loop-implement
Execute an approved loop-plan/v1 plan end to end with docs-first TDD, verification, checkpoint reviews, and commits. Use only…
Review uncommitted changes, unpushed or recent commits, or a branch diff against the plan/target with an external reviewer model (Codex CLI by default; Claude Code or Antigravity on request) — verify correctness, catch unacceptable deviations and bugs
Claude Code
$ npx -y skills add lploc94/cross-review --skill review-impl --agent claude-code
Codex
$ npx skills add lploc94/cross-review --skill review-impl -a codex -y
Cursor
$ npx skills add lploc94/cross-review --skill review-impl -a cursor -y
Gemini CLI
$ npx skills add lploc94/cross-review --skill review-impl -a gemini-cli -y
GitHub Copilot
$ npx skills add lploc94/cross-review --skill review-impl -a github-copilot -y
OpenCode
$ npx skills add lploc94/cross-review --skill review-impl -a opencode -y
Windsurf
$ npx skills add lploc94/cross-review --skill review-impl -a windsurf -y
name: review-impl description: Review uncommitted changes, unpushed or recent commits, or a branch diff against the plan/target with an external reviewer model (Codex CLI by default; Claude Code or Antigravity on request) — verify correctness, catch unacceptable deviations and bugs (logic/security/memory/runtime). No new features or over-engineering beyond the plan. You apply valid fixes, rebut invalid points, and iterate until consensus or stalemate.
Verify the implementation matches the approved plan or target before commit or merge: what is missing, what deviates and whether that breaks the target, and real defects. Design and technology were settled in the plan; this review does not reopen them.
After writing code: before committing, after committing and before pushing, before merging a branch, and at a plan's review checkpoints.
{{PROTOCOL_CORE}}
{{PROTOCOL_VARIANT}}
For this skill: fix accepted issues in code, add a regression test where the defect is testable, and rerun the affected verification. Branch mode: commit the fixes as new commits before replying; never amend, rebase, or force-push reviewed commits unless the user asks. A `plan-gap` finding from the reviewer follows the plan-gap path above.
APPROVE: done. Stalemate: present the deadlocked issues and ask the user. Report rounds, verdict, issues found/fixed/disputed, user decisions, fixed defects by severity, and remaining risks.
Cross-model review skills for Claude Code and Codex CLI: one agent orchestrates, another model reviews plans, code and reasoning.
Execute an approved loop-plan/v1 plan end to end with docs-first TDD, verification, checkpoint reviews, and commits. Use only…
Create an execution-ready, code-grounded phased implementation plan before coding. Only for large work - several features, many…
Review/debate plans before implementation with an external reviewer model (Codex CLI by default; Claude Code or Antigravity on…
Review someone else's pull request or branch with an external reviewer model (Codex CLI by default; Claude Code or Antigravity on…
Peer debate with an external reviewer model (Codex CLI by default; Claude Code or Antigravity on request) on any technical…
Performs AI-powered code review on Git changes using the `ocr` CLI from alibaba/open-code-review. Use when the user asks to…
Address all valid review comments on a PR for the current branch in the streamlit/streamlit repo. Covers both inline review…
Build or update the code review knowledge graph. Run this first to initialise, or let hooks keep it updated automatically.
Maps the `hunkdiff/extension` authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked…