review-loop

review-loop is a Change & PR review skill for AI agents, published by jongwony in the epistemic-protocols repository on GitHub. Skillspace rates review-loop D (61/100) and it passed the safety scan; the rating is based on static analysis only.

Convergence-paced code/PR review-resolve loop via /review-loop. Drives a pluggable review source (codex | code-review), passing it the design intent already captured for the changed surface (relevant project rules + adjacent design comments + decisions constituted at the loop's own gates, with a mission-anchored severity steer) so intentional documented choices are pre-filtered upstream, verifies each finding against the codebase (/inquire) and work-flow (/contextualize), auto-applies Mechanical fixes (Extension) and gates Judgment fixes by shared disposition (Constitution), risk-screens applies (substrate risk → harness permission; epistemic risk → direct Constitution), then re-reviews until the source verdict converges to approve — recurring signals escalate to constituted design decisions rather than suppression, keeping the reviewer independent. At exit, converged or free, a decision constituted at its gates is offered for durable record on the home its reach implies (for a PR…

Grade
D
Quality
61 / 100
Safety
Passed
GitHub stars
124

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

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

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

View source on GitHubjongwony/epistemic-protocols

Our review

Architecture
88 / 100
Maturity
Basic: a single SKILL.md
Security scan
No issues found
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

Not checked yet

  • Category is a classifier prediction; no model has read this skill 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 Change & PR review

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