feat: improve skill review scores for 5 khuym skills

[rohan-tessl]

Hey @SelectXn00b 👋

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
debugging	34%	89%	+55%
browser	38%	95%	+57%
browser-automation	47%	98%	+51%
data-processing	49%	95%	+46%
model-usage	60%	84%	+24%

This PR covers your 5 lowest-scoring skill(s) in the repo. The remaining 39 skills can be reviewed incrementally via the included GitHub Action on future PRs.

What changed in debugging

• Description rewritten with concrete actions (diagnose UI failures, locate root causes, reproduce bugs), explicit "Use when..." clause, and natural trigger terms (error, crash, element-not-found, intermittent failure)
• Trimmed from 607 to 117 lines — removed 3x redundant binary-search explanations, verbose troubleshooting sections, and concepts the agent already knows
• Added concise tool reference table replacing lengthy inline descriptions
• Preserved bilingual elements and domain-specific Android automation context

What changed in browser

• Description rewritten with specific actions (navigate, click, fill forms, extract content, screenshots, execute JS) and "Use when..." clause with natural trigger terms (search the web, scrape, automate browser, fill forms)
• Replaced verbose inline API docs with a compact operations reference table
• Kept concrete Baidu Search workflow, replaced vague pseudocode workflows with executable JSON examples
• Preserved the important browserforclaw usage note (don't use open_app to launch Chrome)

What changed in browser-automation (extensions/BrowserForClaw)

• Description rewritten with concrete actions (navigate URLs, click, fill forms, screenshots, execute JS, manage cookies) and explicit "Use when..." clause
• Removed full Kotlin HTTP client implementation (~60 lines) — already lives in referenced PHONEFORCLAW_HTTP_CLIENT.md
• Removed CSS selector basics the agent already knows
• Added proper progressive disclosure — references TOOLS_REFERENCE.md, QUICK_START.md, and PHONEFORCLAW_HTTP_CLIENT.md for details

What changed in data-processing

• Description completely rewritten from 0% → 92% — added concrete actions (parse JSON/CSV, compute statistics, filter/group arrays), explicit "Use when..." clause, and natural trigger terms
• Removed trivial "Tips" section (advice like "use clear variable names" the agent already knows)
• Consolidated examples from 5 to 3 representative ones, removed the trivial percentage calculation
• Added clear Constraints section documenting JavaScript executor limitations

What changed in model-usage

• Description expanded with more specific actions (generate cost reports by model/time, compare provider pricing, manage budget alerts)
• Trimmed from 364 to 99 lines — removed verbose concepts the agent already knows (what input/output tokens are, what providers are), the "Future Features" section, and redundant report templates
• Added clear 4-step workflow (read logs → parse → report → compare budget) replacing disconnected sections
• Fixed code example to be more complete and executable

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.

Note: Your .gitignore currently excludes .github/workflows/ — you may want to un-ignore that path so the workflow file is properly tracked. The file was force-added to this PR to bypass the ignore rule.

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

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 🙏