feat: improve skill review scores (+17% avg)

[rohan-tessl]

Hey @charliewwdev 👋

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
e2e-testing	78%	90%	+12%
flutter-skill	67%	90%	+23%

This PR covers your 2 skill(s) in the repo. I capped it at 5 skills per PR to keep review manageable — the GitHub Action below covers ongoing review for the rest.

What changed in e2e-testing

• Description rewritten with an explicit "Use when..." clause covering UI end-to-end testing, cross-platform testing, smoke tests, form flow validation, and navigation verification
• Removed version key from frontmatter (was flagged as unknown key)
• Added validation checkpoints after each workflow step (screenshot, tap, navigation) with error recovery guidance
• Added element targeting priority section (ref > key > text > coordinates)
• Removed marketing content (test scorecard line) and redundant Tips section (duplicated Validation Checkpoints)
• Trimmed example prompts — operational instructions over prompt inspiration
• Removed OpenClaw config section to reduce inline bulk

What changed in flutter-skill

• Description rewritten with broader trigger terms (Flutter testing, widget inspection, Flutter automation, tap, scroll, swipe, gesture-based testing) and an explicit "Use when..." clause
• Replaced inline tool catalog (30+ individual tool listings) with a concise category summary table — same information, much less token usage
• Replaced pseudocode examples with concrete tool invocation syntax (launch_app(project_path: ...), enter_text(key: ..., text: ...))
• Added validation checkpoints after launch, inspect, gestures, and navigation with error recovery paths
• Added element targeting priority section (key > text > type)
• Removed marketing-style opening and replaced with direct capability statement

Changes follow the repo's CONTRIBUTING.md guidelines (fork → branch → PR). No token limits or references/ conventions documented, so improvements are inline.

Tessl Skill Review GitHub Action ✅

I've also included a GitHub Action (.github/workflows/skill-review.yml) that automatically reviews any SKILL.md changed in future PRs and posts scores as a PR comment.

What this gives you:

• 🔍 Automatic tessl skill review runs on every PR touching SKILL.md
• 💬 One updated PR comment with scores and improvement feedback
• 🔓 Zero extra accounts — contributors don't need a Tessl login; only GITHUB_TOKEN is used
• ✅ Non-blocking by default — feedback-only, no surprise red CI (add fail-threshold: 70 later if you want a hard gate)
• 📈 Covers future skills incrementally as contributors edit them

This does not replace your existing CI pipeline (ci.yml, release.yml, etc.) — it only reviews skill markdown on PRs.

Want automatic AI optimization on every SKILL.md change? 🚀

The action I've added gives you review scores on PRs. We also have a more powerful variant — tesslio/skill-review-and-optimize — that can:

• Run AI-powered optimization suggestions on every SKILL.md PR (requires adding TESSL_API_TOKEN as a repo secret)
• Let contributors accept suggested improvements by commenting /apply-optimize
• Still works in review-only mode with zero secrets

Interested? Tick the box and I'll raise a follow-up PR:

• Yes please! Add the tesslio/skill-review-and-optimize action so every SKILL.md PR gets AI optimization suggestions + the /apply-optimize flow
• No thanks — the review scores action is enough for now

---

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 and ask it to optimize your skill. Ping me — @rohan-tessl — if you hit any snags.

Thanks in advance 🙏