feat: improve skill scores and add Tessl review workflow

[rohan-tessl]

Hey @Arcadia-1 👋

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
ngspice	61%	86%	+25%
transistor-models	69%	100%	+31%
gmoverid	93%	93%	0%

This PR optimizes all three skills in the repo (well within the five-skill cap to keep things reviewable).

Changes summary

ngspice (61% → 86%)

• Added explicit "Use when..." trigger clause with natural search terms (circuit simulation, SPICE analysis, analog design, etc.)
• Condensed nine verbose, repetitive example sections into a single structured summary table — same information, much less token overhead
• Added a troubleshooting and error recovery table covering common failure modes (missing ngspice, path resolution, convergence, encoding)

transistor-models (69% → 100%)

• Added explicit "Use when..." trigger clause with natural search terms (transistor models, SPICE models, process technology nodes, etc.)
• Added verification steps to the custom PDK model workflow (file copy check, .op sanity run before full simulation)

gmoverid (93% → 93%)

• Tightened the "Core Idea of the gm/ID Methodology" section for conciseness — replaced verbose prose with a compact mapping table while preserving all technical content

Automated Skill Review (GitHub Action)

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

• 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 repo's default GITHUB_TOKEN is used to post the comment.
• Non-blocking by default: the check is feedback-only — no surprise red CI unless you add fail-threshold.
• Not a build replacement: this is review automation for skill markdown, not a substitute for any existing build or simulation pipeline.
• Optional gate: add with: fail-threshold: 70 later if you want PRs to fail on low scores.
• Why only three skills edited here: this PR keeps manual optimization small and reviewable. After merge, every future 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 🙏

[Arcadia-1]

Thanks for the contribution. I am not comfortable merging this as-is because the new workflow runs a third-party action as tesslio/skill-review@main while granting pull-requests: write. That is a mutable external ref with write permission in this repository. Please either remove the workflow from this PR or pin the action to a reviewed immutable commit SHA and document why PR comment write access is required. The SKILL.md edits can be reviewed separately once the workflow risk is addressed.