feat: improve skill scores for 5 lowest-scoring skills

[rohan-tessl]

Hey @aisling404 👋

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
telnyx-fax-curl	52%	94%	+42%
telnyx-seti-curl	58%	95%	+37%
telnyx-seti-python	59%	95%	+36%
telnyx-iot-curl	60%	88%	+28%
telnyx-webrtc-client-js	67%	94%	+27%

This PR covers your 5 lowest-scoring skill(s) in the repo. The remaining 229 skills can improve incrementally via the included GitHub Action (see below). All 5 skills are auto-generated from the Telnyx OpenAPI specs — these changes demonstrate improvements the generation pipeline could adopt.

What changed in telnyx-fax-curl

• Description rewritten with concrete action verbs, an explicit "Use when..." clause, and natural trigger terms (fax API, send/receive faxes, delivery status, webhooks)
• Fixed send fax example — separated file upload (-F) and media URL (-d) into two distinct curl examples (original incorrectly mixed both in one command)
• Added Quick Start workflow with 4-step provisioning sequence
• Moved webhook payload tables and response schemas to references/api-details.md — eliminated 5x repeated response schema blocks, cutting token usage significantly
• Consolidated fax application CRUD into grouped examples to reduce repetition

What changed in telnyx-seti-curl

• Description rewritten with specific actions (query black box test results, check diagnostics), an explicit "Use when..." clause, and natural trigger terms
• Removed erroneous GET /10dlc/enum/{endpoint} — this 10DLC endpoint was incorrectly included in the SETI skill
• Trimmed generic error handling — removed the messaging API example and "curl is pre-installed" note; replaced with a SETI-specific error handling example
• Added domain context — clarified what SETI black box tests validate

What changed in telnyx-seti-python

• Description rewritten with specific actions, an explicit "Use when..." clause, and natural trigger terms
• Removed erroneous GET /10dlc/enum/{endpoint} — same 10DLC endpoint incorrectly included
• Trimmed generic error handling — removed the messaging API example (client.messages.send) that was unrelated to SETI; replaced with SETI-specific error handling
• Streamlined setup — removed redundant comment about default behavior

What changed in telnyx-iot-curl

• Description rewritten with concrete actions (purchase, register, activate, monitor SIMs), an explicit "Use when..." clause, and natural trigger terms (IoT/M2M, cellular connectivity, eSIM)
• Added Quick Start workflow with 4-step provisioning sequence
• Moved bulk endpoints to references/api-details.md — data usage notifications, SIM card orders, OTA updates, wireless blocklists, and additional SIM card endpoints now live in a reference file
• Removed tangential endpoints (storage migrations, mobile voice connections) that don't belong in an IoT SIM card skill
• Reduced from 1062 to 185 lines while keeping all core operations inline

What changed in telnyx-webrtc-client-js

• Description rewritten with concrete actions (initiate/receive calls, handle events, configure auth, monitor quality, integrate AI Agents), an explicit "Use when..." clause, and natural trigger terms (@telnyx/webrtc, browser phone apps, VoIP)
• Added Getting Started Workflow with 5-step connection sequence
• Moved auto-generated API reference to references/api-reference.md — eliminated ~325 lines of duplicated content (the API reference was repeating authentication, call making, and call controls already covered in the main body)
• Cleaned up incomplete stubs (Setting Custom Headers, Call Recovery had no actual content)
• Reduced from 658 to 295 lines while preserving all tutorial content

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

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 🙏