feat: improve skill scores for sparky

[rohan-tessl]

Hey @algal 👋

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
peekaboo	49%	86%	+37%
rotate-interests	65%	100%	+35%
gmail-ro	71%	89%	+18%
gcal-ro	76%	95%	+19%
solveit-notebook	76%	89%	+13%

This PR covers 5 of your 6 skills to keep the contribution focused and reviewable.

Changes summary

All 5 skills:

• Added explicit "Use when..." clauses to frontmatter descriptions so agents know exactly when to activate each skill
• Expanded trigger terms with natural user language (e.g. "schedule", "meetings", "check email", "screenshot") alongside the existing technical terms
• Changed description format from bare strings to quoted strings (standard frontmatter format)

peekaboo:

• Rewrote description from vague "Capture and automate macOS UI" to concrete actions: "Take screenshots, click UI elements, type text, and automate macOS desktop interactions"
• Added Troubleshooting section with permissions check and node-offline guidance

rotate-interests:

• Added error recovery for Wikipedia fetch failures (re-run or proceed with successful candidate)
• Added validation step to verify INTERESTS.md still has exactly 5 entries after rotation

gmail-ro:

• Added Error handling section distinguishing empty results from actual errors
• Added auth failure recovery guidance
• Expanded trigger phrases with common variations ("Check my inbox", "Find emails about...")

gcal-ro:

• Expanded trigger phrases with natural terms ("What's my schedule?", "Any appointments this week?")

solveit-notebook:

• Added "Jupyter" as a trigger term alongside "SolveIt" for broader keyword coverage

Want your remaining skills optimised too? 🚀

This PR covers 5 of your 6 skills to keep the contribution focused and reviewable. We have tooling that can go further:

• Optimize remaining 1 skill automatically (same AI-powered pass as above)
• Add a GitHub Action — tesslio/skill-review-and-optimize — that automatically reviews (and optionally optimizes) any SKILL.md changed in future PRs. Review mode works with zero secrets; maintainers can add TESSL_API_TOKEN for AI suggestions and the /apply-optimize comment flow.

Interested? Just tick the box below and we'll raise a follow-up PR:

• Yes please! Raise a follow-up PR: optimize the remaining 1 skill + add the Tessl skill-review-and-optimize GitHub Action
• No thanks — happy with the 5 skills in this PR

---

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 🙏