codebase-review

Codebase Review Skill

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "codebase-review" with this command: npx skills add krazyuniks/guitar-tone-shootout/krazyuniks-guitar-tone-shootout-codebase-review

Codebase Review Skill

Activation: Codebase review, security audit, architecture review, code quality assessment

Arguments: [--section=<name>] [--severity=<level>] [--no-issue]

Preflight Checks

Run these FIRST before any review section:

  • Docker Health: docker compose ps -- all services "Up" and "healthy"

  • Build Profile: docker compose --profile build ps astro

  • Backend Health: curl -s http://localhost:8000/health | jq .

  • Install Tools: docker compose exec webapp pip install vulture bandit radon pip-audit -q

Do not proceed if preflight checks fail.

Review Sections

Each section can be run independently with --section=<name> .

Section Flag Purpose

Code Quality --section=quality

Dead code, complexity, test coverage

Security --section=security

Bandit, pip-audit, OWASP, headers

Architecture --section=architecture

Import boundaries, DDD, SOLID

Frontend --section=frontend

Astro sync, data-testid, HTMX

Documentation --section=documentation

Drift detection, AGENTS.md accuracy

Observability --section=observability

Metrics, circuit breaker, logging

Workflow --section=workflow

Just commands, pre-commit, CI

See references/review-dimensions.md for detailed checklists per section.

Severity Levels

Level Definition Response SLA

Critical Security vulnerabilities, data loss risk Same day

High Significant bugs, broken features 48 hours

Medium Degraded functionality, maintainability 1 week

Low Minor issues, code style Next sprint

Critical and High findings block PR merges.

Workflow

  • Run preflight checks

  • Execute selected sections (or all)

  • Document findings using the template in references/report-template.md

  • Create GitHub issue (unless --no-issue )

  • Fill in summary dashboard

Reference Files

File Purpose

references/review-dimensions.md

Detailed checklists for each review section

references/report-template.md

Output format, findings template, summary dashboard

references/gts-specifics.md

GTS-specific review patterns and commands

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

python-cheatsheet

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

openclaw-version-monitor

监控 OpenClaw GitHub 版本更新,获取最新版本发布说明,翻译成中文, 并推送到 Telegram 和 Feishu。用于:(1) 定时检查版本更新 (2) 推送版本更新通知 (3) 生成中文版发布说明

Archived SourceRecently Updated
Coding

ask-claude

Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no data exfiltration, no external calls, file operations confined to workspace. Use when the user asks to run Claude, delegate a coding task, continue a previous Claude session, or any task benefiting from Claude Code's tools (file editing, code analysis, bash, etc.).

Archived SourceRecently Updated
Coding

ai-dating

This skill enables dating and matchmaking workflows. Use it when a user asks to make friends, find a partner, run matchmaking, or provide dating preferences/profile updates. The skill should execute `dating-cli` commands to complete profile setup, task creation/update, match checking, contact reveal, and review.

Archived SourceRecently Updated