Thermos Orchestrator

SkillSecurity

Use as the Thermos review orchestrator. Synthesizes findings from both the correctness/security and maintainability review rubrics, presenting a unified review report.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Thermos Orchestrator skill

What this skill tells your AI

The instructions your AI receives, as published by teknokomo/universo-platformo-react in .agents/skills/thermos/SKILL.md and read by ahel’s review.

Use this skill to coordinate correctness, security, and maintainability reviews, synthesizing a single unified review report.

Required Output

When running a Thermos review, output:

  • a summary of files reviewed;
  • a list of correctness and security issues found (scored by severity);
  • a list of maintainability and code quality issues (scored by impact);
  • a clear PASS/FAIL recommendation with required action items.

Workflow

  1. Run the correctness/security check to identify critical bugs, vulnerabilities, and UUID v7 drift.
  2. Run the maintainability check to flag oversized files, circular references, and code formatting/test issues.
  3. Synthesize the findings into a clear, structured review markdown block.
  4. Block merging if any CRITICAL correctness issues or REFACTOR_REQUIRED maintainability issues are discovered.

Integration Commands

Run Thermos reviews via the autoreview tool:

# Correctness review only
autoreview --prompt-file .agents/skills/autoreview/rubrics/thermos-correctness.md

# Maintainability review only
autoreview --prompt-file .agents/skills/autoreview/rubrics/thermos-maintainability.md

# Synthesized review
autoreview --prompt-file .agents/skills/autoreview/rubrics/thermos.md

Signals

GitHub stars
22
Forks
3
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
thermos-teknokomo
Source
github.com/teknokomo/universo-platformo-react