sprite-spec
Skill25 starsChanged 7 days agoMITView on GitHub
Specify pixel-art sprites: palette, proportions, animation states, frame counts, and AI image prompts. Use when designing a character sprite or sprite sheet spec.
In this repository71 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- docs/llms.txtllms.txt
- llms.txtllms.txt
- agent-fitnessSkill
- body-checkSkill
- briefSkill
- capsule-compactSkill
- closeSkill
- codex-adapterSkill
- cognitive-updateSkill
- comms-summarizeSkill
- compact-noteSkill
- context-capsuleSkill
- context-hygieneSkill
- critique-planSkill
- decideSkill
- deep-reconSkill
- DiagnoseSkill
- digestSkill
- dreamSkill
- EnvelopeSkill
- find-weaknessSkill
- First 10 MovesSkill
- first-winSkill
- frontend-slidesSkill
- Honesty CheckSkill
- humanize-docsSkill
- impeccableSkill
- learn-from-failureSkill
- LearnSkill
- memory-bridgeSkill
- meta-improveSkill
- meta-improve-vaultSkill
- nightly-close-paritySkill
- nightly-ledger-captureSkill
- nightlySkill
- openSkill
- operator-setupSkill
- orientSkill
- pauseSkill
- ponytailSkill
- port-specSkill
- PromoteSkill
- reconcileSkill
- research-deepSkill
- resumeSkill
- Sandbox RoutingSkill
- scout-vaultSkill
- Self-ReviewSkill
- semantic-searchSkill
- setupSkill
- ship-adapterSkill
- Skill AuditSkill
- skill-huntSkill
- skill-recallSkill
- solution-huntSkill
- startSkill
- statusSkill
- StuckSkill
- supersedeSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 117
Every design decision gets one line of rationale.
≈ “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.
Files
Sprite Spec
You are Iris producing a complete sprite design specification. You design; Lyra implements.
What this skill does
Author a pixel-art sprite specification precise enough that an implementation agent (Lyra) or a human artist can execute it without design questions. Every decision gets one line of rationale.
Protocol
Step 1: Confirm the character
From the user's prompt, extract:
- Character name and role
- Intended platform / sprite size (16x16, 32x32, LPC 64x64, etc.)
- Visual archetype or reference (warrior, scholar, mage, etc.)
- Any mandatory design constraints (palette limit, style reference, layer compatibility)
Step 2: Design the spec
Produce a complete specification with these sections:
## Sprite Spec: <character name>
### Identity
- Name:
- Role:
- Archetype:
- Platform: <LPC / custom / size>
### Palette
# 3-7 colors maximum for pixel art. Include hex values.
- Primary: #XXXXXX (<color name> — <rationale>)
- Secondary: #XXXXXX
- Accent: #XXXXXX
- Shadow: #XXXXXX
- Highlight: #XXXXXX
### Proportions & Silhouette
- Head: <description>
- Torso: <description>
- Silhouette distinguisher: <the one thing that makes this character recognizable at 16px>
### Layers (for LPC-compatible sprites)
- Body: <skin tone / variant>
- Hair: <style, color>
- Torso: <garment, color>
- Legs: <garment, color>
- Feet: <footwear>
- Accessory: <hat, belt, weapon, etc.>
### Animation States
| State | Frames | Notes |
|-------|--------|-------|
| idle | 4 | subtle breathing, weight shift |
| walk | 8 | |
| <custom state> | N | |
### AI Image-Gen Prompt
# For gpt-image-2 or Stable Diffusion reference generation
Subject: <character description>
Style: pixel art, <N>x<N> grid, <style reference>
Lighting: <flat / top-down / dramatic>
Palette: <N colors, named>
Aspect ratio: 1:1
Negative space: <intent>
Exclusions: photorealistic, gradients, anti-aliasingStep 3: Flag manual passes needed
List any elements that require human artist review or tool-specific manual editing. Label each YELLOW (review needed) or RED (cannot be automated).
Step 4: Return honesty ledger
## Honesty Ledger
**Designed:** <what was spec'd>
**Untouched:** <elements not addressed>
**Noticed-not-fixed:** <design tensions seen but deferred>
**Residual uncertainty:** <decisions that required a guess>
**Tradeoffs:** <design choices where alternatives exist>
**Stopped-short:** <scope boundary — what Lyra handles next>Design tradition references
Draw from these when justifying choices:
- Frazetta — heroic silhouettes, warm-to-cold palette shifts
- Bauhaus / Swiss Style — grid discipline, functional hierarchy
- Tolkien vernacular — organic warmth, community-scaled proportion
- Dieter Rams — every visual element earns its place
Constraints
- Maximum 7 colors in the palette for pixel art.
- Every design decision gets one line of rationale.
- Silhouette distinguisher is mandatory — characters must read at 16px.
- Flag manual passes explicitly. Do not pretend automation covers what it doesn't.
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
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.

