generate2dsprite

Generate and postprocess general 2D game assets and animation sheets: pixel-art sprites, clean HD map props, creatures, characters, NPCs, spells, projectiles, impacts, props, summons, and transparent GIF exports. Use when Codex should infer the asset plan from a natural-language request, match a reference or map art style, call built-in `image_gen` for solid-magenta raw sheets, and use the local processor only for chroma-key cleanup, frame extraction, alignment, QC, and transparent exports.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a well-sequenced, validation-rich workflow and real executable commands. Its main weaknesses are length/repetition across redundant sections and a heavy inline footprint that underuses the reference files for detail offloading.

Suggestions

Deduplicate guidance that recurs across Agent Rules, the Workflow guardrails, and the Defaults section (e.g. single-row sheet prohibition, body-only attack sheets, scale_strategy=preserve) into a single canonical statement to tighten conciseness.

Move the detailed guardrail catalogs (animated body grid, map prop pack, mixed-action atlas) and the Defaults table into references/ files, leaving SKILL.md as a leaner overview that links out, to improve progressive disclosure.

Consolidate the QC numeric-gate thresholds into one referenceable checklist so the same limits are not restated in prose across the Postprocess and QC sections.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining basics Claude already knows and is domain-specific, but it is ~370 lines with notable repetition (single-row sheet prohibition, body-only attack guidance, and scale_strategy=preserve each restated across Agent Rules, Workflow guardrails, and Defaults), so it could be tightened; not 1 because it is not padded with known concepts, not 3 because of the duplicated guidance.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands with real flags (e.g. "python scripts/generate2dsprite.py process --input ... --align feet --scale-strategy preserve --component-mode largest --strict-qc", make_layout_guide.py, make_anchor_layout.py, build-godot-bundle) plus concrete expected outputs; not 2 because the examples are complete rather than pseudocode.	3 / 3
Workflow Clarity	A clear six-step sequence (infer plan, write prompt, generate, postprocess, QC, return bundle) with explicit validation checkpoints and feedback loops (numeric QC gates, "If not, rerun...", strict-qc, regenerate-on-drift) for this batch asset operation; not 2 because validation is explicit and recovery loops are stated.	3 / 3
Progressive Disclosure	References (modes.md, prompt-rules.md) and scripts are real, one-level deep, and clearly signaled, but the SKILL.md body itself is heavy with inline guardrails and Defaults content that could live in reference files; not 1 because structure and signaled references exist, not 3 because content is not appropriately split out of the main file.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concrete, trigger-rich, and clearly states both capability and activation conditions for a well-bounded 2D sprite skill. Its only weakness is mild verbosity from the long asset-type enumeration, but this does not undermine specificity or trigger quality.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and asset types ("Generate and postprocess", "pixel-art sprites, clean HD map props, creatures, characters, NPCs, spells, projectiles, impacts", "chroma-key cleanup, frame extraction, alignment, QC, and transparent exports"), matching the multi-action anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Explicitly answers both what ("Generate and postprocess general 2D game assets...") and when ("Use when Codex should infer the asset plan from a natural-language request, match a reference or map art style..."), satisfying the explicit-trigger anchor; not 2 because the when clause is present and explicit.	3 / 3
Trigger Term Quality	Natural user-facing terms a game-art request would use are well covered ("2D game assets", "animation sheets", "pixel-art sprites", "characters, NPCs, spells, projectiles"); the tool jargon ("image_gen", "solid-magenta") is secondary, so it clears the good-coverage bar rather than the jargon-only bar at 2.	3 / 3
Distinctiveness Conflict Risk	A clearly bounded 2D sprite/animation niche with distinctive signals (solid-magenta raw sheets, local postprocess, Godot Sprite3D contracts) makes overlap with other skills unlikely; not 2 since it is more than 'somewhat specific'.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: 0x0funky/agent-sprite-forge
Path: skills/generate2dsprite/SKILL.md
Commit: 64fd0b5

Reviewed: ~1 month ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.