feat: improve iwsdk-physics skill score (81% → 90%)#39
Conversation
Hey @felixtrz 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements for your `iwsdk-physics` skill. Here's the full before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | iwsdk-physics | 81% | 90% | +9% | | iwsdk-grab | 99% | 99% | — | | iwsdk-ray | 99% | 99% | — | | iwsdk-debug | 86% | 86% | — | | iwsdk-ui | 84% | 84% | — | | iwsdk-planner | 72% | 72% | — | <details> <summary>Changes made</summary> **Description improvement (90% → 100%):** - Replaced generic "Guide for implementing physics" with specific concrete actions: sets up rigid bodies, configures collision shapes and material properties, applies forces and impulses, creates interactive grabbable objects - Added trigger terms for tuning collision response, building throwable/kinematic objects, and debugging physics behavior **Workflow clarity (added verification checkpoints):** - Added "Verify" steps to the dynamic physics object workflow (check `_linearVelocity` after a few frames) - Added "Verify" step to the static collider workflow (drop test to confirm collision) - Added "Verify" step to the grabbable object workflow (throw velocity inheritance check) **Conciseness (trimmed redundant comments):** - Removed obvious inline code comments (`// Bouncy`, `// Impulse force vector`, `// Required if physics objects should be grabbable`, `// 1. Create Three.js mesh`, etc.) - Trimmed numbered step comments and section labels that repeated what the code already showed **Progressive disclosure (split reference content):** - Moved GLXF/Editor configuration (enum values, JSON schema) to `references/GLXF_CONFIG.md` - Moved complete Physics Playground example to `references/EXAMPLES.md` - Main SKILL.md now focuses on core concepts, workflows, and troubleshooting </details> I also stress-tested your `iwsdk-grab` skill against a few real-world task evals and it held up really well on proximity-based grip vs trigger distinction with emulated controllers. Kudos for that. Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch — just saw room for improvement and wanted to contribute. Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at [this Tessl guide](https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices) and ask it to optimize your skill. Ping me — [@yogesh-tessl](https://github.com/yogesh-tessl) — if you hit any snags. Thanks in advance 🙏
|
Hi @yogesh-tessl! Thank you for your pull request and welcome to our community. Action RequiredIn order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks! |
Hey @felixtrz 👋
I ran your skills through
tessl skill reviewat work and found some targeted improvements for youriwsdk-physicsskill. Here's the full before/after:Changes made
Description improvement (90% → 100%):
Workflow clarity (added verification checkpoints):
_linearVelocityafter a few frames)Conciseness (trimmed redundant comments):
// Bouncy,// Impulse force vector,// Required if physics objects should be grabbable,// 1. Create Three.js mesh, etc.)Progressive disclosure (split reference content):
references/GLXF_CONFIG.mdreferences/EXAMPLES.mdI also stress-tested your
iwsdk-grabskill against a few real-world task evals and it held up really well on proximity-based grip vs trigger distinction with emulated controllers. Kudos for that.Honest disclosure. I work at https://github.com/tesslio where we build tooling around skills like these. Not a pitch, just saw room for improvement and wanted to contribute.
If you want to self-improve your skills, or define your own scenarios to pressure test, just ask your agent (Claude Code, Codex, etc.) to evaluate and optimize your skill with Tessl. Ping me @yogesh-tessl, if you hit any snags.