CtrlK
BlogDocsLog inGet started
Tessl Logo

ammo-mmd-physics-hacks

应对 WebGL 端 MMD 物理 (Ammo.js) 炸模、穿模、卡顿等极限边缘工况的终极调优指南与 Hack 技巧。

59

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agent/skills/ammo-mmd-physics-hacks/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

The body is a tight, well-sectioned instruction-only guide with concrete Ammo.js parameters and APIs, but it is organized as a symptom catalog rather than a sequenced workflow and includes some dramatic padding. Adding a validation/recovery loop and trimming flourish would improve it.

Suggestions

Trim dramatic phrasing (e.g. "超音速抛出", "毁灭性的原形复原能力") to lift conciseness from 3 toward 4-5.

Add a brief ordered tuning workflow with a verification checkpoint (e.g. "apply fix → reload scene → confirm no tearing/freeze for 60 frames") to raise workflow_clarity.

Optionally include one small executable code snippet (e.g. the velocity-limiter loop) to push actionability from 4 to 5.

DimensionReasoningScore

Conciseness

The symptom→cause→solution structure is mostly efficient, but dramatic padding ("滚筒洗衣机效用", "超音速抛出", "毁灭性的原形复原能力") and explanatory flourishes could be tightened; fits anchor 3 rather than 4.

3 / 5

Actionability

Provides concrete APIs and parameters (setCenterOfMassTransform, setActivationState(4), MotionState sync, LinearVelocity>50, AngularVelocity>30, ERP 0.8, CFM 0.015, scale 1.0/margin 0.05, btBoxShape 100x1x100) with only minor gaps in exact call sites, fitting anchor 4.

4 / 5

Workflow Clarity

Organized by symptom→cause→solution rather than as a sequenced process, with no explicit validation checkpoints or feedback loops; fits anchor 3 (structure present but checkpoints missing/implicit).

3 / 5

Progressive Disclosure

Single file under 50 lines with well-organized sections by symptom and numbered problem; no external references needed, so the simple-skill exception yields a 5.

5 / 5

Total

15

/

20

Passed

Description

70%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.

The description is specific and distinctive, naming concrete MMD physics symptoms and the Ammo.js domain, but it lacks an explicit "Use when…" trigger clause, which caps its completeness. Adding a trigger phrase and a few discrete corrective actions would raise it.

Suggestions

Append an explicit trigger clause, e.g. "Use when MMD physics in WebGL shows clothing/hair explosion, clipping, or frame freezes that standard Ammo.js tuning cannot resolve."

List 2-3 discrete corrective actions (e.g. "restore Mode 2 kinematic sync, add velocity limiter, apply local gravity") to lift specificity from 4 to 5.

Add natural synonyms/file references (e.g. .vmd, Bullet physics, cloth simulation) to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain (WebGL MMD physics / Ammo.js) and several concrete symptom types ("炸模、穿模、卡顿等极限边缘工况") plus "调优指南与 Hack 技巧"; falls short of 5 because it does not enumerate discrete corrective actions.

4 / 5

Completeness

Has a clear "what" (tuning guide and hack techniques for MMD physics edge cases) but no explicit "when to use" clause; per rubric a missing "Use when…" caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural user-facing terms like "炸模", "穿模", "卡顿", "MMD", "Ammo.js" that a user would actually say, but lacks synonyms and an explicit "Use when…" trigger phrase, keeping it below 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a very specific niche (WebGL MMD Ammo.js physics hacks) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Project-N-E-K-O/N.E.K.O
Reviewed

Table of Contents

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.