Individual skill
running-a-review-panel
Convenes several reviewers on one frozen evidence packet, names the diversity axis each seat actually varies, preserves dissent, and verifies every finding against live source before it counts as actionable. Use when a trust-bearing or irreversible verdict currently rests on a single reviewer, or on several that cannot fail differently. Do not use for reversible low-stakes work where a second opinion is ceremony, and do not use it to overrule direct contradictory evidence by majority.
skills/running-a-review-panel/SKILL.md
Source commit e44af0e5811e11a3601625cf657d257915689deb
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Instructions only
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 33
- Repository last updated
- Nov 6, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai-agents Repository topic
- ai-safety Repository topic
- coding-agents Repository topic
- configuration-management Repository topic
- developer-tools Repository topic
- prompt-engineering Repository topic
- software-engineering Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
Read excerpt
# Running a Review Panel
## Overview
The repo already says high-consequence verdicts should use a panel, and that "a panel that shares one biased brief is not three independent views, it is one view voiced three times" (`docs/02-operating-system/evaluation-integrity.md` §4). It has not said how to build one. This is that procedure. Its central move is making each seat declare the axis it varies -- model family, mechanism, brief, or human judgment -- because a panel's worth is not its headcount but the number of ways it can fail differently. It also separates the panel's *result* from its *health*: a panel degraded to two correlated seats still returns a confident unanimous verdict. And nothing it says is actionable until checked against live source here -- a blocking finding is a reason to look, not an authorization to fix.
## Decision contract
- **Claim checked:** each seat names the diversity axis it varies, distinct-axis count is recorded separately from seat count, material dissent is preserved rather than averaged, and every actionable finding carries a host-verified state.
- **Artifact observed:** the frozen packet, the seat roster with declared axes, each seat's independent first-pass response, any challenge-round responses, and the degradation record -> `panel.md` plus Evidence IDs in `verification.md`.
- **Decision affected:** block -- does the panel's verified finding set support the underlying verdict, or does dissent or degradation escalate the call to a human?
- **Failure class:** false-independence (correlated seats counted as separate views, consensus treated as proof, dissent averaged away, a degraded panel reported as full, or an unverified finding acted on).
- **Next action:** record result and health together, verify each actionable finding against live source, and escalate a split or degraded panel rather than resolving it by vote.
