Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Tileset

ASecurity

Create pixel-art tilesets with no external tools: terrain, autotiles (RPG Maker MZ A1-A5 and B-E, blob-47, 16-tile corner sets), seamless backgrounds, and parallax layers, laid out as the target engine's sheet. The model authors a palette-locked spec or a procedural generator, the bundled stdlib renderer writes the sheet, and a render-review loop iterates until the seams read. Use when: 'tileset', 'autotile', 'terrain tiles', 'blob tileset', 'parallax background', 'RPG Maker tileset', 'seamle...

20 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentspythongobashbackend

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 10/4/2026

$npx -y skills add melodic-software/claude-code-plugins --skill tileset --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Tileset?

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

Security grade badge for Tileset
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/melodic-software-tileset/badge)](https://www.skillsdirectory.com/skills/melodic-software-tileset)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
description: "Create pixel-art tilesets with no external tools: terrain, autotiles (RPG Maker MZ A1-A5 and B-E, blob-47, 16-tile corner sets), seamless backgrounds, and parallax layers, laid out as the target engine's sheet. The model authors a palette-locked spec or a procedural generator, the bundled stdlib renderer writes the sheet, and a render-review loop iterates until the seams read. Use when: 'tileset', 'autotile', 'terrain tiles', 'blob tileset', 'parallax background', 'RPG Maker tileset', 'seamless tile'. Not for a single sprite or icon (use /pixel-art:sprite), a character walk cycle (use /pixel-art:animate), a window skin or icon set (use /pixel-art:ui), an effect sheet (use /pixel-art:vfx), or an HTML cutscene (use /pixel-art:scene)."
argument-hint: "<terrain or set> [engine] [tile size]"
user-invocable: true
disable-model-invocation: false
metadata:
  workflow-stage: implement
  summary: Author, render, and review an engine tileset or parallax
---

# Tileset

Produce a tileset or parallax layer the target engine can load, and show it.

## 1. Brief

Follow [`brief.md`](${CLAUDE_PLUGIN_ROOT}/reference/brief.md) the same way `/pixel-art:sprite`
does, including the `brief.md` file, the one-line defaults, and the presence-gated
`/planning:interview` offer. Then add:

- **Set**: seamless single tile, blob-47, 16-tile corner, RPG Maker quarter-tile block, or parallax layers.
- **Tile size and sheet**: the engine cell and which file (A2, B, a Godot atlas, a plain strip). Read
  [`engine-layouts.md`](${CLAUDE_PLUGIN_ROOT}/reference/engine-layouts.md) and
  [`craft-tiles.md`](${CLAUDE_PLUGIN_ROOT}/reference/craft-tiles.md). Do not restate their tables.

## 2. Choose the backend

Same rule as `/pixel-art:sprite`: read [`backends.md`](${CLAUDE_PLUGIN_ROOT}/reference/backends.md).
`native` is the default and always available. Honor `${user_config.backend}` when it names another
backend (`native` or `aseprite`). Stay on native unless the request or that setting names Aseprite.

## 3. Author

Draw the set `craft-tiles.md` names for that engine. Quarter-tile targets are the source block (the
engine composes the final shapes), not a hand-drawn tile for every composed shape, unless the brief
asks for that proof. Blob and corner sets are the full tiles the engine samples. Parallax layers
follow the depth rules in `craft-tiles.md`: slower, darker, and less detailed as they recede, and
the scroll step divides the loop width.

Prefer a short procedural generator when the sheet is larger than a few tiles. A worked A2 ground
sheet is `${CLAUDE_PLUGIN_ROOT}/examples/tileset/a2_ground.py`. Keep the palette locked in the spec.

## 4. Render

```bash
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/backends.py" <spec.json> --out <dir> --scale 4
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/gallery.py" <dir>
```

`backends.py` writes the same files `render.py` does. Pass `--backend <name>` when this request
names one; otherwise pass `--backend ${user_config.backend}` when that option is set, rather than
relying on the environment to carry it.

Output location resolves as in `/pixel-art:sprite`. Keep the spec and the generator beside the output.

## 5. Review loop

Read `preview.png` and critique it against the brief and `craft-tiles.md`: seams on a repeat (the
generator or a 3x3 preview), edge-band thickness on an autotile, a center that does not shout the
grid, and a blank top-left cell when the target sheet requires one. Fix the spec or generator,
re-render, re-read. Stop when it reads at 1x or after the user's direction says so; typically 2 to
4 rounds. Name the remaining weaknesses honestly.

## 6. Deliver

Report `sheet.png` at 1x under the filename the engine expects, `sheet.json`, the preview, and the
gallery. Name the engine folder (`img/tilesets` for RPG Maker MZ).

## Next

/pixel-art:scene to place the tiles in a scene or parallax backdrop.

## Gotchas

- `sheet.png` is the engine asset. `preview.png` is for review.
- An RPG Maker B-E sheet starts with a blank cell. See `engine-layouts.md`.
- Quarter edges must match every partner quarter. A seam that only shows up in a composed shape is
  still a fail.

Attribution

melodic-softwaremelodic-software
View sourceSee grades on GitHubMore from melodic-software →
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

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →