跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
其他技能

vfx-review

Independently score one rendered game VFX filmstrip against a fixed rubric and return a JSON verdict. Use when asked to review, score or judge an effect's strip images (for example from the effekseer-vfx skill's `vfx review`) as a reviewer who did not author it.

kanaworksai-hue · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add kanaworksai-hue/effekseer-vfx-skill --skill vfx-review

技能说明


name: vfx-review description: Independently score one rendered game VFX filmstrip against a fixed rubric and return a JSON verdict. Use when asked to review, score or judge an effect's strip images (for example from the effekseer-vfx skill's vfx review) as a reviewer who did not author it. license: MIT metadata: version: "0.1.0"

Independent VFX review

You are the reviewer, not the author. Judge only what is visible in the images you are given. Do not open, read or ask for the recipe code, the brief's intentions or the author's notes; a design sentence from the manifest is context, not evidence.

Inputs you should receive

Usually one brief file written by vfx review-handoff (vfx/work/handoff/<evidence_id>.md) that lists everything below and the report_file path to write your JSON to. Otherwise:

  • the whole-timeline strip vfx/previews/strips/<ID>.png and the key-frame sheet (paths from vfx review); optionally <ID>_compare.png (previous round above, current below) and a --bright strip;
  • the effect's manifest entry: id, category, element, duration, peak, impact, delivery, design;
  • its review flags;
  • the evidence ID of the capture.

Open every image with your image-viewing tool. Tiles are labelled with absolute frame numbers at 60 FPS from the effect's own start. If you need full-size frames, ask the author to run vfx frames <evidence_id> <frames...> and give you the paths (or run it yourself if you have the skill installed). If an image is missing, say so — do not score from flags.

Rubric

Score each criterion 0–3: 0 missing or wrong · 1 present but weak, a player would not notice it · 2 clearly works · 3 reads instantly and has a distinct identity.

idQuestionLook at
readFrom the first lit tile alone, can you tell what the effect is (hit, slash, element, buff...)?first 2–3 lit tiles
timingAnticipation → contact → body → secondary → dissipation (or the slow fade-in / inward build for heals, buffs and charges)? Is the contact the brightest moment and only 2–5 frames?tile labels against manifest peak
layeringAt the strongest tile: a white-hot core, a saturated body and a darker rim or residue, not one flat colour?peak tile; bright strip if provided
shape_changeDoes the main shape erode, sweep or distort over time, or only scale and fade like a sticker?the main shape across consecutive tiles
motionDo secondary particles burst fast then slow, and move as the element should (fire up, ice falls, dark draws in, holy descends or rises)?secondary particles across tiles
placementDo arcs, columns and ground decals sit on or under the dummy rather than beside it or floating?all tiles
tailDoes the last third still show deliberate dissipation, or is it empty or cut off?last third of the strip
identityWould it be distinguishable from other effects of the same category if recoloured grey?whole strip

The authoritative copy is vfx rubric (from assets/review_rubric.json of the effekseer-vfx skill); if it differs from this table, follow it.

Purpose exceptions: heals, shields and buffs need no attack-style white flash; charges build inward before one release; a projectile strip ends at arrival and does not include its impact.

Output

Return exactly one JSON object and save it where the author asks (for example report.json):

{"id": "VFX_Fire_Explosion",
 "scores": {"read": 2, "timing": 3, "layering": 3, "shape_change": 2, "motion": 3, "placement": 3, "tail": 2, "identity": 3},
 "worst": "shape_change",
 "fix": "From f18 to f30 let the main fire layer burn a large gap open on one side so the round outline breaks up.",
 "verdict": "ship",
 "observed_frames": [1, 4, 9, 10, 12, 18, 30, 42, 54, 72]}

Rules:

  • Every criterion gets an integer 0–3. worst names a lowest-scoring criterion.
  • verdict is iterate if any score is below 2, otherwise ship.
  • fix is one concrete change for the worst criterion in recipe terms (which layer, timing, texture or motion), naming frames. One fix only: each iteration round changes one class of problem.
  • observed_frames lists the frame labels you actually looked at.

Save it to the report_file named in the brief (or where the author asks), then reply with your scores, verdict and fix. The author then runs vfx review-submit <evidence_id> <report_file> --reviewer <your reviewer id>. Your reviewer id is whatever the host uses to identify you (subagent name or session id); never author or self.