Skip to content
Agentmart
Submit a tool

pr-management

Use the team-lead subagent to run a staged PR workflow.

Skill by judepayne

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying pr-management?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/judepayne-pr-management

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use the team-lead subagent to run a staged PR workflow. Invoke when the user mentions a PR, a diff, or wants to delegate a multi-file change end-to-end with explicit checkpoints.

Use cases: sales, productivity, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/pr-management

What's inside

Skill name
pr-management
Description
Use the team-lead subagent to run a staged PR workflow. Invoke when the user mentions a PR, a diff, or wants to delegate a multi-file change end-to-end with explicit checkpoints.
License
MIT
Instructions
85 lines in SKILL.md · view on GitHub

Files (2)

  • README.md
  • SKILL.md

SKILL.md (first lines)

# PR Management

Use the `team-lead` subagent when the user wants to:
- assess and implement a PR in stages
- delegate a multi-file change end-to-end
- checkpoint after assessment and planning before continuing

## Parent-agent role

In this workflow, the parent agent remains in charge of the user conversation.

The pattern is:
1. launch `team-lead`
2. receive a stage handback
3. ask the user for the decision
4. resume the same child with explicit continuation

The parent should not expect `team-lead` to talk directly to the user.

## First launch

Start the workflow with a fresh delegated run:

```text
Use the team-lead subagent to assess PR #123: the auth refactor. Read the diff and related code, return the assessment, and stop for my decision.
```

## Continuing the same workflow

When the team-lead hands back, note the returned `childSessionId` from the delegation details.

Then resume the same child explicitly, for example:

```json
{
  "agent": "team-lead",
  "context": "continue",
  "childSessionId": "<child-session-id>",
  "task": "User approved. Produce the implementation plan and stop for plan approval."
}
```

And later:

```json
{
  "agent": "team-lead",
  "context": "continue",
  "childSessionId": "<child-session-id>",
  "task": "Plan approved. Execute the plan, use workers in parallel where appropriate, then run review and return the final handback."
}
```

## Expected handback

Each team-lead stage should return:
- Stage
- Status
- Next
- Summary
- Artifacts
- Failures

The important point is that the handback tells the parent whether to ask the user something or continue the workflow.

## Nested team shape

The team-lead manages these stages internally:

| Stage | Who does it | Notes |
|-------|-------------|-------|
| Assess | team-lead + optional scouts | Returns assessment handback |
| Plan | team-lead + optional scouts | Returns plan handback |
| Execute | worker(s) | Can fan out in parallel |
| Review | reviewer(s) | Returns final verdict |

## Guidelines

- Provide the PR number, branch name, or diff context in the initial task
- Do not pre-approve later stages in the first launch
- Treat the user checkpoints as parent-agent responsibilities
- If a nested worker fails, the team-lead should stop and report it
- If review finds serious issues, the parent should decide whether to continue the same thread or stop

From judepayne/picode, MIT.

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Apr 23, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from judepayne

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get pr-management running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying pr-management?

CallGet help
Cite this page

pr-management skill. Agent Mart. https://agentmart.dev/skills/judepayne-pr-management (last updated 2026-10-24)