feat: improve skill quality scores (+58% avg)

[rohan-tessl]

Hey @pgte 👋

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
competitive-intel	17%	75%	+58%
document-faq-assistant	17%	73%	+56%
email-follow-up	17%	82%	+65%
web-research-assistant	17%	73%	+56%
image-generation-assistant	17%	73%	+56%

This PR covers 5 of your 30 skill(s) in the repo. All 30 skills were scoring 17% due to the name field using Title Case instead of the required kebab-case format, which blocked the LLM judge from running entirely. I've capped this PR at 5 skills to keep the review manageable — the included GitHub Action covers ongoing review for the rest on future PRs.

What changed in competitive-intel

• Fixed name field from "Competitive Intelligence" to kebab-case competitive-intel (unblocks LLM judge)
• Description rewritten with "Use when..." clause and natural trigger terms (competitor analysis, market research, pricing comparison)
• Added triggers array for frontmatter compliance
• Restructured content into clear Workflow/Guidelines/Examples/Edge Cases sections
• All helpmaton-specific frontmatter (id, role, requiredTools) preserved

What changed in document-faq-assistant

• Fixed name field from "Document FAQ Assistant" to kebab-case document-faq-assistant
• Description rewritten with "Use when..." clause and trigger terms (document question, knowledge base lookup, FAQ answer)
• Added triggers array for frontmatter compliance
• Restructured content with clearer workflow steps and concise edge case handling

What changed in email-follow-up

• Fixed name field from "Email Follow-up" to kebab-case email-follow-up
• Description rewritten with "Use when..." clause and trigger terms (follow-up email, send follow-up, email after meeting)
• Added triggers array for frontmatter compliance
• Restructured content emphasizing the confirmation-before-send safety pattern

What changed in web-research-assistant

• Fixed name field from "Web Research Assistant" to kebab-case web-research-assistant
• Description rewritten with "Use when..." clause and trigger terms (web research, search the web, find information online)
• Added triggers array for frontmatter compliance
• Restructured content with clearer workflow and source attribution guidelines

What changed in image-generation-assistant

• Fixed name field from "Image Generation Assistant" to kebab-case image-generation-assistant
• Description rewritten with "Use when..." clause and trigger terms (generate image, create image, hero image, illustration)
• Added triggers array for frontmatter compliance
• Restructured content with prompt construction workflow and content policy guidance

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 workflow does not replace your existing CI/CD pipeline — 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 🙏