Token导航 LogoToken导航TokenDH.com
开发执行命令github未标认证来源可访问许可证需确认审计异常

charted-review图表回顾

Agent Skill

charted-review 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

563

周安装

23

GitHub Stars

8

下载量

182
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:charted-review(图表回顾)
来源仓库:https://github.com/marmicode/skills
仓库路径:skills/charted-review
安装命令:
npx skills add https://github.com/marmicode/skills --skill charted-review
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/marmicode/skills --skill charted-review

简介

charted-review 并行调度四名专家子代理对设计文档进行多角度评审,综合输出 actionable feedback。

  • 适用于复杂系统设计前的质量把关,覆盖可用性、性能与安全等多个维度。
  • 首次使用需手动复制子代理配置至本地,非 Cursor 环境需调整文件路径。
  • 评审结果为建议列表,最终决策仍需人工判断与权衡取舍。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Context

  • designDocPath: $ARGUMENTS[0]

Goal

Review the design doc at ${designDocPath} by dispatching four expert sub-agents in parallel, then synthesize their feedback into a single, actionable review.

Step 1 - Set up agents

If the sub-agents from Step 2 are not already configured, ask me to install them. If I confirm, copy sub-agents from the ./assets/agents folder to the {workspaceRoot}/.cursor/agents folder if using Cursor. Adapt the paths if I am not using Cursor.

Step 2 — Parallel Expert Reviews

Spawn the following four sub-agents simultaneously (all in one message). Each agent receives the full design doc content and must return a structured review.

Sub-agent typeFocus area
accessibility-expertAccessibility of the proposed UI — ARIA, keyboard navigation, screen-reader support, color contrast, focus management, semantic HTML.
security-analystSecurity implications — input validation, injection risks, auth/authz gaps, data exposure, secure defaults.
ux-expertUsability — interaction patterns, error/empty/loading states, information architecture, responsiveness, cognitive load.
xp-coachEngineering practices — testability, incremental delivery, PR plan quality, simplicity, YAGNI, refactoring opportunities.

Each sub-agent prompt must include:

  1. The full content of the design doc.
  2. Instructions to return a review with exactly these sections:

- Praise — what the design does well (keep brief). - Concerns — numbered list. Each concern has a short title, an explanation, and a concrete suggestion. - Verdict — one of: approve, request-changes, or needs-discussion.

Step 3 — Synthesize & Detect Conflicts

Collect the four reviews. Present a summary table to the user:

ExpertVerdict# Concerns

Then list all concerns grouped by expert.

After listing, identify conflicts — cases where two or more experts give contradictory guidance (e.g., one says "add a confirmation dialog" and another says "reduce interaction steps", or one says "split into more PRs" and another says "too many PRs already").

Step 4 — Challenge Round (if conflicts exist)

For each conflict:

  1. Clearly describe the disagreement to both involved experts.
  2. Re-launch each conflicting sub-agent with:

- The original design doc. - Their own original review. - The opposing expert's concern that contradicts theirs. - Instructions to either revise their position or defend it with stronger justification.

  1. Run conflicting pairs in parallel when they are independent.

After the challenge round, check if the experts now agree.

Step 5 — Resolution

  • If all conflicts are resolved: present the final consolidated review with the agreed-upon changes.
  • If any conflict remains unresolved: present the remaining disagreement(s) to the user in a clear format:
Unresolved: {short title} {Expert A} argues: *{summary of position}* {Expert B} argues: *{summary of position}* What is your call?

Wait for the user's decision on each unresolved conflict before producing the final consolidated review.

Step 6 — Final Output

Produce a consolidated review with:

  1. Overall Verdictapprove, request-changes, or approve-with-nits based on the aggregated outcome.
  2. Action Items — a numbered checklist of concrete changes to make to the design doc, ordered by priority.
  3. Resolved Conflicts — brief note on how each conflict was settled (expert concession or user decision).

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

37.51%
按下载量换算68

Claude

31.18%
按下载量换算57

Cursor

19.39%
按下载量换算35

Gemini CLI

8.78%
按下载量换算16

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/marmicode/skills --skill charted-review 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills