New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Conlang

by jwynia in jwynia/agent-skills

Generate phonologically consistent constructed languages for fiction.

MITAuto-check passedWriting & Content

Install Conlang

skills CLI
$ npx skills add jwynia/agent-skills --skill conlang -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jwynia/agent-skills conlang --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jwynia/agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/creative/fiction/worldbuilding/conlang .claude/skills/conlang && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
conlang
GitHub stars
169
Token cost
~3k tokens
SKILL.md length
1,360 words
Files
5 (incl. scripts)
Skills in repo
111
Repo updated
First seen
Licence
MIT

At a glance

Generate phonologically consistent constructed languages for fiction.

  • Works in 6 steps: Identify the need - What's the language… → Match complexity - flavor (quick names),… → Check for existing constraints - Any… → …
  • You need naming languages
  • SKILL.md covers Core Principle, The Language States, Diagnostic Process and Key Diagnostic Questions, plus 4 more sections
  • Runs TypeScript scripts from its folder; calls deno

What it does

Conlang is an agent skill from jwynia/agent-skills. Generate phonologically consistent constructed languages for fiction. Use when you need naming languages, alien speech, or fantasy tongues without deep linguistics knowledge.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts (for example `data/phoneme-frequencies.json`, `data/syllable-templates.json` and `scripts/phonology.ts`).

It sits in Writing & Content, covering Creative writing and fiction. The licence is MIT.

When your agent uses it

  • You need naming languages
  • Fantasy tongues without deep linguistics knowledge

Example prompts

  • “/conlang”

Requirements

  • Node.js

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  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

What it can do on your machine

Read from SKILL.md and the folder at commit e02ec7e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (TypeScript), which the agent can run.

    Shell commands in SKILL.md call:

    • deno

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Conlang loads about 3k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 1,360 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from jwynia/agent-skills at commit e02ec7e, republished under its MIT licence (© jwynia). 1,360 words, ~3,010 tokens.

Download SKILL.mdSave it as .claude/skills/conlang/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
conlang
description
Generate phonologically consistent constructed languages for fiction. Use when you need naming languages, alien speech, or fantasy tongues without deep linguistics knowledge.
license
MIT
metadata.author
jwynia
metadata.version
1.0
metadata.type
generator
metadata.mode
generative
metadata.domain
worldbuilding

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.

bash
# 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.

bash
# 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
bash
# Generate inventory, then words
deno run --allow-read scripts/phonology.ts --json | deno run --allow-read scripts/words.ts --count 30
Show full SKILL.md (568 more words)Show less

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
  4. 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

© jwynia, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts) in skills/creative/fiction/worldbuilding/conlang of jwynia/agent-skills.

  • SKILL.md
  • data/phoneme-frequencies.json
  • data/syllable-templates.json
  • scripts/phonology.ts
  • scripts/words.ts

Open the folder on GitHubat commit e02ec7e

Compare with similar skills

Conlang next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Conlang compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Conlang this skilljwynia/agent-skills169—~3kAutomated safety check: PassMIT
Story Multi-Perspective Reviewzenstory-ai/oh-story-claudecode7.4k3 repos~3kAutomated safety check: PassMIT
Short Web Fiction Trend Scanzenstory-ai/oh-story-claudecode7.4k2 repos~1.2kAutomated safety check: PassMIT
InkOS Creative HarnessNarcooo/inkos10k1 repos~1.1kAutomated safety check: PassAGPL-3.0
Novel Arteternityspring/shuohao-skills4.3k—~1.1kAutomated safety check: NotesApache-2.0
SepiaNanako0129/sepia3k—~3.6kAutomated safety check: PassMIT

Similar skills

  • Story Multi-Perspective Review

    zenstory-ai/oh-story-claudecode

    Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.

    7.4k GitHub starsUsed in 3 repos~3k tokens
    Writing & ContentAuto-check passed

  • Short Web Fiction Trend Scan

    zenstory-ai/oh-story-claudecode

    Scans popular short web-fiction rankings on Chinese platforms such as Dianzhong and Heiyan to surface trending emotional hooks, themes and topic candidates with an expiry warning.

    7.4k GitHub starsUsed in 2 repos~1.2k tokens
    Writing & ContentAuto-check passed

  • InkOS Creative Harness

    Narcooo/inkos

    Drives long-form fiction, scripts, storyboards, interactive films and long-document translation through InkOS, with every change made by a typed action.

    10k GitHub starsUsed in 1 repo~1.1k tokens
    Writing & ContentAuto-check passed

  • Novel Art

    eternityspring/shuohao-skills

    给 AI 短剧出美术设定集（场景 + 叙事道具）：场景的设计意图、一致性锚点、光照时段变体、 空景提示词；道具的戏剧功能、状态变体、尺度参照、白底无手提示词。

    4.3k GitHub stars~1.1k tokensUpdated yesterday
    Writing & ContentAuto-check: notes

  • Sepia

    Nanako0129/sepia

    Make AI-generated writing read as human-written, in fiction and in professional prose.

    3k GitHub stars~3.6k tokensUpdated 3 days ago
    Writing & ContentAuto-check passed

  • Story Toolbox Router

    zenstory-ai/oh-story-claudecode

    Routes a Chinese web-novel writing request to the matching tool in a 13-skill toolbox, covers author habit memory, and can launch a local dashboard for browsing a project.

    7.4k GitHub stars~1.7k tokensUpdated 6 days ago
    Writing & ContentAuto-check passed

More from jwynia/agent-skills

All 111 skills in this repo

  • Devcontainer

    jwynia/agent-skills

    Diagnose devcontainer configuration problems and guide development environment setup.

    169 GitHub stars~1.2k tokensUpdated 7 mo ago
    Auto-check: notes

  • Frontend Design

    jwynia/agent-skills

    Create distinctive, production-grade frontend interfaces with high design quality.

    169 GitHub stars~3.2k tokensUpdated 7 mo ago
    Auto-check passed

  • Gitea Workflow

    jwynia/agent-skills

    Orchestrate agile development workflows for Gitea repositories using the tea CLI.

    169 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed

  • Godot Asset Generator

    jwynia/agent-skills

    Generate game assets using AI image generation APIs (DALL-E, Replicate, fal.ai) and prepare them for Godot.

    169 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed

  • Mastra Hono

    jwynia/agent-skills

    Develop AI agents, tools, and workflows with Mastra v1 Beta and Hono servers.

    169 GitHub stars~2.9k tokensUpdated 7 mo ago
    Auto-check passed

  • PPTX Generator

    jwynia/agent-skills

    Create and manipulate PowerPoint PPTX files programmatically.

    169 GitHub stars~3.1k tokensUpdated 7 mo ago
    Auto-check passed

Categories

Questions about Conlang

What does Conlang do?

Generate phonologically consistent constructed languages for fiction. Conlang is an agent skill from jwynia/agent-skills. Generate phonologically consistent constructed languages for fiction.

When should I use Conlang?

Conlang fits situations like: you need naming languages; fantasy tongues without deep linguistics knowledge.

How do I install Conlang in Claude Code?

Run `npx skills add jwynia/agent-skills --skill conlang -a claude-code`. Or copy the skill folder (skills/creative/fiction/worldbuilding/conlang in jwynia/agent-skills) into .claude/skills/conlang in your project. Claude Code loads it when a task matches its description.

How do I install Conlang in Codex?

Run `npx skills add jwynia/agent-skills --skill conlang -a codex`. Or copy the skill folder (skills/creative/fiction/worldbuilding/conlang in jwynia/agent-skills) into .agents/skills/conlang in your project. Codex loads it when a task matches its description.

Can I use Conlang in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jwynia/agent-skills --skill conlang -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/conlang, .gemini/skills/conlang, .github/skills/conlang and .opencode/skills/conlang in your project.

What does Conlang need to run?

Going by SKILL.md and its folder, Conlang needs TypeScript for the scripts in its folder and the command-line tools its instructions call (deno). Our summary lists: Node.js.

Does Conlang access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Conlang safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Conlang use?

Conlang is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Conlang use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Conlang?

Skills that share tags, products or a category with Conlang: Story Multi-Perspective Review (zenstory-ai/oh-story-claudecode, 7.4k stars), Short Web Fiction Trend Scan (zenstory-ai/oh-story-claudecode, 7.4k stars), InkOS Creative Harness (Narcooo/inkos, 10k stars) and Novel Art (eternityspring/shuohao-skills, 4.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Conlang?

jwynia (a GitHub user) maintains it in jwynia/agent-skills, which has 169 GitHub stars. The repository holds 111 skills in this directory. The repository was last updated on February 24, 2026.

Source: jwynia/agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.