use-plannotator-for-review

Route code review requests through Plannotator (https://plannotator.ai) so Jack can leave comments, request changes, or approve in an interactive UI instead of inline chat. Triggers whenever the user asks to review a branch, diff, PR, or pending changes — phrases like "review this", "review the branch", "review my changes", "look over this PR", "can you review", "ready for review", or any request for code review feedback. Also triggers when a task ends with "now review it" or similar handoff to a review step.

跳到安装

仓库: jaysoo/dot-ai-config
最近来源活动: 2026年4月24日 15:39
检测到的 SKILL.md 语言: 英语
星标: 1
分支: 0

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

直接命令不会经过审查 Prompt；运行前请先检查来源。

npx skills add https://github.com/jaysoo/dot-ai-config --skill use-plannotator-for-review

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

检查来源文件

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

SKILL.md

来源说明 · 只读预览

返回搜索返回安装

nx-docs-style-check

Check modified Nx documentation pages against the astro-docs style guide. Auto-trigger after writing or editing docs content in the nx repo. Also trigger on "check style", "style guide", "docs review", "validate docs". Should run as a final step whenever docs files are modified.

2026-08-06

cnw-dist-smoke

Smoke-test the locally built create-nx-workspace CLI end-to-end against the real npm registry, optionally simulating blocked github.com egress (sandboxed AI agents). Packs the built package, pins its version to a published nx so the sandbox install works, and runs scenario commands with a fetch shim + diverted telemetry. Use when changing CNW download/preset/error flows and needing live proof beyond unit tests. Triggers: "smoke test CNW", "run the CNW dist smoke", "test create-nx-workspace locally", "simulate blocked github", "verify the CNW error path live".

2026-08-05

cnw-stats-analyzer

Query and analyze create-nx-workspace (CNW) telemetry data from MongoDB. Supports prod and staging environments. Use for error analysis, funnel metrics, version comparisons, and usage trends. Triggers on "CNW stats", "workspace stats", "error rates", "telemetry", "commandStats", "CNW errors", "CNW analysis". Also triggers on "show CNW UI", "CNW dashboard", "CNW report", "show me visually" — generates a self-contained HTML dashboard from the bundled template.

2026-08-01

查看这个仓库的全部 Skills

use-plannotator-for-review

Jack's preferred review flow is Plannotator — an interactive UI where he reads diffs and leaves comments, approvals, or change requests. Do not produce a long inline review in chat.

When to invoke

Trigger on any review request targeting a branch, working tree, staged changes, a PR URL, or a specific commit range. Examples:

"review this branch"

"can you review my changes"

"review the PR"

"ready for review"

"look over the diff"

What to do

Pick the right Plannotator command based on intent:

Reviewing current uncommitted changes or a PR URL → invoke /plannotator-review (skill name: plannotator-review).
Re-annotating the last assistant message Gemini just rendered → /plannotator-last.
Annotating a specific markdown file → /plannotator-annotate <path>.

Invoke via the Skill tool, e.g. Skill(skill: "plannotator-review", args: "<PR URL or empty>"). Pass the PR URL through if the user supplied one; otherwise leave args empty so Plannotator picks up the current branch's changes.

Do not write a chat-based review summary first — go straight to the Plannotator skill so Jack can interact in the UI. A one-line "opening this in Plannotator" is fine.

Why

Inline chat reviews are hard for Jack to act on (comment, approve, batch-resolve). Plannotator is the source of truth for review feedback — see https://plannotator.ai/docs/getting-started/installation/.

name

use-plannotator-for-review

description