feat: improve skill review scores across 3 skills

[rohan-tessl]

Hey @pselamy 👋

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
analyze-symbol	10%	88%	+78%
check-prediction-market-alpha	10%	76%	+66%
detect-patterns	10%	77%	+67%
evaluate-performance	10%	83%	+73%
recommend-retirement	10%	79%	+69%

This PR covers 5 of the 7 skill(s) in the repo. I capped it at five to keep the review manageable — the included GitHub Action covers ongoing review for the remaining skills on future PRs.

What changed in analyze-symbol

• Added YAML frontmatter with name, description (including "Use when..." clause), fixing validation failure
• Description rewritten with concrete action verbs and explicit trigger terms for signal generation workflows
• Added signal decision rules section documenting BUY/SELL/HOLD logic from the agent's system prompt
• Improved error handling formatting with bold labels for each failure mode

What changed in check-prediction-market-alpha

• Added YAML frontmatter with name, description (including "Use when..." clause), fixing validation failure
• Description rewritten listing specific platforms (Polymarket, Kalshi) and trigger conditions (BTC, ETH, SOL analysis, volatility detection)
• Reorganized workflow to inline API endpoints directly in each data source step, reducing duplicate sections
• Added contextual annotations to Kalshi market categories (e.g., "direct impact on risk assets" for Fed decisions)

What changed in detect-patterns

• Added YAML frontmatter with name, description (including "Use when..." clause), fixing validation failure
• Description rewritten with specific pattern categories and signal-enrichment focus
• Replaced verbose pattern lists with a table for efficient scanning of pattern categories, names, and signals
• Clarified workflow with explicit MCP tool calls and step descriptions

What changed in evaluate-performance

• Added YAML frontmatter with name, description (including "Use when..." clause), fixing validation failure
• Expanded from 16 to 42 lines — the original was too sparse to guide an agent effectively
• Added retirement thresholds table with explicit values and rationale for each factor
• Added 6-step workflow with clear sequencing: query → filter → evaluate → verify alternatives → check protections → recommend
• Added safety rules from the janitor agent system prompt (CANONICAL protection, batch limits, soft delete)

What changed in recommend-retirement

• Added YAML frontmatter with name, description (including "Use when..." clause), fixing validation failure
• Expanded from 14 to 40 lines — the original listed edge cases but gave no evaluation framework
• Added edge case evaluation table with specific checks and actions for each scenario
• Added 5-step workflow linking this skill to evaluate-performance output
• Added structured output format with three clear decision types: RETIRE, DEFER, REASSIGN

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 🙏