feat: improve bikeshed-conversion skill score 84% → 97%#69
Open
yogesh-tessl wants to merge 1 commit into
Open
Conversation
Hey @yoavweiss 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements for `bikeshed-conversion`. Here's the full before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | bikeshed-conversion | 84% | 97% | +13% | | publish-wg-minutes | 96% | 96% | — | Changes made to bikeshed-conversion: - Expanded frontmatter description — now lists concrete actions (ReSpec-to-Bikeshed conversion, anchor ID preservation, dfn/IDL attribute handling, cross-spec reference resolution) and includes trigger terms users would naturally say (respec, .bs, spec migration, markup conversion) - Condensed introductory prose — removed the redundant "The Problem" sub-section; the key insight is now folded into a single sentence under "Preserving Anchor IDs" - Extracted ID patterns table into ID_PATTERNS.md for progressive disclosure — keeps SKILL.md concise while preserving the full reference - Tightened code examples — shorter BAD/GOOD blocks, removed verbose inline explanations that repeated what the examples already showed - Added error recovery to checklist — step 4 now includes bikeshed --die-on=warning and guidance on diagnosing missing anchors I also stress-tested your `bikeshed-conversion` skill against a few real-world task evals and it held up really well on anchor ID preservation during data-dfn-for scoped conversions with compound hyphenated IDs. 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 https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices and ask it to optimize your skill. Ping me — @yogesh-tessl — if you hit any snags. Thanks in advance 🙏
475d5f0 to
bb1560b
Compare
Author
|
hey @yoavweiss, just a gentle nudge in case this got buried, let me know if you need any changes! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hey @yoavweiss 👋
appreciate how you keep all the spec links organised in one place. Having the full list from High Resolution Time through to Paint Timing makes it easy to see the scope of what this working group covers.
ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the before/after:Changes summary
bikeshed-conversion (+13%):
ID-PATTERNS.mdfor better progressive disclosure - keeps the main skill lean while preserving the full pattern catalogAll W3C/Bikeshed/IDL domain terminology and expert framing preserved intact.
also stress-tested your
bikeshed-conversionskill against a few real-world task evals and it held up really well on preservingdfn-forscoped anchor IDs during a multi-interface spec conversion. Kudos for that.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.