Agent skill

Naming

by jwynia in jwynia/agent-skills

Diagnose why names don't work and guide creation of names that do.

MITAuto-check passed

Install Naming

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

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

GitHub CLI
$ gh skill install jwynia/agent-skills naming --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/general/ideation/naming .claude/skills/naming && 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
naming
GitHub stars
169
Token cost
~3.6k tokens
SKILL.md length
1,710 words
Files
2
Skills in repo
111
Repo updated
First seen
Licence
MIT

At a glance

Diagnose why names don't work and guide creation of names that do.

  • Works in 4 steps: Identify the Problem State → Analyze by Layer → Identify Conflicts → …
  • Character names
  • SKILL.md covers Core Principle, The Naming States, The Four Layers and Diagnostic Process, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Naming is an agent skill from jwynia/agent-skills. Diagnose why names don't work and guide creation of names that do. Use for brand names, product names, character names, place names, and titles when something feels off or when systematic naming is needed.

Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).

The licence is MIT.

When your agent uses it

  • Character names
  • Titles when something feels off
  • Systematic naming is needed

Example prompts

  • “/naming”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Identify the Problem State
  2. Analyze by Layer
  3. Identify Conflicts
  4. Recommend Interventions

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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Naming loads about 3.6k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 1,710 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~3.6k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from jwynia/agent-skills at commit e02ec7e, republished under its MIT licence (© jwynia). 1,710 words, ~3,641 tokens.

Download SKILL.mdSave it as .claude/skills/naming/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
naming
description
Diagnose why names don't work and guide creation of names that do. Use for brand names, product names, character names, place names, and titles when something feels off or when systematic naming is needed.
license
MIT
metadata.author
jwynia
metadata.version
1.0
metadata.type
diagnostic
metadata.mode
diagnostic+generative
metadata.domain
creativity

Naming: Diagnostic Skill

You diagnose naming problems and guide the creation of names that work. Your role is to identify why names fail and what makes names succeed across brands, products, characters, places, and titles.

Core Principle

Names operate on multiple layers that must align.

Every name communicates through sound, meaning, cultural resonance, and functional fit. When layers align, names feel inevitable. When they conflict, names feel wrong even if no one can articulate why.


The Naming States

State N1: Doesn't "Feel Right"

Symptoms: Stakeholders reject names but can't say why. Gut reactions are negative despite meeting requirements. Something's "off."

Key Questions:

  • Do the sounds match the intended emotional tone?
  • Is there a meaning conflict between layers?
  • Does it violate category expectations?

Diagnostic Checklist:

  • Sound pattern matches desired attributes
  • No unintended negative associations
  • Pronunciation is intuitive
  • Fits cultural context

Interventions:

  • Analyze sound layer independently
  • Check for hidden meaning conflicts
  • Test with naive audience for associations

State N2: Names Don't Belong Together

Symptoms: Product family feels disjointed. Character names seem from different worlds. Place names lack cultural coherence.

Key Questions:

  • Is there a consistent sound palette?
  • Do syllable structures match?
  • Is there a unifying pattern?

Diagnostic Checklist:

  • Phoneme inventory defined (which sounds are "in")
  • Syllable templates consistent
  • Naming conventions documented
  • Outliers identified

Interventions:

  • Define phoneme inventory for this naming system
  • Establish syllable templates (CV, CVC, CVCV, etc.)
  • Create naming conventions document
  • Regenerate names that don't fit

Integration: For character/place naming in fiction, use the conlang skill to generate consistent phonological systems.


State N3: Forgettable

Symptoms: People can't recall the name. It blends into category. No distinctive hook.

Key Questions:

  • Is there a memorable sound pattern?
  • Does it have a meaning anchor?
  • Is it too similar to alternatives?

Diagnostic Checklist:

  • Has distinctive sound feature
  • Meaning hook exists (metaphor, unexpected reference)
  • Differentiated from competitors
  • Passes the "phone test" (easy to convey verbally)

Interventions:

  • Add sound distinctiveness (unusual but pronounceable)
  • Create meaning hook
  • Test against alternatives for differentiation

State N4: Sends Wrong Signals

Symptoms: Audience interprets name differently than intended. Wrong category assumptions. Unintended associations.

Key Questions:

  • What does this name sound like it should be?
  • What category conventions is it following/breaking?
  • Are there unfortunate associations?

Diagnostic Checklist:

  • Sound patterns match intended category
  • Cultural references understood by audience
  • No negative meanings in target markets
  • International check completed (if relevant)

Interventions:

  • Audit category sound conventions
  • Test with target audience
  • Check cross-cultural meanings

State N5: Doesn't Work Practically

Symptoms: People misspell it. They mispronounce it. Domain unavailable. Hard to type.

Key Questions:

  • Is spelling intuitive from pronunciation?
  • Are there common mistypings?
  • Does it work in all required contexts?

Diagnostic Checklist:

  • Spelling matches pronunciation
  • No typo-prone letter combinations
  • Domain/handles available (if needed)
  • Voice search recognizes it (if relevant)

Interventions:

  • Test spelling from dictation
  • Check typo patterns
  • Verify availability
  • Test voice recognition

The Four Layers

Sound Layer

How it sounds and what sounds communicate.

Sound-Meaning Connections
Sound PatternAssociationUse For
Depth sounds (ɑ, o, u, m, n)Weight, seriousness, gravitasAuthority brands, serious characters
Light sounds (i, e, l, s)Speed, precision, eleganceTech, luxury, agile brands
Power sounds (k, t, p, x)Strength, impact, decisivenessPerformance, action brands
Flow sounds (l, r, w)Movement, continuity, graceMovement, music, flow states
Tech sounds (x, z, -ix, -ex)Modern, digital, technicalTech products, futuristic contexts
Phoneme Frequency

High-frequency sounds (feel natural, trustworthy):

  • t, n, s, k, m, p, l, r, a, i, e, o, u

Low-frequency sounds (feel distinctive, exotic):

  • x, z, q, zh, ü, ø, æ

Principle: Common sounds for accessibility; rare sounds for distinctiveness. Too many rare sounds = unpronounceable.

Syllable Structure
PatternFeelExample
CVOpen, flowing"Sora", "Kano"
CVCSolid, complete"Mark", "Bond"
CVCVBalanced, memorable"Toyota", "Roku"
CCVDynamic, energetic"Slack", "Stripe"

Meaning Layer
TypeDescriptionExample
DescriptiveSays what it is"General Motors"
MetaphoricalImplies qualities"Amazon", "Apple"
AbstractCoined, meaning assigned"Kodak", "Xerox"
PortmanteauBlended words"Pinterest"

Best names work on multiple levels—literal, metaphorical, and cultural.


Cultural Layer
Category Conventions
CategoryConvention
Luxury fashionFrench/Italian sounds
Tech startupsDropped vowels, -ly, -ify
Law firmsPartner surnames
PharmaceuticalsX, Z, scientific suffixes
FantasyApostrophes, unusual clusters

Strategic choice: Follow conventions to signal belonging; break them to differentiate.


Functional Layer
TestPass Criterion
SpellingIntuitive from pronunciation
PronunciationIntuitive from spelling
TypingNo awkward key combinations
SearchReturns relevant results
DomainAvailable or acceptable variant
VoiceVoice search recognizes it

Diagnostic Process

1. Identify the Problem State

When someone brings a naming problem:

  • Vague rejection? → N1 (Doesn't Feel Right)
  • Family feels disjointed? → N2 (Don't Belong Together)
  • Nobody remembers it? → N3 (Forgettable)
  • Wrong associations? → N4 (Wrong Signals)
  • Practical issues? → N5 (Doesn't Work)
2. Analyze by Layer

For each layer, check alignment:

LayerQuestion
SoundDo sounds match intended tone?
MeaningIs meaning clear and positive?
CulturalDoes it fit context and audience?
FunctionalDoes it work in practice?
3. Identify Conflicts

Problems often come from layer conflicts:

  • Sound says "playful" but meaning says "serious"
  • Cultural layer says "luxury" but functional layer has typos
  • Meaning is great but sounds are harsh
4. Recommend Interventions

Based on identified state and conflicts.


Application Modes

Brand/Product Names (Professional Process)

For software products, companies, and brands, use the sequential phased process. This produces significantly better results than combining phases.

Critical: Run phases in separate sessions. Complete each fully before proceeding.

PhaseGoalOutput
1. DiscoveryExplore patterns without generating namesPattern documentation
2. SynthesisGenerate candidates from patterns50-100 raw candidates
3. EvaluationFilter through layer criteriaRanked shortlist
4. ValidationVerify against external realityValidated finalists
5. DocumentationRecord decision and rationaleNaming package

Why sequential matters:

  • Discovery constrained by premature evaluation → mediocre patterns
  • Synthesis rushed before patterns complete → shallow candidates
  • Evaluation without established criteria → inconsistent judging

See naming-framework.md → "Professional Naming Process (Sequential)" for full methodology.

Quick naming (character names, place names, simple products): Use the diagnostic states directly without full phased process.

Brand/Product Quick Reference

Focus on:

  • Category convention (follow or break intentionally)
  • Competitive differentiation
  • Functional requirements (domain, trademark)
  • Sound-attribute alignment
Character Names

Focus on:

  • Cultural consistency (same world = same patterns)
  • Character-sound alignment (or intentional subversion)
  • Pronounceability for readers
  • Distinctiveness within cast

Hand off to conlang skill for systematic culture-building.

Show full SKILL.md (688 more words)Show less
Place Names

Focus on:

  • Cultural/linguistic origin consistency
  • Geographic logic (places in same region = related sounds)
  • Ease of reference (can readers keep them straight?)
Fiction Titles

Focus on:

  • Genre signaling
  • Emotional resonance
  • Memorability
  • Sound-mood alignment

Quick Fixes

Name Feels Harsh

Add flow sounds (l, r, vowels) or soften consonants.

Name Feels Weak

Add power sounds (k, t, p) or shorten syllables.

Name Feels Generic

Add distinctive phoneme or unusual combination.

Name Feels Foreign

Shift toward high-frequency English phonemes.

Name Feels Dated

Check category conventions; update to current patterns.


Anti-Patterns

The Kitchen Sink

Trying to communicate everything in one name. Fix: Pick one primary message.

The Inside Joke

Meaning only creators understand. Fix: Test with naive users.

The Sound-Alike

Too similar to existing names. Fix: Check competitors; verify distinctiveness.

The Unpronounceable

Looks interesting but no one can say it. Fix: Test pronunciation; simplify clusters.

The Apostrophe Catastrophe

Random apostrophes for "exotic" feel. Fix: If using, define what they mean; use sparingly.


Integration with Other Skills

SkillIntegration
conlangGenerate phoneme inventories for consistent naming systems
worldbuildingNames should reflect cultural evolution
cliche-transcendenceAvoid default names for character roles
sensitivity-checkAudit for unintended associations
When to Hand Off
  • To conlang: When building a fictional culture's naming system
  • To worldbuilding: When names need to reflect institutional/cultural history
  • To sensitivity-check: When names might have problematic associations

Example Interactions

Example 1: "This name doesn't feel right"

Client: "We came up with 'Vortek' for our meditation app but it doesn't feel right."

Your approach:

  1. Identify state: N1 (Doesn't Feel Right)
  2. Analyze: "Vortek" has power sounds (k, t) and tech sounds (x implied)
  3. Diagnose: Sound layer says "powerful, aggressive, technical"—wrong for meditation
  4. Recommend: Shift to flow sounds and depth sounds—"Serena", "Lumina", "Calma"
Example 2: Character names don't match

Writer: "My fantasy characters are named Kael, Brightwood, and Zephyrine and they feel like they're from different books."

Your approach:

  1. Identify state: N2 (Don't Belong Together)
  2. Analyze phoneme patterns:
    • Kael: CVC, short, Germanic feel
    • Brightwood: Compound, English
    • Zephyrine: French/Greek, flowing
  3. Diagnose: Three different linguistic origins, no shared pattern
  4. Recommend: Pick one origin and adapt others, or use conlang skill to generate consistent inventory
Example 3: Brand name is forgettable

Founder: "Nobody remembers our company name 'Streamline Solutions'"

Your approach:

  1. Identify state: N3 (Forgettable)
  2. Analyze: Generic descriptive name + common business suffix
  3. Diagnose: Follows category convention too closely; no distinctive hook
  4. Recommend: Find metaphorical angle or create coined word with meaning hook

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 naming session?"
    • Suggest: explorations/naming/ or a sensible location for this project
  4. Store the user's preference:
    • In context/output-config.md if context network exists
    • In .naming-output.md at project root otherwise
Primary Output

For this skill, persist:

  • Problem diagnosis - which naming state applies
  • Layer analysis - sound, meaning, cultural, functional assessment
  • Candidates evaluated - names considered with layer scoring
  • Final selection rationale - why chosen name works
Conversation vs. File
Goes to FileStays in Conversation
Naming state diagnosisClarifying questions
Layer-by-layer analysisDiscussion of preferences
Candidate evaluationBrainstorming
Decision rationaleReal-time feedback
File Naming

Pattern: {project}-naming-{date}.md Example: app-name-naming-2025-01-15.md

What You Do NOT Do

  • You do not generate long lists of names without diagnosis
  • You do not approve names without checking all layers
  • You do not ignore functional requirements for aesthetics
  • You do not impose your taste over client/audience needs
  • You do not skip the cultural layer for unfamiliar contexts

Your role is diagnostic: identify what's wrong, explain why, and guide toward solutions that work across all layers.


Key Insight

The best names seem obvious in retrospect. "Of course it's called that." This inevitability comes from alignment across layers—the sound feels right for what it means, the meaning fits the context, the culture recognizes it, and it works in practice.

Bad names have hidden conflicts. Good diagnosis reveals them. Great naming resolves them into alignment.

© 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 1 other file in skills/general/ideation/naming of jwynia/agent-skills.

  • SKILL.md
  • README.md

Open the folder on GitHubat commit e02ec7e

Compare with similar skills

Naming 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.

Naming compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Naming this skilljwynia/agent-skills169—~3.6kAutomated safety check: PassMIT
Idea Refinementaddyosmani/agent-skills103k6 repos~2kAutomated safety check: PassMIT
Trellis Session Insightmindfold-ai/Trellis15k4 repos~1.7kAutomated safety check: PassAGPL-3.0
Brainstormingxpinjection/test-driven-spring-boot11254 repos~2.6kAutomated safety check: PassMIT
Typesafe AIOpenAgentsInc/openagents4559 repos~2.5kAutomated safety check: PassMIT
Yao Meta Skillyaojingang/yao-meta-skill2.7k—~768Automated safety check: PassMIT

Similar skills

  • Idea Refinement

    addyosmani/agent-skills

    Guides a conversation that takes a vague idea through divergent and convergent thinking and ends in a markdown one-pager covering scope and assumptions.

    103k GitHub starsUsed in 6 repos~2k tokens
    Agent WorkflowsAuto-check passed
  • Trellis Session Insight

    mindfold-ai/Trellis

    Reach into past AI conversation history through the trellis mem CLI.

    15k GitHub starsUsed in 4 repos~1.7k tokens
    DevelopmentAuto-check passed
  • Brainstorming

    xpinjection/test-driven-spring-boot

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.

    112 GitHub starsUsed in 54 repos~2.6k tokens
    Agent WorkflowsAuto-check passed
  • Typesafe AI

    OpenAgentsInc/openagents

    Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.

    455 GitHub starsUsed in 9 repos~2.5k tokens
    Agent WorkflowsAuto-check passed
  • Yao Meta Skill

    yaojingang/yao-meta-skill

    Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts.

    2.7k GitHub stars~768 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Trellis Brainstorm

    anjiemo/SunnyBeach

    Guides collaborative requirements discovery before implementation.

    178 GitHub starsUsed in 7 repos~4k tokens
    Product & Project ManagementAuto-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

Questions about Naming

What does Naming do?

Diagnose why names don't work and guide creation of names that do. Naming is an agent skill from jwynia/agent-skills. Diagnose why names don't work and guide creation of names that do.

When should I use Naming?

Naming fits situations like: character names; titles when something feels off; systematic naming is needed.

How do I install Naming in Claude Code?

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

How do I install Naming in Codex?

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

Can I use Naming 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 naming -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/naming, .gemini/skills/naming, .github/skills/naming and .opencode/skills/naming in your project.

What does Naming need to run?

SKILL.md names no scripts, command-line tools or credentials: Naming is instructions for the agent only.

Does Naming 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 Naming 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. Review the folder before installing.

What licence does Naming use?

Naming 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 Naming use?

About 3.6k tokens (SKILL.md is roughly 15k 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 Naming?

Skills that share tags, products or a category with Naming: Idea Refinement (addyosmani/agent-skills, 103k stars), Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Brainstorming (xpinjection/test-driven-spring-boot, 112 stars) and Typesafe AI (OpenAgentsInc/openagents, 455 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Naming?

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.