“code-review”

开箱 / 对比评测模板：生成电商开箱视频与 A/B 对比评测的结构、口播稿、拍摄清单与分镜（含公平对比规则、测试设计、缺点与适合人群），可直接转成 storyboard.json 渲染。Use when the user wants an unboxing video, 开箱, 测评, 评测, 横评, 对比…

Transform security review findings into targeted GitHub PR review comments.

Agent skill (SKILL.md)の品質を評価基準に沿って採点し、観点ごとの判定と修正案をレポートするSkill。 ユーザーが「このskillを評価して」「skillをレビューして」「SKILL.mdの品質を見て」のように依頼したら必ずこのSkillを使うこと。…

Use to analyze plugin usage patterns and suggest improvements.

Deep multi-model review pipeline with deliberation, structured verdicts, and learning extraction (invoke as /deep-review — not Cursor's built-in /review).

Present a proposed plan with several real decisions in a local HTML page, collect answers, and revise it in rounds before writing the final plan.

Review recent personal Pi sessions for recurring collaboration problems and return a few small, testable improvements.

Write SOLID-compliant code with principle rules loaded as constraints.

Turn a week's wins, learnings, blockers and OKR progress, gathered by hand from your calendar, tasks and journal, into a structured review with next-week…

广告合规审核技能，用于审核广告素材是否符合中国广告法及相关法规。适用场景：(1) 用户提交广告文案、广告素材要求合规审核时；(2) 用户提到"广告审核""广告合规""广告法审查"等关键词时；(3) 用户要求检查广告内容是否存在违法违规风险时；(4)…

广告公司 AI 合规审查。基于客户品牌调性与违禁词库，对广告/营销文案做合规风险审查（广告法违禁词、绝对化用语、医疗功效暗示、平台限制、品牌调性冲突）并给出修改建议。当用户需要审查广告文案、排查违禁词、做品牌合规检查，或广告/营销公司要为客户提供"上线前合规闸"服务时使用。也适用于把合规审查封装成可售卖的 AI 功能。

Check a result (a Google Doc or Drive file, a ClickUp task or doc, a Miro board, a Claude artifact) against its ticket before the ticket closes: Playwright…

Use when a Claude Code plugin project needs auditing against live official docs — hooks.json, SKILL.md, plugin.json, MCP config — for misuse, broken hook…

Reviews Red Hat Developer Hub pull request code on GitHub in rhdh, rhdh-operator, rhdh-plugins, or community-plugins.

Systematic multi-lens code review for TitleRun.

Review the changes since a fixed point (commit, branch, tag, or merge-base) on two axes — Standards (documented coding standards plus the Fowler smell…

SkillsBench task PR review — classifies the task track (standard / research / multimodal), runs static policy checks against the track-specific rubric…

Orchestrate configurable multi-persona editorial review panels over book-review.

Run a multi-agent security review TEAM over a codebase or recent diff.

Audit and correct existing tests for real production execution, independent assertions, useful behavioral coverage, and resistance to refactors and flakiness.

기구설계 검토 결과·계산·도면 해석을 Gemini로 교차검증한다.

Run a code review through a native subagent in the calling harness, using the Codex or Claude CLI as reviewer.

Use when the author wants independent full reviews of a PR from multiple models or CLI harnesses, followed by evidence-based adjudication and optional scoped…

Fetches open GitHub PRs waiting for your review.