Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Registry Descriptions

ASecurity

How to write the one-line `description` a registered item, ability or move carries. Applies whenever adding an entry to a data registry under src/data, or rewording an existing line. The line describes this engine's behaviour, not the mainline's, and is derived from the data wherever the data already knows the answer.

3 stars
0 votes
0 copies
0 views
Added 9/20/2026
developmentgo

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add lxsmnsyc/overwander --skill registry-descriptions --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Registry Descriptions?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Registry Descriptions
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/lxsmnsyc-registry-descriptions-overwander/badge)](https://www.skillsdirectory.com/skills/lxsmnsyc-registry-descriptions-overwander)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: registry-descriptions
description: >
  How to write the one-line `description` a registered item, ability or
  move carries. Applies whenever adding an entry to a data registry
  under src/data, or rewording an existing line. The line describes
  this engine's behaviour, not the mainline's, and is derived from the
  data wherever the data already knows the answer.
---

Every registry entry carries a `description`: one line saying what the thing does. The field is **required**, so an entry cannot be added without one, and `tsc` names the file that forgot.

## What the line is for

It is player-facing text under the name in a list — a market row, a bag entry, a catch sheet. Write it for somebody deciding whether to carry the thing, not for somebody maintaining it.

## Rules

- **Describe this engine, never the mainline.** Where the two differ, the line follows the code. A Zoom Lens here answers a target that is _casting or channelling_, because there is no "moved second" in a real-time fight. Analytic is the same. Leftovers pays out _each time its holder acts_, because there are no turns to hang a residual on. Pressure doubles a _cooldown_, not PP.
- **Use the engine's own numbers.** Read the constant, do not remember the mainline's. `1.2x`, `a sixteenth of its HP`, `30%`. Round a fraction like `5325 / 4096` to `1.3x` — the reader wants the size, not the ratio.
- **State the modifier, not a derived total.** Sniper is "1.5x on critical hits", never "criticals do 3x rather than 2x": a total baked from today's base goes stale the moment another feature also touches that number. Describe what this entry contributes.
- **Say "HP" for health, never "pool".** Pool is too broad a term to read cold in a list.
- **Figures, not number words.** "1/3 of its HP", "at 1/2 HP", "2 stages", "2x Speed", "5 seconds" — never "a third", "two stages", "doubles", "five seconds". Shorter and easier to scan. Articles stay words: "one of its moves", "the two nobody learns".
- **One sentence where one will do, two at most.** Ends with a full stop; a test enforces that.
- **Say the cost as well as the benefit** when the entry has one: "1.5x Attack, but physical moves are 20% less accurate."
- **No implementation vocabulary.** No event names, no file paths, no "listener", "veto", "lifecycle". "Refuses every stat drop from anybody else" — not "vetoes CheckUnitCanAddStage".
- **Plain, complete prose.** Short is not cryptic. Same voice as the codebase.

## Derive it when the data already knows

A line that restates a table drifts the moment the table changes. Where the registry has the answer, compute it:

```ts
// gems: the type is already in the table
description: `${TYPE_NAMES[type]} moves hit 1.5x. Spent on the first one that lands.`,

// valuables: the sell price is already the entry
description: `Worth ${sell.toLocaleString('en-US')} gold to a vendor. Nothing else.`,
```

For a family whose members differ in kind rather than in a value, write a `describeX(item)` that reads the same tables the engine reads — see `describeBerry` in `src/data/items/berries.ts` and `describeMedicine` in `src/data/items/medicine.ts`. A berry moved between tables then re-describes itself with no edit.

Entries whose behaviour is genuinely their own get a hand-written line, kept in a `DESCRIPTIONS` map beside the names rather than inline in the loop.

## Where they live

| registry  | field added in                   | filled in                     |
| --------- | -------------------------------- | ----------------------------- |
| items     | `src/data/items/__create.ts`     | each `src/data/items/*.ts`    |
| abilities | `src/data/abilities/__create.ts` | `src/data/abilities/gen-1.ts` |

## Test it

Each registry has a test asserting every registered entry has a non-empty description ending in a full stop. The empty string is what a derived description falls back to when nothing matches, so that assertion is what catches a new entry falling through the table — keep it when adding a registry.

Attribution

lxsmnsyclxsmnsyc
View sourceMore from lxsmnsyc →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Browser Extension Developer

Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

284722 votes

Seo Optimizer

SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.

2192 votes

Google Official Seo Guide

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

1862 votes

Tanstack Start

Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per ...

9881 votes

Pentest

PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.

5491 votes
View all in development →