agentleFS
jackchukajackchuka/skills/project-namer/SKILL.md

project-namer

Skill15 starsChanged 9 days agoMITView on GitHub

Use when naming a project, repository, tool, or product and wanting a memorable, unique name

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask what the project contains and does:

    line 38
  2. Distinctive:

    Must work as CLI command? (short, typeable)

    line 50
  3. Distinctive:

    Keep short (1-2 syllables preferred)

    line 68
  4. Distinctive:

    When user shows interest, validate:

    line 84
  5. Distinctive:

    Search it - is the name taken?

    line 89

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Project Namer

Overview

Guide users from vague naming requirements to a memorable, unique name through structured exploration of scope, constraints, and style preferences.

When to Use

  • Naming a new repository, project, tool, or product
  • User is unsure what to call something
  • User rejects initial suggestions as "too generic" or "too vendor-specific"

Core Workflow

digraph naming {
  rankdir=TB;
  "Understand scope" -> "Clarify constraints" -> "Offer style categories" -> "Generate options" -> "Iterate on feedback" -> "Converge";
  "Iterate on feedback" -> "Offer style categories" [label="style shift"];
  "Iterate on feedback" -> "Generate options" [label="refine"];
}

1. Understand Scope

Ask what the project contains and does:

  • Single purpose or multi-purpose?
  • What goes in it? (code, docs, tools, configs)
  • Who uses it? (personal, team, public)

2. Clarify Constraints

Identify naming constraints:

  • Vendor lock-in concerns? (avoid "claude-tools", "openai-kit")
  • Technical limits? (npm name available, no special chars)
  • Must work as CLI command? (short, typeable)

3. Offer Style Categories

Present naming styles - let user pick direction:

StyleExamplesWhen to suggest
Functionaltoolkit, dev-tools, workflowsUser wants clarity over personality
Character/Butlerfriday, jeeves, pennyworthUser wants personality, memorability
Compounddevbox, workstation, codekitBalance of clear + catchy
Metaphorforge, lighthouse, compassEvokes purpose without stating it
Coinedvercel, kubectl, nginxMaximum uniqueness, brand potential

4. Generate Options

Within chosen style, generate 5-8 options. For each:

  • Keep short (1-2 syllables preferred)
  • Easy to pronounce (no awkward consonant clusters)
  • Easy to type (avoid special chars, unusual spellings)
  • Room to grow (not too narrow in scope)

5. Iterate on Feedback

Listen for signals:

  • "Too generic" → move toward Character or Coined
  • "Too tied to X" → broaden scope or change metaphor
  • "I like the vibe of Y" → generate more in that direction
  • "Not just for Z" → revisit scope understanding

6. Converge

When user shows interest, validate:

  • Say it out loud - does it flow?
  • Type it - comfortable on keyboard?
  • Explain it - easy to tell others?
  • Search it - is the name taken? (npm, github, domains)

Quick Reference

Good names are:

  • Unique (not the first thing everyone thinks of)
  • Pronounceable (one way to say it)
  • Memorable (sticks after hearing once)
  • Short (under 10 chars ideal)
  • Unexpired (room to grow)

Avoid:

  • Acronyms (hard to remember: JATK, CDTL)
  • Overused references (jarvis, alfred, hal - too derivative)
  • Generic terms alone (tools, utils, helpers, kit)
  • Vendor names (claude-x, gpt-y, copilot-z)
  • Version numbers in name (toolkit2, tools-v3)

Common Mistakes

MistakeFix
Jumping to suggestions without understanding scopeAsk what goes in it first
Only offering one stylePresent style categories, let user choose
Giving up after one rejectionRejection = information about preferences
Suggesting overused pop cultureDig deeper - lesser-known references or original

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.