$ loading_
Run a structured code review before commit or release on local or PR branches.
The materials indicate this is an open-source, prompt-only code review helper skill with no required secrets and no declared remote endpoints. Overall risk appears low from the available facts, but supply-chain confidence is limited because the repo has 0 stars, no declared license, and unknown maintenance status.
The materials explicitly state that no keys or environment variables are required. No API tokens, account credentials, or other sensitive authentication data are requested, so credential exposure and abuse risk appears low.
Both the system checks and the materials show no declared remote endpoints. As a prompt-only skill, it does not present its own standalone data exfiltration path. The README mentions optional models/web search as usage context, but does not declare fixed hosts that this skill itself connects to.
The objective check marks it as prompt-only, and there are no installation scripts, executables, local process launches, or system command execution requirements. The README describes review workflow and behavior constraints, not components that directly execute code.
Its stated purpose is to run structured reviews on a local branch or PR branch, so it necessarily reads and analyzes code content. There is no stated file-writing, broad authorization, or overprivileged access, but it will access project source and adjacent files, so users should be mindful of sensitive code or configuration within scope.
The source is an open GitHub repository, which is a positive factor because the code can in principle be audited. However, the repo has 0 stars, no declared license, and unknown maintenance status, so community validation and maintenance signals are weak. No explicit malicious red flags are visible, but supply-chain trust is limited and the repository and commit history should be reviewed first.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "autoreview" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/agent-skills/main/skills/autoreview/SKILL.md 2. Save it as ~/.claude/skills/autoreview/SKILL.md 3. Reload skills and tell me it's ready
Run a structured code review on my current local branch. Focus on potential bugs, maintainability issues, test gaps, and security risks, and rank findings by severity with suggested fixes.
A structured review report with findings, severity levels, explanations, and fix recommendations.
Perform a pre-release closeout review for this PR branch. Check code quality, edge cases, regression risks, and whether logging and error handling are sufficient, then state whether you recommend merging.
A pre-release review summary with key risks, major issues, and a merge recommendation.
Use Claude to perform a structured code review on the current branch. Focus on style consistency, readability of complex logic, duplicated implementations, and testing suggestions.
A review focused on readability and maintainability, with concrete improvement suggestions.
Run the bundled structured review helper as a closeout check. This is code review, not Guardian auto_review approval routing.
Codex review is the default when no engine is set. It usually delivers the best review results and should remain the normal final closeout engine.
Use when:
review still running: ... elapsed=... pid=... as healthy progress, not a hang. Let the helper continue while heartbeats are advancing. Pass --stream-engine-output when live engine text is useful; Codex and Claude filter tool/file chatter, other engines pass raw output through.clawsweeper[bot] or another automation, identify the human trigger when practical. Check timeline/comments first; if rate-limited, use gitcrawl/cache or public PR HTML. Look for maintainer commands such as @clawsweeper automerge, /landpr, or labels/status comments that armed automerge. Report automerge triggered by @login; if not found, say trigger unknown.codex review, nested reviewers, or reviewer panels from inside the review. The helper builds one bundle, calls one selected engine, validates one structured result, and stops.…
Render AI session JSONL logs into searchable, shareable single-file HTML viewers.
Run cross-platform OpenClaw remote validation with provider and lease reporting.
Attach redacted agent transcripts to GitHub PRs or issues for local provenance.
Write a path-free, clipboard-ready handoff prompt that lets another agent investigate, discuss, or pick up a specific task.
Fetch GitHub issues, create fixes, open PRs, and handle reviews.
Convert text to speech locally and offline with sherpa-onnx, no cloud needed.
Automatically closes out code reviews with Codex as the default reviewer.
Review code or branches for correctness, compatibility, architecture, tests, performance, and security.
Run multi-model reviews for code changes, PRs, and risky edits.
Review code deeply across correctness, tests, security, performance, and product quality.
Review local changes, branch diffs, and patches for AI-assisted coding.
Use Claude skills to automate Git, testing, and code review workflows.