.cursor/skills/go-quality-reviewer-subagent/SKILL.md
Delegates read-only Go quality and pattern reviews to the project subagent defined in .cursor/agents/go-quality-reviewer.md. Use for verification during or after implementation: audit diffs and touched packages against repo conventions and idiomatic Go. Also use when the user asks for a standalone standards or pattern review. Triggers: "go quality review", "use go-quality-reviewer", "subagent review", "verify quality", "standards review", "pattern review", idiomatic Go audit, or after substantive pkg/cmd changes.
npx skillsauth add lolocompany/bifrost go-quality-reviewer-subagentInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This repository defines a Cursor subagent at .cursor/agents/go-quality-reviewer.md. That file is the subagent’s system prompt: read-only Go audits against this repo’s conventions (errors, interfaces, concurrency, cmd/pkg layout) plus common Go patterns (boundaries, options, testing, concurrency hygiene).
The subagent never edits code—it only analyzes and returns a structured report.
Use this skill when any of these apply:
go-quality-reviewer or points at .cursor/agents/go-quality-reviewer.md.file:line) of violations plus suggested fixes in the report (the subagent does not apply them).Separation of roles: wanting code changes does not mean skipping this skill. Use it to verify that new or edited code meets the bar. Only the subagent is read-only; implementation is done by the main agent or the user after (or in a follow-up turn) using the report.
go-quality-reviewer). If the UI requires a path, use .cursor/agents/go-quality-reviewer.md.main” or “Review commits on this branch.”pkg/kafka/, cmd/…, or specific files.git diff main...HEAD or staged diff—state the base ref.git diff. No writes, formatters, or patches.If subagent delegation is not available in the session, read .cursor/agents/go-quality-reviewer.md and follow that prompt yourself (still read-only): same scope rules and same report format.
Per the subagent definition, the report must include:
path:line list (or grouped counts + how to reproduce search if huge), suggested fix (text/snippet).Findings use Critical / High / Medium / Low.
go-quality-reviewer on the relevant scope → read the report → main agent applies suggested fixes (or the user does). The subagent never edits files..cursor/rules/agent-golang-and-replies.mdc; follow it while writing, and use go-quality-reviewer to verify that the result matches conventions and patterns (read-only check).git diff origin/main...HEAD.”pkg/config/ and pkg/metrics/ only.”context in the Kafka client package.”testing
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
development
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.