Skip to content

fix: quote YAML description in modern-css skill#5242

Open
yogesh-tessl wants to merge 1 commit into
gitkraken:mainfrom
yogesh-tessl:improve/skill-review-optimization
Open

fix: quote YAML description in modern-css skill#5242
yogesh-tessl wants to merge 1 commit into
gitkraken:mainfrom
yogesh-tessl:improve/skill-review-optimization

Conversation

@yogesh-tessl
Copy link
Copy Markdown

@yogesh-tessl yogesh-tessl commented May 18, 2026

Hey @d13 👋

great work truly. 28 skills covering everything from accessibility audits and deep planning to live pairing and performance inspection. The breadth is striking, especially the a11y skills (audit, flow-audit, remediate) that show accessibility isn't an afterthought. With merge-mate already handling AI review, you've clearly invested in making AI a first-class part of the GitLens development workflow.

ran your skills through tessl skill review at work and found some targeted improvements. Here's the before/after:

Skill Before After Change
modern-css 16% 94% +78%

the modern-css skill had the most headroom. Its YAML frontmatter contained unquoted backticks and special characters that broke YAML parsing entirely, causing validation to fail before the content judge could even evaluate the (excellent) body and 7 reference files.

Changes Summary
  • Quoted the YAML description field - the original contained unquoted backticks and angle brackets that broke YAML frontmatter parsing, preventing the skill from passing validation
  • Restructured the description - added a clear capability statement, preserved the "Use when..." trigger clause and "Skip when..." exclusion, trimmed the lengthy consequence explanation that was contributing to the parse failure
  • Preserved all domain expertise - the body content, detection spine, routing table, load-bearing rules, audit guidance, and all 7 reference files are untouched

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.

Hey @d13 👋

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 |
|-------|--------|-------|--------|
| modern-css | 16% | 94% | +78% |
| a11y-audit | 94% | 94% | — |
| a11y-flow-audit | 94% | 94% | — |
| a11y-remediate | 88% | 88% | — |
| deep-planning | 85% | 85% | — |
| update-issues | 84% | 84% | — |
| challenge-plan | 83% | 83% | — |
| worktree | 82% | 82% | — |
| live-inspect | 82% | 82% | — |
| live-pair | 81% | 81% | — |
| ux-review | 78% | 78% | — |
| triage | 78% | 78% | — |
| dev-scope | 78% | 78% | — |
| live-exercise | 75% | 75% | — |
| commit | 73% | 73% | — |
| create-issue | 73% | 73% | — |
| add-icon | 71% | 71% | — |
| audit-commits | 70% | 70% | — |
| investigate | 68% | 68% | — |
| add-command | 68% | 68% | — |
| live-perf | 67% | 67% | — |
| deep-review | 67% | 67% | — |
| add-ai-provider | 65% | 65% | — |
| add-test | 64% | 64% | — |
| prioritize | 64% | 64% | — |
| review | 64% | 64% | — |
| add-webview | 59% | 59% | — |
| analyze | 51% | 51% | — |

The `modern-css` skill had the most headroom — its YAML frontmatter contained unquoted backticks and special characters that broke YAML parsing entirely, causing validation to fail before the content judge could even evaluate the (excellent) body and 7 reference files.

Changes made:
- Quoted the YAML description field — the original contained unquoted backticks and angle brackets that broke YAML frontmatter parsing, preventing the skill from passing validation
- Restructured the description — added a clear capability statement, preserved the "Use when..." trigger clause and "Skip when..." exclusion, trimmed the lengthy consequence explanation that was contributing to the parse failure
- Preserved all domain expertise — the body content, detection spine, routing table, load-bearing rules, audit guidance, and all 7 reference files are untouched

I also stress-tested your modern-css skill against a few real-world task evals and it held up really well on shadow DOM boundary detection with ::part and :host selectors in Lit-based webview components. 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 🙏
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Fixes YAML frontmatter parsing in the modern-css skill by quoting the description value and rewording it to avoid embedded backticks/angle brackets that broke YAML parsing.

Changes:

  • Wraps the description field in double quotes so YAML parses successfully.
  • Rewrites the description into a capability statement plus trimmed "Use when…/Skip when…" guidance, removing unquoted backticks and <style> angle brackets.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants