PR Flow Cleanup Agent Skill

Cleans up merged pull request branches, synchronizes target base branches, and safely manages Git worktrees.

Context cost
1.1k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 4.2 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

清理已合并 PR 的 head branch(源分支),同步 base branch(目标分支),并删除本地分支。

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

developer toolsgit

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md4.2 kB · preview
--- name: pr-flow-cleanup ---
6# PR Flow Cleanup
7
8## 边界
9
10只处理已合并 PR 的 cleanup(清理)。会校验 PR 已合并、当前工作区干净、当前工作树位于 PR head branch(源分支)或最新远端目标提交的 detached HEAD(分离头),且 head branch 不等于 base branch(目标分支)。
11
12命令会定位到最新远端目标提交,并将本地 base branch(目标分支)安全快进到同一提交;随后安全同步当前工作树与目标分支状态,再按实时状态删除远端和本地 head branch(源分支)。若其他工作树已检出目标分支,cleanup(清理)仅在该工作树仍检出目标分支、工作区和暂存区干净、无进行中的 Git(版本管理)操作、提交未变化且本地提交是远端提交祖先时,才在该工作树执行 git merge --ff-only(仅快进合并);随后刷新本地 remote-tracking branch(远端跟踪分支)副本,并确认该副本、本地目标分支和当前提交均等于本轮最新远端目标提交;一致后,当前工作树保留在该提交的 detached HEAD(分离头),完成源分支清理并记录跳过切回的原因。若 primary worktree(主工作树)遇到 target/base branch(目标/基础分支)被其他 worktree(工作树)占用,无论是否传入 --remove-worktree(删除工作树参数),都必须在任何 Git 状态改变前停止;只有 linked non-primary target(关联非主目标工作树)可在安全条件下快进 occupied base(被占用的基础分支),并在切换前保护 occupied worktree(被占用工作树)的 active cwd(活跃当前目录)。工作树身份只按 Git worktree registration(Git 工作树登记)判定,不依赖 main 名称、路径名或宿主:--remove-worktree(删除工作树参数)作用于 primary worktree(主工作树)时不删除,完成后检出实际 target/base branch(目标/基础分支)的最新提交;registered linked non-primary worktree(已登记关联非主工作树)仅在 active session(活跃会话)位于其中时保留在该提交的 detached HEAD(分离头),从外部调用该关联工作树仍删除。任何需要切换提交且 active cwd(活跃当前目录)在目标提交中不存在又未被 Git(版本管理)忽略时,必须在切换前停止。任一检查、快进或一致性回读失败都会安全停止。若目标分支在检出时才被占用,命令会重新读取工作树清单并采用相同降级或停止规则。失败后可直接重试。默认保留 worktree(工作树);--remove-worktree(删除工作树参数)仅在安全收尾后生效。从 registered linked non-primary worktree(已登记关联非主工作树)外运行时,若显式删除工作树,仍先完成登记删除和实体目录核验;从被保留的关联工作树内运行时不要求外部交接,且永不强制删除;primary worktree(主工作树)不执行删除。若目标工作树由 Orca(工作区管理器)登记,命令优先使用 Orca(工作区管理器)的非强制删除;Orca(工作区管理器)未登记或不可用时回退 Git(版本管理)删除。已登记目标的 Orca(工作区管理器)删除失败时停止并保留诊断,不回退 Git(版本管理)删除。不合并 PR,不创建提交,也不修改 MySpec(自有规格)任务。
13
14cleanup 不查询 GitHub Branch Protection(GitHub 分支保护)或 Rulesets(规则集),也不自动配置远端保护规则;它只保证不删除 base branch。
15
16## 命令
17
18以本次加载的技能安装目录为基准,使用 ../pr-flow/scripts/pr_flow.py,确认脚本存在。
19
20下方填入本技能安装目录和目标项目目录的绝对路径;--project 始终指向用户目标项目,不指向插件目录。不切换当前目录;无法确认路径或脚本不存在时,停止并报告。
21
22```bash
23python "<本技能安装目录>/../pr-flow/scripts/pr_flow.py" cleanup --project "<目标项目目录>" --pr <number>
24```
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md121 words
Files1
Licencenot declared
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈30
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
1,020
on trigger
The instruction body, read only when the skill fires.
0.53%
of a 200k window
Ten skills this size would take about 5% of the window before you open a file.
050k100k150k200k context window

1.1k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Small enough to keep loaded permanently without thinking about it.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

1 file, 4.2 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md4.2 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# PR Flow Cleanup · 1.1k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/pr-flow-cleanup/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/pr-flow-cleanup" ] && { [ ! -e .claude/skills/pr-flow-cleanup ] || { mv .claude/skills/pr-flow-cleanup "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/pr-flow-cleanup" .claude/skills/ && echo "Installed .claude/skills/pr-flow-cleanup"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add liuli195/pr-flow-cleanup

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/pr-flow-cleanup/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/pr-flow-cleanup/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/pr-flow-cleanup" ] && { [ ! -e ~/.claude/skills/pr-flow-cleanup ] || { mv ~/.claude/skills/pr-flow-cleanup "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/pr-flow-cleanup" ~/.claude/skills/ && echo "Installed ~/.claude/skills/pr-flow-cleanup" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/pr-flow-cleanup/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referenceliuli195/pr-flow-cleanup

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill