feat: improve skill scores + add Tessl skill review CI

[rohan-tessl]

Hey @kyle-sexton 👋

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
use-case-two (was use-case-2.0)	0%	93%	+93%
ea-explain	29%	79%	+50%
create-style-guide	30%	79%	+49%
workshop	30%	86%	+56%
docs-as-code	32%	68%	+36%

This PR intentionally caps changes to five skills to keep review manageable — the included workflow (below) will surface Tessl feedback on future SKILL.md changes automatically.

What changed in each skill

• use-case-two (was use-case-2.0): Fixed name validation failure (periods aren't valid in kebab-case names — scored 0% before). Condensed 767 lines of inline YAML/C# code blocks into a focused workflow that references the existing references/ files. Added clear "Use when" triggers and structured steps.
• ea-explain: Expanded from a bare 39-line stub to a proper skill with structured workflow (identify concept → load context → build explanation → provide example), concrete ADR example, and comprehensive description with trigger terms.
• create-style-guide: Replaced 370 lines of inline HTML/CSS/JSON template dumps with a concise workflow describing what the skill does at each step. Output section details remain available via the referenced supporting skills.
• workshop: Condensed 544 lines (including a 130-line inline example session) to a focused workflow covering all four workshop formats (JAD, Discovery, Refinement, Prioritization) with structured capture templates and output locations.
• docs-as-code: Replaced 757 lines of full configuration templates (Docusaurus config, MkDocs YAML, CI/CD pipelines, Vale/markdownlint configs) with a streamlined 7-step workflow. Templates are available via docs-management skill and MCP servers.

Tessl Skill Review GitHub Action

This PR also adds .github/workflows/skill-review.yml — a lightweight GitHub Action that automatically reviews SKILL.md files on PRs.

• What runs: On PRs that change **/SKILL.md, the workflow runs tesslio/skill-review and posts one comment with Tessl scores and feedback (updated on new pushes).
• Zero extra accounts: Contributors do not need a Tessl login — only the default GITHUB_TOKEN is used to post the comment.
• Non-blocking by default: The check is feedback-only — no surprise red CI. You can add with: fail-threshold: 70 later if you want a hard gate.
• Not a build replacement: This is review automation for skill markdown, not a substitute for your existing markdown-lint or other CI pipelines.
• Why only five skills here: This PR caps manual optimization so it stays reviewable. After merge, every PR that touches SKILL.md gets automatic review comments, so the rest of the library improves incrementally.

---

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 🙏