Agent skill

PR Walkthrough

Generate a local static interactive D3 walkthrough of a pull request.

MITAuto-check passedDevelopment

Install PR Walkthrough

skills CLI

$ npx skills add Terry-Mao/AICodingFlow --skill pr-walkthrough -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install Terry-Mao/AICodingFlow pr-walkthrough --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/Terry-Mao/AICodingFlow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/pr-walkthrough .claude/skills/pr-walkthrough && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "pr-walkthrough" agent skill from https://github.com/Terry-Mao/AICodingFlow/tree/main/.agents/skills/pr-walkthrough into .claude/skills/pr-walkthrough/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-walkthrough", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/Terry-Mao/AICodingFlow/tree/main/.agents/skills/pr-walkthrough

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add Terry-Mao/AICodingFlow --skill pr-walkthrough -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Terry-Mao/AICodingFlow pr-walkthrough --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Terry-Mao/AICodingFlow.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/pr-walkthrough .agents/skills/pr-walkthrough && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "pr-walkthrough" agent skill from https://github.com/Terry-Mao/AICodingFlow/tree/main/.agents/skills/pr-walkthrough into .agents/skills/pr-walkthrough/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-walkthrough", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Terry-Mao/AICodingFlow --skill pr-walkthrough -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Terry-Mao/AICodingFlow pr-walkthrough --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Terry-Mao/AICodingFlow.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/pr-walkthrough .cursor/skills/pr-walkthrough && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "pr-walkthrough" agent skill from https://github.com/Terry-Mao/AICodingFlow/tree/main/.agents/skills/pr-walkthrough into .cursor/skills/pr-walkthrough/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-walkthrough", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/Terry-Mao/AICodingFlow.git --path .agents/skills/pr-walkthrough

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add Terry-Mao/AICodingFlow --skill pr-walkthrough -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Terry-Mao/AICodingFlow pr-walkthrough --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Terry-Mao/AICodingFlow.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/pr-walkthrough .gemini/skills/pr-walkthrough && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "pr-walkthrough" agent skill from https://github.com/Terry-Mao/AICodingFlow/tree/main/.agents/skills/pr-walkthrough into .gemini/skills/pr-walkthrough/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-walkthrough", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install Terry-Mao/AICodingFlow pr-walkthrough

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add Terry-Mao/AICodingFlow --skill pr-walkthrough -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/Terry-Mao/AICodingFlow.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/pr-walkthrough .github/skills/pr-walkthrough && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "pr-walkthrough" agent skill from https://github.com/Terry-Mao/AICodingFlow/tree/main/.agents/skills/pr-walkthrough into .github/skills/pr-walkthrough/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-walkthrough", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add Terry-Mao/AICodingFlow --skill pr-walkthrough -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Terry-Mao/AICodingFlow pr-walkthrough --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Terry-Mao/AICodingFlow.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/pr-walkthrough .opencode/skills/pr-walkthrough && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "pr-walkthrough" agent skill from https://github.com/Terry-Mao/AICodingFlow/tree/main/.agents/skills/pr-walkthrough into .opencode/skills/pr-walkthrough/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-walkthrough", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: pr-walkthrough
GitHub stars: 167
Token cost: ~2.1k tokens
SKILL.md length: 478 words
Files: 3 (incl. scripts)
Skills in repo: 30
Repo updated: Oct 3, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Generate a local static interactive D3 walkthrough of a pull request.

Works in 9 steps: 建立 PR 上下文 → 初始化输出路径 → 收集视觉素材 → …
The user wants a zoomable PR map
SKILL.md covers 输出, 视觉风格, 工作流 and 最终回复
Runs Python scripts from its folder; calls git, gh and python3; reaches cdn.jsdelivr.net and github.com

What it does

PR Walkthrough is an agent skill from Terry-Mao/AICodingFlow. Generate a local static interactive D3 walkthrough of a pull request. Use when the user wants a zoomable PR map, graph/canvas PR orientation, or alternate visualization of PR system components, data flow, code dependencies, and user actions.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/d3_canvas_runtime.py` and `scripts/validate_d3_canvas.py`).

It sits in Development, covering Pull requests. It works with GitHub. The repository describes itself as: Setup a AI Coding Flow. The licence is MIT.

When your agent uses it

The user wants a zoomable PR map
Graph/canvas PR orientation
Alternate visualization of PR system components
Code dependencies

Example prompts

“/pr-walkthrough”

Requirements

Python 3

Workflow steps

9 steps, taken from the step headings in SKILL.md.

建立 PR 上下文
初始化输出路径
收集视觉素材
构造 GitHub diff links
设计四个独立视图
写入数据模型
生成静态页面
验证
可选发布到 GitHub Pages

What it can do on your machine

Read from SKILL.md and the folder at commit 7703e16. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- git
- gh
- python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- cdn.jsdelivr.net
- github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

PR Walkthrough loads about 2.1k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 478 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~64
When it runs · the whole SKILL.md, loaded when a task matches: ~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Terry-Mao/AICodingFlow at commit 7703e16, republished under its MIT licence (© Terry-Mao). 478 words, ~2,057 tokens.

Download SKILL.mdSave it as .claude/skills/pr-walkthrough/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: pr-walkthrough
description: Generate a local static interactive D3 walkthrough of a pull request. Use when the user wants a zoomable PR map, graph/canvas PR orientation, or alternate visualization of PR system components, data flow, code dependencies, and user actions.

pr-walkthrough

为当前分支或 GitHub PR 生成一个本地静态 HTML 讲解页，帮助 reviewer 快速理解 PR 涉及的系统、数据流、代码依赖和用户路径。此技能不是代码评审技能，不生成新的 review finding、approval 或 request-changes 结论。

输出

生成文件到临时目录下的统一 slug 目录。默认本地产物根目录为 ${TMPDIR:-/tmp}/pr-walkthrough（并去掉末尾 /）；如果用户明确指定其他目录，可改用指定目录。

优先使用 PR number；无 PR number 时使用当前分支名：

text

$output_dir/graph.json
$output_dir/index.html

<short-sha> 是生成 walkthrough 时的 head commit 短 SHA。<sanitized-branch> 使用小写字母、数字和 -，把 /、空格和其他分隔符归一为 -。本地目录名和 GitHub Pages 路径必须使用同一个 slug。PR 更新后再次调用会因 short SHA 变化生成新目录；只有用户明确要求更新同一路径时才覆盖旧目录。不要把生成产物写入仓库目录，除非用户明确要求。

站点必须可以直接用 file:// 打开，不要求 dev server、打包器、安装依赖或构建步骤。优先生成单个自包含 HTML 文件，内联 CSS、JavaScript 和图数据；如果必须拆分资源，只使用相对路径，并避免用 fetch() 读取本地数据。

D3 使用固定版本的官方 CDN：

text

https://cdn.jsdelivr.net/npm/d3@7.9.0/dist/d3.min.js

优先使用本技能自带脚本生成和验证页面：

bash

python3 .agents/skills/pr-walkthrough/scripts/d3_canvas_runtime.py --template --data "$graph_json" > "$index_html"
python3 .agents/skills/pr-walkthrough/scripts/validate_d3_canvas.py --html "$index_html" --require-browser

视觉风格

不要套用任何公司视觉规范、专属字体、专属色或外部视觉规范技能。使用脚本内置的中性文档/工具界面样式即可。可以为四个视图使用不同的功能色，但颜色只表达信息类型，不表达品牌。

推荐视图颜色：

System overview view: #b7791f
Data flow graph: #0f7b5f
Code dependency graph: #2563eb
User action graph: #7c3aed
Active/focus/selected node: #2563eb

工作流

1. 建立 PR 上下文

识别仓库根目录、当前分支和比较 base。若用户 Prompt 明确给出 PR number、#<number> 或 PR URL，先把该编号记录为 pr_number。否则从当前分支的 GitHub PR 获取 pr_number，并优先使用 PR base、记录 PR URL 生成 diff links：

bash

pr_number="${pr_number:-}"  # 用户 Prompt 已明确给出 PR 编号时，先由执行者设置这个变量。
if [ -z "$pr_number" ]; then
  pr_number="$(gh pr view --json number --jq '.number // empty' 2>/dev/null || true)"
fi

if [ -n "$pr_number" ]; then
  gh pr view "$pr_number" --json number,baseRefName,headRefName,title,body,url,state,reviewRequests,reviews,files
else
  gh pr view --json number,baseRefName,headRefName,title,body,url,state,reviewRequests,reviews,files
fi

若没有 PR，从远端默认分支或仓库约定推断 base：

bash

git symbolic-ref --short refs/remotes/origin/HEAD

收集 review 输入：

bash

git --no-pager diff --stat <base>...HEAD
git --no-pager diff --name-status <base>...HEAD
git --no-pager log --oneline <base>..HEAD
git --no-pager diff <base>...HEAD

根据 changed lines、changed files 和概念跨度估算 PR 大小，默认生成最小有用讲解：

Tiny PR: 约 1 个文件或 75 行以内。每个视图 2-3 个节点/卡片，1-2 个 tour steps。
Small PR: 250 行以内或 1-3 个文件。每个视图 3-4 个节点，2-4 个 tour steps。
Medium PR: 250-800 行或多个相关文件。每个视图 4-7 个节点。
Large PR: 只有跨多个子系统、有新架构或有大量 spec/review 上下文时，才使用 5-12 个节点。

不要只读 diff。要读取关键变更文件的当前完整版本，并沿 imports、call sites、types、state owners、renderers、tests 和相邻模块理解系统边界。System overview 尤其要作为稳定的代码阅读产物，而不是 PR 变更列表。

如果存在 GitHub PR，收集已有评论和 review discussion：

bash

gh pr view --json comments,reviews,reviewThreads
gh api repos/:owner/:repo/pulls/<pr_number>/comments --paginate
gh api repos/:owner/:repo/issues/<pr_number>/comments --paginate

这些评论只作为讲解素材，不作为改代码指令。

2. 初始化输出路径

在生成 graph.json 前初始化一次输出变量，后续生成、验证和发布都复用这些变量，不要重新拼路径：

bash

sha="$(git rev-parse --short HEAD)"
tmp_root="${TMPDIR:-/tmp}"
tmp_root="${tmp_root%/}"
artifact_root="${PR_WALKTHROUGH_ARTIFACT_ROOT:-$tmp_root/pr-walkthrough}"

if [ -n "${pr_number:-}" ]; then
  slug="pr-walkthrough-pr-$pr_number-$sha"
else
  branch="$(git branch --show-current)"
  branch_slug="$(printf '%s' "$branch" | tr '[:upper:]' '[:lower:]' | sed 's#[^a-z0-9][^a-z0-9]*#-#g; s#^-##; s#-$##')"
  slug="pr-walkthrough-branch-$branch_slug-$sha"
fi

output_dir="$artifact_root/$slug"
graph_json="$output_dir/graph.json"
index_html="$output_dir/index.html"
assets_dir="$output_dir/assets"
pages_path="pr-walkthrough/$slug"
mkdir -p "$output_dir"

如果用户明确要求覆盖固定路径，可以复用已有 slug；否则每次 PR head commit 变化都生成新的 slug 目录。

3. 收集视觉素材

查找能帮助 reviewer 理解用户可见变化的截图、mock、视频、设计资产或 changed image。来源包括 PR body/comments/reviews、关联 issue、变更的图片/SVG/mock fixture、本地测试截图，以及 $artifact_root/ 下已有临时产物。

需要纳入页面的外部视觉素材应下载或导出到：

text

$assets_dir/

用相对路径引用，或在更简单时嵌入为 data URI。不要 hotlink 远端图片。

4. 构造 GitHub diff links

当已知 PR URL 时，每个 changed file reference、节点附件、代码摘录和依赖边都应链接到 PR 的 Files changed 页：

text

<pr_url>/files#diff-<file_anchor>
<pr_url>/files#diff-<file_anchor>R<new_line>
<pr_url>/files#diff-<file_anchor>L<old_line>

<file_anchor> 是变更文件路径的 lowercase SHA-256 hex digest。用确定性 helper 或脚本生成，不要手写猜测。

5. 设计四个独立视图

先构建数据模型，再生成 HTML。必须恰好包含四个视图：

system-overview: 受影响子系统的稳定架构概览。不要提 PR、changed files、diff links、review comments、screenshots、specs 或实现 delta。通常 edges: []，用较大的卡片和可读段落说明。
data-flow: 状态、数据、事件、请求、文件、资产或渲染输出如何流动。
code-dependency: 变更组件之间的依赖方向、入口点、边界和 leaf dependencies。
user-action: 用户从哪个 surface 开始，触发什么动作，看到什么反馈。

每个视图都需要自己的 nodes、edges 和 guided tour。除 system-overview 外，其他视图必须有有向边、箭头和描述 source-to-target 关系的 edge label。

每个节点回答：

reviewer 需要先理解什么？
此节点在这个视图中解释哪个概念？
哪些文件、spec、测试、视觉素材或已有评论能作为证据？
点击后 detail panel 应该展示什么？

Tour 顺序要教 reviewer 从起点读到终点，不要只是文件顺序。

Show full SKILL.md (197 more words)Show less

6. 写入数据模型

将图数据内联到 HTML，赋值给 window.PR_WALKTHROUGH_D3_DATA 或写入 id="pr-walkthrough-data" 的 JSON script。不要用 fetch() 加载本地 JSON。

数据形状：

json

{
  "meta": {
    "title": "PR title",
    "prUrl": "https://github.com/owner/repo/pull/123",
    "baseRef": "main",
    "headRef": "feature-branch",
    "summary": "What the PR is trying to accomplish."
  },
  "graphs": [
    {
      "id": "system-overview",
      "label": "System overview",
      "color": "#b7791f",
      "summary": "Concise component overview for the affected subsystem.",
      "nodes": [],
      "edges": [],
      "tour": []
    }
  ]
}

坐标建议：

起点放在左侧或上方。
Tour 路径尽量从左到右或从上到下。
相关节点靠近，低层依赖放在调用者右侧或下方。
小 PR 的图应紧凑到无需大量平移即可读懂。

7. 生成静态页面

可先生成样例数据，修改为真实 PR 数据，再渲染：

bash

python3 .agents/skills/pr-walkthrough/scripts/d3_canvas_runtime.py --sample-data > "$graph_json"
python3 .agents/skills/pr-walkthrough/scripts/d3_canvas_runtime.py --template --data "$graph_json" > "$index_html"

必备交互：

单个 D3 SVG canvas，支持 zoom、pan、fit-to-view 和 reset zoom。
四个 view toggles: System overview, Data flow graph, Code dependency graph, User action graph。
Tour controls: Previous tour step, Next tour step, Restart tour 和 step indicator。
Search input 可搜索 active graph 的 node titles、file paths 和 comments。
点击节点更新 detail panel，并在可能时同步到对应 tour step。
键盘支持：Right Arrow/n、Left Arrow/p、1-4、+/=、-、0、f、/、Escape。
稳定的 data-graph-id、data-node-id、data-edge-id、data-tour-index 属性，方便自动化截图和验证。

8. 验证

完成前必须运行：

bash

python3 .agents/skills/pr-walkthrough/scripts/validate_d3_canvas.py --html "$index_html" --require-browser

验证至少确认：

D3 使用固定版本 URL，未使用 latest。
页面不用 fetch() 读取本地数据。
图数据恰好包含 system-overview、data-flow、code-dependency、user-action。
必备控件存在。
每个视图都有节点和 tour。
非 overview 图都有有向边和箭头。
System overview 是 PR-agnostic 的架构概览，不带 PR 附件。
PR-changed specs 和已有 PR review comments 被纳入或明确报告为不存在/不可用。
视觉素材是本地相对路径或 data URI。

如果浏览器环境不可用，报告 canvas rendering 未验证，不要说 walkthrough 已完全 ready。

9. 可选发布到 GitHub Pages

默认只保留临时目录里的本地产物，不发布公网，也不提交生成 HTML。只有用户明确要求公开 URL 时才发布。发布前必须确认 PR 内容、截图、评论和代码上下文可以公开。

推荐使用 gh-pages 分支作为 Pages 来源，并把生成站点复制到临时 worktree，避免把生成物混入当前开发分支：

bash

site_dir="/tmp/aicodingflow-pr-walkthrough-pages-$slug"
git fetch origin gh-pages || true
git worktree add "$site_dir" gh-pages
mkdir -p "$site_dir/$pages_path"
cp -R "$output_dir/." "$site_dir/$pages_path/"
cd "$site_dir"
git add "$pages_path"
git commit -m "docs: publish PR walkthrough $slug"
git push origin gh-pages

如果仓库尚未启用 GitHub Pages，先让用户在仓库设置里选择 gh-pages 分支作为 Pages source，或在有权限时使用 GitHub API/CLI 配置 Pages。不要在未征得用户同意时更改仓库 Pages 设置。

发布后的 URL 通常为：

text

https://<owner>.github.io/<repo>/pr-walkthrough/<slug>/

最终回复

报告：

生成的 walkthrough 路径。
file:// URL。
使用的 base branch、PR title 或 branch name。
用于 diff links 的 GitHub PR URL。
是否找到并纳入 PR review comments。
D3 canvas validation 是否通过。
若发布，报告 GitHub Pages URL。
重要 caveats、缺失 specs 或无法完成的验证。

Files

SKILL.md and 2 other files (scripts) in .agents/skills/pr-walkthrough of Terry-Mao/AICodingFlow.

SKILL.md
scripts/d3_canvas_runtime.py
scripts/validate_d3_canvas.py

Open the folder on GitHubat commit 7703e16

Compare with similar skills

PR Walkthrough next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

PR Walkthrough compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
PR Walkthrough this skillTerry-Mao/AICodingFlow	167	—	~2.1k	Automated safety check: Pass	MIT	6 days ago
PR Babysitteropeninterpreter/openinterpreter	69k	3 repos	~4.2k	Automated safety check: Pass	Apache-2.0	2 days ago
Check PRonyx-dot-app/onyx	32k	2 repos	~2.3k	Automated safety check: Pass	MIT	today
Contributor-First PR MergeHKUDS/OpenHarness	16k	1 repos	~847	Automated safety check: Pass	MIT	4 mo ago
Create Pull Requestcline/cline	70k	1 repos	~1.6k	Automated safety check: Pass	Apache-2.0	today
Pull Request Title and Body Writeropeninterpreter/openinterpreter	69k	2 repos	~1.1k	Automated safety check: Pass	Apache-2.0	2 days ago

Similar skills

PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
69k GitHub starsUsed in 3 repos~4.2k tokens
DevelopmentAuto-check passed
Check PR
onyx-dot-app/onyx
Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.
32k GitHub starsUsed in 2 repos~2.3k tokens
DevelopmentAuto-check passed
Contributor-First PR Merge
HKUDS/OpenHarness
Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.
16k GitHub starsUsed in 1 repo~847 tokens
DevelopmentAuto-check passed
Create Pull Request
cline/cline
Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.
70k GitHub starsUsed in 1 repo~1.6k tokens
DevelopmentAuto-check passed
Pull Request Title and Body Writer
openinterpreter/openinterpreter
Rewrites the title and body of one or more pull requests with gh, leading with why the change was made, then what changed, and describing only the net result.
69k GitHub starsUsed in 2 repos~1.1k tokens
DevelopmentAuto-check passed
GitHub Review Iteration
prisma/orm
Official
Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.
48k GitHub stars~2.2k tokensUpdated today
DevelopmentAuto-check passed

Questions about PR Walkthrough

What does PR Walkthrough do?

Generate a local static interactive D3 walkthrough of a pull request. PR Walkthrough is an agent skill from Terry-Mao/AICodingFlow. Generate a local static interactive D3 walkthrough of a pull request.

When should I use PR Walkthrough?

PR Walkthrough fits situations like: the user wants a zoomable PR map; graph/canvas PR orientation; alternate visualization of PR system components; code dependencies.

How do I install PR Walkthrough in Claude Code?

Run `npx skills add Terry-Mao/AICodingFlow --skill pr-walkthrough -a claude-code`. Or copy the skill folder (.agents/skills/pr-walkthrough in Terry-Mao/AICodingFlow) into .claude/skills/pr-walkthrough in your project. Claude Code loads it when a task matches its description.

How do I install PR Walkthrough in Codex?

Run `npx skills add Terry-Mao/AICodingFlow --skill pr-walkthrough -a codex`. Or copy the skill folder (.agents/skills/pr-walkthrough in Terry-Mao/AICodingFlow) into .agents/skills/pr-walkthrough in your project. Codex loads it when a task matches its description.

Can I use PR Walkthrough in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Terry-Mao/AICodingFlow --skill pr-walkthrough -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pr-walkthrough, .gemini/skills/pr-walkthrough, .github/skills/pr-walkthrough and .opencode/skills/pr-walkthrough in your project.

What does PR Walkthrough need to run?

Going by SKILL.md and its folder, PR Walkthrough needs Python for the scripts in its folder and the command-line tools its instructions call (git, gh and python3). Our summary lists: Python 3.

Does PR Walkthrough access the network?

SKILL.md names 2 domains. In commands or code: cdn.jsdelivr.net and github.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is PR Walkthrough safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does PR Walkthrough use?

PR Walkthrough is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does PR Walkthrough use?

About 2.1k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to PR Walkthrough?

Skills that share tags, products or a category with PR Walkthrough: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PR Walkthrough?

Terry-Mao (a GitHub user) maintains it in Terry-Mao/AICodingFlow, which has 167 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 3, 2026.

Source: Terry-Mao/AICodingFlow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install PR Walkthrough

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

pr-walkthrough

输出

视觉风格

工作流

1. 建立 PR 上下文

2. 初始化输出路径

3. 收集视觉素材

4. 构造 GitHub diff links

5. 设计四个独立视图

6. 写入数据模型

7. 生成静态页面

8. 验证

9. 可选发布到 GitHub Pages

最终回复

Files

Compare with similar skills

Similar skills

More from Terry-Mao/AICodingFlow

Related

Questions about PR Walkthrough