tribunal

tribunal is a Multi-agent review & consensus skill for AI agents, published by Hive-Academy in the ptah-extension repository on GitHub. Skillspace rates tribunal D (68/100) and it passed the safety scan; the rating is based on static analysis only.

Multi-vendor ensemble workflows — a flat PANEL OF PEERS across different AI vendors (codex, copilot, cursor, and ptah-cli providers: Moonshot Kimi, Z.AI GLM, Ollama Cloud, OpenRouter) where disagreement and cross-vendor review are the SIGNAL, not noise. Four moves: COUNCIL (fan a question to N vendors, anonymized cross-critique, synthesize a cited verdict — no code), FORGE (same coding task per vendor in isolated git worktrees, round-robin cross-review of diffs, judge ranks, merge the winner), RACE (N attempts, judge-panel rubric, verify the winner before any commit), RELAY (one task through a plan→architect→implement→review pipeline, each phase run on a CLI vendor lane instead of a subagent, persisted to .ptah/specs). TRIGGER on: "tribunal", "convene a council", "council of models", "forge", "race the models", "relay", "second opinion", "multi-vendor", "ensemble", "panel of models", "have the models debate", "cross-vendor review", "which vendor does this best". DISTINCT from…

Grade
D
Quality
68 / 100
Safety
Passed
GitHub stars
27

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

View source on GitHubHive-Academy/ptah-extension

Our review

Architecture
89 / 100
Maturity
Structured: ships references or scripts
Security scan
No issues found
License
Not declared. Check the repository before reusing it.
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Multi-agent review & consensus

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.