feat: improve test-environment skill score (66% → 93%)#42
Conversation
Hey @felixtrz 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements. Here's the full before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | test-environment | 66% | 93% | +27% | <details> <summary>Changes made</summary> **Description improvement (biggest impact — 40% → 100%):** - Added explicit "Use when..." clause with five trigger scenarios: running environment tests, verifying default lighting setup, checking gradient configuration, validating scene environment components, debugging environment rendering issues - Expanded from a topic-level description to concrete actions: validates environment system defaults, DomeGradient/IBLGradient color values, EnvironmentSystem registration, and component schemas - Added natural trigger terms (`environment tests`, `default lighting`, `gradient configuration`, `scene environment components`) alongside existing domain-specific ones **Content improvement (77% → 85%):** - Extracted the ~35-line MCPCALL shell helper into a standalone `mcpcall-helper.sh` file — reduces SKILL.md from 331 to 257 lines while preserving the exact same functionality - Moved Known Issues & Workarounds to a separate `KNOWN_ISSUES.md` reference file (gradient rendering limitations, `_needsUpdate` flag behavior, entity index volatility, boolean type requirements) - Consolidated the verbose tool calling pattern explanation into a compact 4-line usage reference - Progressive disclosure score improved from 2/3 → 3/3 by properly referencing supporting files instead of inlining everything **Unchanged skills (sampled):** - iwsdk-grab (99%), iwsdk-ray (99%), iwsdk-debug (92%), xr-mode-test (89%) — already scoring excellently, left untouched </details> I also stress-tested your `test-environment` skill against a few real-world task evals and it held up really well on validating the DomeGradient vs IBLGradient sky color differentiation — that subtle default distinction between `[0.2423, 0.6172, 0.8308, 1.0]` and `[0.6902, 0.749, 0.7843, 1.0]` is a nice detail to have locked down. 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 👋
ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the before/after:Changes made
Description improvement (biggest impact - 40% → 100%):
environment tests,default lighting,gradient configuration,scene environment components) alongside existing domain-specific onesContent improvement (77% → 85%):
mcpcall-helper.shfile - reduces SKILL.md from 331 to 257 lines while preserving the exact same functionalityKNOWN_ISSUES.mdreference file (gradient rendering limitations,_needsUpdateflag behavior, entity index volatility, boolean type requirements)Unchanged skills (sampled):
quick 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.