosophical study of language: How do words mean? How does reference work? What is truth?

Core Questions

QuestionIssue
How do words mean?Theory of meaning
How do names refer?Reference theory
What is truth?Truth theories
What do we do with words?Speech act theory

Theories of Meaning

Frege: Sense and Reference

FREGEAN SEMANTICS
═════════════════

REFERENCE (Bedeutung)
├── What expression picks out
├── "Venus" refers to Venus
└── Compositional: Reference of whole from parts

SENSE (Sinn)
├── Mode of presentation
├── Cognitive significance
├── "Morning star" vs. "Evening star"
└── Same reference, different sense

WHY BOTH?
├── "Hesperus = Phosphorus" is informative
├── "Hesperus = Hesperus" is trivial
├── Same reference, different sense
└── Sense determines reference

Russell: Descriptions

The Problem: "The present King of France is bald"

  • No King of France exists
  • What does the sentence mean?

Russell's Analysis:

"The F is G" =
∃x(Fx ∧ ∀y(Fy → y=x) ∧ Gx)

"There is exactly one F, and it is G"

Not a referring expression but a quantified claim
False (not meaningless) because no unique F exists

Direct Reference

Kripke's Revolution:

  • Names are rigid designators
  • Refer to same thing in all possible worlds
  • Not abbreviated descriptions
KRIPKE'S ARGUMENTS
══════════════════

MODAL ARGUMENT:
"Aristotle might not have been a philosopher"
├── Makes sense
├── But "The teacher of Alexander might not have taught Alexander"
│   └── Would make Aristotle not Aristotle
└── Names ≠ descriptions

EPISTEMIC ARGUMENT:
We can discover "Hesperus = Phosphorus"
├── A posteriori necessary truth
├── Same thing in all worlds
└── But discovered, not known a priori

SEMANTIC ARGUMENT:
Reference is causal-historical
├── Not by fitting description
├── Baptism + chain of communication
└── Name-using practice

Meaning and Use

Wittgenstein: Meaning as Use

Early: Meaning is picturing reality Later: "Meaning is use in a language game"

Language Games:

  • Meaning depends on context, rules, practice
  • No single essence to "meaning"
  • Family resemblance

Private Language Argument:

  • No purely private meanings
  • Rule-following requires community
  • Meaning is public

Speech Act Theory (Austin, Searle)

SPEECH ACT THEORY
═════════════════

THREE TYPES OF ACTS:

LOCUTIONARY
├── Saying something with meaning
└── Uttering words with sense and reference

ILLOCUTIONARY
├── What you do in saying it
├── Promising, warning, asserting
└── Force of the utterance

PERLOCUTIONARY
├── Effect on hearer
├── Persuading, frightening, amusing
└── Consequences of saying

FELICITY CONDITIONS:
├── Preparatory: Appropriate circumstances
├── Sincerity: Speaker means it
├── Essential: Counts as the act
└── Infelicity: Act fails (not false, but unhappy)

Reference and Names

Descriptivist Theory

Frege/Russell: Names = disguised descriptions

  • "Aristotle" = "The teacher of Alexander" (or cluster)
  • Reference determined by satisfying description

Problems (Kripke):

  • Modal: Could have failed to satisfy description
  • Epistemic: Can discover identity
  • Semantic: Reference even with false beliefs

Causal-Historical Theory

Kripke/Putnam:

  • Initial baptism fixes reference
  • Reference transmitted through causal chain
  • Community-based reference

Natural Kind Terms

Putnam's Twin Earth:

TWIN EARTH
══════════

Scenario:
├── Twin Earth exactly like Earth
├── Except "water" is XYZ, not H₂O
├── XYZ phenomenally identical to H₂O
└── 1750: No one knows difference

Question: Does "water" mean the same?

Putnam: No!
├── "Water" on Earth refers to H₂O
├── "Water" on Twin Earth refers to XYZ
├── "Meanings ain't in the head"
└── Natural kind terms refer to natural kinds

Truth

Correspondence Theory

  • Truth = correspondence to facts
  • "Snow is white" is true iff snow is white
  • Problems: What are facts? What is correspondence?

Coherence Theory

  • Truth = coherence with other beliefs
  • System of beliefs that hangs together
  • Problems: Coherent fictions?

Pragmatic Theory

  • Truth = what works
  • Useful beliefs are true
  • Problems: Useful ≠ true

Deflationism

  • "True" is just a device for endorsement
  • "Snow is white" is true = Snow is white
  • No substantial property

Tarski's Semantic Theory

TARSKIAN TRUTH
══════════════

T-SCHEMA:
"S" is true iff S

EXAMPLE:
"Snow is white" is true iff snow is white

Requirements:
├── Object language (mentioned)
├── Metalanguage (used)
├── Hierarchy avoids liar paradox
└── Truth defined for formal languages

Context and Indexicals

Indexicals

  • "I", "here", "now", "this"
  • Reference depends on context of utterance
  • Kaplan: Character vs. Content
KAPLAN'S THEORY
═══════════════

CHARACTER
├── Rule for determining reference
├── "I" = speaker of context
└── Constant across contexts

CONTENT
├── What's said in context
├── "I am tired" said by me
└── Proposition about me

Contextualism

  • Meaning of many expressions context-dependent
  • Not just indexicals
  • "Knows", "tall", "ready"

Key Vocabulary

TermMeaning
SenseMode of presentation
ReferenceWhat expression picks out
Rigid designatorSame reference in all worlds
IndexicalContext-dependent expression
PropositionWhat is said, content
Speech actAction performed in speaking
Illocutionary forceType of speech act
CompositionalityMeaning of whole from parts
Use theoryMeaning is use
Direct referenceNames refer without sense

Integration with Repository

Related Skills

  • analytic-philosophy: Core tradition
  • logic: Formal semantics

Related Themes

  • thoughts/knowledge/: Language and thought

平台分布

Codex

34.84%
按下载量换算25

Claude

30.2%
按下载量换算21

Cursor

18.36%
按下载量换算13

Gemini CLI

8.73%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills