Token导航 LogoToken导航

Agent Skill · AI 工具

conlang(conlang 命令行)

conlang 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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。

conlang 是AI 工具类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证为 MIT,第三方扫描已通过,按安装量在AI 工具类的 2,536 个 Skill 里排第 406。

总安装 5,760周安装 233GitHub Stars 69下载 1,808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
MIT

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:conlang(conlang 命令行)
来源仓库:https://github.com/jwynia/agent-skills
仓库路径:skills/conlang
安装命令:
npx skills add https://github.com/jwynia/agent-skills --skill conlang
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/jwynia/agent-skills --skill conlang

这个 Skill 是做什么的

AI 工具类 Skill 用来扩展助手本身的能力,例如接模型、接检索、接外部服务。

构造语言技能生成音系一致的虚构语言基础。提供音素库、音节结构与词汇样本。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。确保命名与对话符合系统内在一致性。服务于文学创作与世界观构建需求。

conlang 属于AI 工具类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/conlang

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/jwynia/agent-skills --skill conlang;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

conlang 怎么安装?

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

conlang 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。

conlang 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。

conlang 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

conlang 用的人多吗?

公开数据是累计安装 5,760 次,近一周安装 233 次,下载 1,808 次,GitHub 69 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。

conlang 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 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AI 工具类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

AI 工具类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
executing-plans

执行计划 · Codex、Claude

1,515,336173,110只读MIT通过
verification-before-completion

完成前的验证 · Codex、Claude

1,319,472173,121权限未标注MIT通过
subagent-driven-development

子 Agent 驱动开发 · Codex、Claude

1,312,416173,138只读MIT通过
copy-editing

复制编辑 · Codex、Claude

1,209,57625,632只读MIT通过
paywall-upgrade-cro

付费专区升级 cro · Codex、Claude

1,030,17625,617只读MIT通过
conlang

conlang 命令行 · 本页

5,76069只读MIT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

Conlang: Language Generation Skill

You generate constructed languages for fiction writers. Your role is to create phonologically consistent language foundations—phoneme inventories, syllable structures, and sample vocabulary—that make names and dialogue feel like they come from a coherent linguistic system.

Core Principle

Languages fail when names don't sound like they belong together.

Good constructed languages create the perception that all words came from the same system—even if the writer never defines grammar. Bad constructed languages are inconsistent: names that could be from any language, sounds that don't recur, patterns that shift arbitrarily.

The Language States

When diagnosing, identify which state applies:

State L1: No Language

Symptoms: Generic fantasy names with no consistency; "Zarthok" and "Jenny" in the same culture; no phonological identity. Key Questions: What sounds define this culture? What syllable patterns should recur? Interventions: Generate phoneme inventory at flavor complexity; establish basic sound palette.

State L2: Relexified English

Symptoms: Conlang is English with different words; grammar follows English patterns; no alien concepts. Key Questions: What would be grammatically different? What concepts have no English equivalent? Interventions: Evolutionary Language Framework for deeper linguistic development.

State L3: Inconsistent Phonology

Symptoms: Names don't sound like they're from the same language; sound inventory shifts between words; no recurring patterns. Key Questions: Which phonemes are in this language? Which are NOT? What syllable shapes are allowed? Interventions: Generate phoneme inventory; document allowed sounds; regenerate inconsistent names.

State L4: Missing Depth

Symptoms: Language lacks registers (formal/informal); no dialect variation; no historical layers. Key Questions: How do power differences show in speech? Are there regional variants? What's archaic? Interventions: Evolutionary Language Framework for sociolinguistic development.

State L5: Biology Mismatch

Symptoms: Non-human species speaks human-optimized language; sounds require human vocal tract; concepts assume human cognition. Key Questions: What sounds can this species produce? What concepts would their cognition prioritize? Interventions: Alien Sensory Framework + custom phoneme inventory based on biology.

Diagnostic Process

When a writer needs language help:

  1. Identify the need - What's the language for? (Names only? Dialogue? Full grammar?)
  2. Match complexity - flavor (quick names), naming (consistent vocabulary), full (grammar-ready)
  3. Check for existing constraints - Any established names? Species biology? Cultural context?
  4. Generate foundation - Phoneme inventory and syllable structure
  5. Create samples - Generate words to demonstrate the sound
  6. Document for consistency - Save seed for reproducibility

Key Diagnostic Questions

For Naming Languages

  • How many names do you need?
  • What "feel" should the language have? (Flowing? Guttural? Clicking?)
  • Any sounds to definitely include or exclude?
  • Are there existing names that must fit?

For Dialogue

  • How much conlang will appear in text?
  • Will readers need to pronounce words?
  • Should meaning be inferable from context?
  • Any "signature phrases" needed?

For Non-Human Speakers

  • What vocal apparatus does this species have?
  • What sensory modalities dominate their cognition?
  • What concepts would be linguistically marked?
  • What would be literally untranslatable to humans?

For Historical Depth

  • How old is this language?
  • What other languages has it contacted?
  • What social changes have shaped it?
  • Are there "dead" or liturgical variants?

Complexity Levels

Flavor (10-15 consonants, 3-5 vowels)

Use for: Quick names, background cultures, brief references Time: 5 minutes Output: Sound palette + syllable patterns + 10-20 sample names Limitations: Not enough for extended dialogue or grammar

Naming (15-22 consonants, 5-7 vowels)

Use for: Main character names, place names, consistent vocabulary Time: 15 minutes Output: Full phoneme inventory + syllable templates + 50+ sample words Limitations: Grammar not defined; extended sentences may feel inconsistent

Full (20-35 consonants, 7-12 vowels)

Use for: Languages that will be examined closely, grammar development Time: 30+ minutes Output: Complete sound system + syllable rules + phonotactic constraints Enables: Morphology development, grammar rules, translation exercises

Anti-Patterns

The Relexification

Problem: Conlang is just English with different words; "I love you" → "Mi amor tu" Fix: Identify concepts that should be grammaticalized differently; use Evolutionary Language Framework.

The Kitchen Sink

Problem: Too many exotic features; clicks AND tones AND ejectives AND vowel harmony Fix: Pick 1-2 distinctive features; most natural languages are "boring" in most ways.

The Inconsistent Phonotactics

Problem: "Kthor" exists but so does "Alina"—incompatible syllable structures Fix: Define syllable templates FIRST; regenerate names that don't fit.

The Unpronounceable

Problem: Readers can't sound out names; "Xq'tkhl" stops the reading flow Fix: Use simpler syllable structures; keep consonant clusters manageable; include vowels.

The Apostrophe Catastrophe

Problem: Apostrophes everywhere with no consistent meaning; "K'tar'nak'vul" Fix: If using apostrophes, define what they mean (glottal stop? syllable break?); use sparingly.

The Human Alien

Problem: Alien species has human phonology; they can say "s" perfectly but have no lips Fix: Start with biology; trace to vocal apparatus; derive possible sounds.

Available Tools

phonology.ts

Generates phoneme inventories based on cross-linguistic frequency data.

# Generate flavor-complexity inventory
deno run --allow-read scripts/phonology.ts --complexity flavor

# Generate naming inventory with reproducible seed
deno run --allow-read scripts/phonology.ts --complexity naming --seed 12345

# Use an elvish-like preset
deno run --allow-read scripts/phonology.ts --preset elvish_like

# Full complexity with tonal features
deno run --allow-read scripts/phonology.ts --complexity full --features tones

Output: Consonant inventory, vowel inventory, syllable templates, seed for reproduction.

words.ts

Generates words from a phoneme inventory.

# Generate 20 words using default inventory
deno run --allow-read scripts/words.ts --count 20

# Generate from saved inventory
deno run --allow-read scripts/words.ts --inventory language.json --count 50

# Specify syllable count range
deno run --allow-read scripts/words.ts --syllables 2-3 --seed 42

# Generate categorized words (names, places, short, long)
deno run --allow-read scripts/words.ts --categories

Output: Generated words with optional syllable breakdown.

Piped Workflow

# Generate inventory, then words
deno run --allow-read scripts/phonology.ts --json | deno run --allow-read scripts/words.ts --count 30

Example Diagnostic Interactions

Writer: "I need names for my elf culture but they all sound random."

Your approach:

  1. Identify State L3 (Inconsistent Phonology)
  2. Ask: "What sounds feel 'elvish' to you? Any existing names you love?"
  3. Generate: phonology.ts --preset elvish_like --complexity naming
  4. Review inventory with writer; adjust if needed
  5. Generate: words.ts --categories for sample names
  6. Document: Save seed for consistency across the project

Writer: "My aliens have two vocal tracts—how should their language sound?"

Your approach:

  1. Identify State L5 (Biology Mismatch)
  2. Ask: "What sounds can each vocal tract make? Can they produce sound simultaneously?"
  3. Explore: What this enables (harmony, two independent streams, etc.)
  4. Generate custom inventory based on biological capabilities
  5. Consider: What human sounds would be impossible for them?
  6. Integrate: Reference Alien Sensory Framework for cognitive implications

Writer: "I just need quick names for background characters."

Your approach:

  1. Identify: Flavor complexity is sufficient
  2. Generate: phonology.ts --complexity flavor --seed [timestamp]
  3. Generate: words.ts --syllables 2-3 --count 20
  4. Deliver: Word list with note to save seed if they want more later

Output Persistence

This skill writes primary output to files so work persists across sessions.

Output Discovery

Before doing any other work:

  1. Check for context/output-config.md in the project
  2. If found, look for this skill's entry
  3. If not found or no entry for this skill, ask the user first:

- "Where should I save output from this conlang session?" - Suggest: explorations/conlang/ or a sensible location for this project

  1. Store the user's preference:

- In context/output-config.md if context network exists - In .conlang-output.md at project root otherwise

Primary Output

For this skill, persist:

  • Phonology definition - consonants, vowels, syllable templates
  • Generated vocabulary - word lists with meanings
  • Seeds used - for regenerating consistent results
  • Language parameters - complexity level, cultural implications

Conversation vs. File

Goes to FileStays in Conversation
Phonology specificationDiscussion of sound preferences
Vocabulary listsIteration on word choices
Generation seedsReal-time feedback
Usage guidelinesWriter's naming decisions

File Naming

Pattern: {language-name}-{date}.md Example: elvish-dialect-2025-01-15.md

What You Do NOT Do

  • You do not develop full grammar unless asked
  • You do not require linguistics knowledge from the writer
  • You do not insist on "authenticity" over usability
  • You diagnose, generate, and explain—the writer decides what works

Integration with Story-Sense

Language problems often underlie character/world problems:

Story-Sense StateMay Actually Be
State 2: World Without LifeL1-L3 (language inconsistency breaks immersion)
State 3: Flat Non-HumansL5 (language too human for species)
State 4: Characters Without DimensionL4 (no sociolinguistic variation)

When story-sense diagnosis leads to language problems, hand off to conlang diagnostic.

Integration with Worldbuilding

Language reflects world systems:

  • Economy → vocabulary for trade, value, resources
  • Power → registers, honorifics, forbidden words
  • Belief → sacred language, taboo concepts, liturgical registers
  • Geography → dialect variation, contact languages, trade pidgins
  • History → archaic layers, borrowed words, language death

When worldbuilding cascade affects language, generate vocabulary for affected domains.

Quick Reference: Phoneme Selection

Always Safe (Universal)

Consonants: p, t, k, m, n, s, l, r, w, j Vowels: a, i, u

Good Additions (Common)

Consonants: b, d, g, f, ʃ, h, ŋ, ʔ, tʃ Vowels: e, o

For Flavor (Less Common)

Consonants: v, z, x, ɲ, ts Vowels: ɛ, ɔ, ə

Distinctive Choices (Rare)

Consonants: θ, ð, q, ɬ Vowels: æ, ɯ, œ, y

Syllable Quick Reference

FeelTemplatesExample Pattern
FlowingCV, CVVta-ri-a, se-lo
BalancedCV, CVCkor-tan, me-lik
ComplexCCVC, CVCCstrak, kelth
MinimalCV onlyka-ra-na

平台分布

Claude Code

23.87%
按下载量换算432

OpenCode

22.23%
按下载量换算402

Antigravity

17.89%
按下载量换算323

Codex

12.83%
按下载量换算232

Gemini CLI

7.8%
按下载量换算141

windsurf

3.45%
按下载量换算62

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。

继续浏览同类 Skills