Review Protocol | Agent Skills Atlas

About this skill

Use when a calling skill (e.g., /dso:implementation-plan, /dso:design-review, /dso:preplanning architectural-pattern check) needs to run a multi-perspective review of an artifact (plan, design, pattern). The caller passes subject, artifact, a perspectives list (each is a reviewer file), passthreshold, startstage, maxrevisioncycles, and callerid; this skill dispatches one sub-agent per perspective, scores on configured dimensions, detects conflicts between reviewers, runs a revision cycle up to maxrevisioncycles, and returns JSON per the standardized REVIEW-SCHEMA. Not user-invocable directly — it is the shared review engine that calling skills delegate to instead of writing ad-hoc review logic.

Quick start

Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.

Installation guide →

Review, license & listing details

Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: 42ce5b7889e60be6b06dde20c8cc01a0aef4408b0c577a339a866306d978685f

About scan coverage and limitations

Original listing metadata

Original name

review-protocol

Original description

Use when a calling skill (e.g., /dso:implementation-plan, /dso:design-review, /dso:preplanning architectural-pattern check) needs to run a multi-perspective review of an artifact (plan, design, pattern). The caller passes subject, artifact, a perspectives list (each is a reviewer file), pass_threshold, start_stage, max_revision_cycles, and caller_id; this skill dispatches one sub-agent per perspective, scores on configured dimensions, detects conflicts between reviewers, runs a revision cycle up to max_revision_cycles, and returns JSON per the standardized REVIEW-SCHEMA. Not user-invocable directly — it is the shared review engine that calling skills delegate to instead of writing ad-hoc review logic.

About this listing

Category: General
Reported license: Apache-2.0
Listing language (estimated): English
Review status: Not individually reviewed
Agent compatibility: Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.