sprite-forge

角色动态 sprite / 桌宠皮肤 / atlas 状态行生产线：母图锚身份 → Frame A 首帧 → AI 视频生成（人工环节）→ 截帧确定性加工 → atlas row + 三道闸。 Use when: 做桌宠皮肤、给猫补新状态动画行、visible-cafe/F258 猫形象素材、角色小循环动画（呼吸/走路/睡觉/挥手级）、把静态角色"做成动态的"。 Not for: 动画短片成片（用 anime-forge）、录屏/教程视频（用 video-forge）、单张静态图/头像（用 image-generation）、UI 图标。 Output: 192×208 atlas row strip + QA 包（contact/GIF/provenance）→ 过三道闸 + operator identity veto 后接 pet.json。

Quality

90%

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

88%Weight 40%Scale 1-5

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

An action-dense, well-sequenced production-line skill with executable commands, explicit batch validation gates, and an identity-veto feedback loop. Its main gaps are inline time-stamped incident notes that mildly inflate tokens and external (non-bundled) reference paths.

Suggestions

Move the dated incident history (F229/F258 dates) into a short 'provenance' or 'deprecated patterns' note so time-sensitive detail does not pad the live workflow.

Bundle the referenced truth-source files (video-to-spritesheet-pipeline.md, prompt-pack-v1.md) under references/ so the skill is self-contained and progressive-disclosure structure is verifiable.

Trim the narrative '出生/Skill化诱因' blockquote to a one-line rationale; the first-principles section already carries the design intent.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly lean, but inline incident dates (2026-06-22~24, 2026-07-08, 2026-07-09) and a narrative '出生/Skill化诱因' backstory add tokens that could be trimmed without losing actionable guidance.	4 / 5
Actionability	Provides copy-paste-ready ffmpeg/magick commands for the deterministic processing stage and a concrete 5-step table with roles and constraints; the one human step (video generation) is honestly flagged rather than glossed.	5 / 5
Workflow Clarity	A clearly sequenced 5-step pipeline with an explicit validation stage — '三道闸 + 分批审', '每批过了才做下一批', and an 'operator identity veto 终审' feedback loop — satisfying the batch-operation validation requirement rather than triggering the cap.	5 / 5
Progressive Disclosure	Well-organized sections with a '真相源' block signaling one-level-deep references (video-to-spritesheet-pipeline.md, prompt-pack-v1.md, petskin-contract.md, pet.json) read on demand, but no actual bundle files ship with the skill and the referenced paths point into the wider repo rather than a bundled reference set.	4 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

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

A dense, well-structured description that states a concrete multi-step production pipeline, explicit use-when triggers, a not-for boundary, and a precise output artifact. The only weakness is slightly project-internal trigger vocabulary rather than universally natural synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete production actions explicitly — '母图锚身份 → Frame A 首帧 → AI 视频生成 → 截帧确定性加工 → atlas row + 三道闸' plus a concrete 'Output: 192×208 atlas row strip + QA 包' — comprehensive coverage of the pipeline.	5 / 5
Completeness	Explicitly answers both what (the production-line steps and the 192×208 atlas/QA output) and when (a clear 'Use when:' with concrete triggers), and adds a 'Not for:' exclusion — matching the top anchor.	5 / 5
Trigger Term Quality	The 'Use when:' clause covers natural phrases ('做桌宠皮肤', '把静态角色做成动态的', '角色小循环动画（呼吸/走路/睡觉/挥手级）') but leans on project jargon (visible-cafe/F258) and omits file extensions or common synonyms, so it is not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	A 'Not for:' clause actively redirects adjacent tasks to anime-forge, video-forge, and image-generation, carving a clear niche with minimal conflict risk.	5 / 5
	Total	19 / 20 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: zts212653/clowder-ai
Path: cat-cafe-skills/sprite-forge/SKILL.md
Commit: 61389cc

Reviewed: 3 hours 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.