Communication & Collaboration Agent Skills for OpenAI Agents SDK

Use when reviewing third-party feedback on a document, spec, implementation, code change, or review file and producing a point-by-point…

Reviews uncommitted, commit, or merge-base firmware diffs.

Turn /review and /scale-review findings into a prioritized, executable fix-ticket document grounded in the PR/feature context

Automates code review disposition, orchestrates necessary fixes, and validates re-reviews to achieve delivery-ready status.

Use when reviewing a diff, pull request, or implementation for correctness, maintainability, and human readability.

Turn PUBMAXX captain feedback and merged-fix lessons into durable review checks.

Owns the shared finding policy, Lens selection index, and individual Lens definitions used by review workflows.

Review llama.cpp changes against project conventions and common reviewer pitfalls before a PR.

Executes an iterative code review and self-correction loop using sub-agents to critique diffs and fix confirmed issues.

Sends your own plan, diff, or design out to independent external models (Codex, Gemini, optionally a fresh Claude) to find what you MISSED…

Review technical, architectural, migration, implementation, or refactoring plans by first asking product-level questions that resolve…

Review the current branch for code quality, security, and Rails 8 conventions compliance.

Produces a completion summary of a code-review session — what was resolved, skipped, and postponed — for a downstream consumer such as a…

Read this codebase and write, or sharpen, a review skill fitted to it.

Run two independent Codex-internal reviews of documents, markdown, specs, plans, source code, diffs, or implementation files with gpt-5.5…

Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.

Review one task diff or aggregate Change through owner-selected independent lenses, synthesize file-backed findings, and perform…

Quality gate: verify each acceptance criterion of a completed task/work unit, run quality checks, and create follow-up tasks for gaps.

Use when reviewing a pull request or a change in this repository — orients the reviewer to this repository's standards (AGENTS.md…

Generic, repo-agnostic PR review methodology — use this whenever reviewing a pull request in any repo, whether that's an autonomous…

Fires before a plan is accepted or a diff merged when its size, layer count, or abstraction budget is in question — and at the moment…