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.
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.
About
Use cases: sales, productivity, agent-building
Reviews
Write a reviewNo 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 stopFrom judepayne/picode, MIT.
More from judepayne/picode
- 0.587score
orchestrate-subagents
judepayne
Use mediated subagent delegation through delegate_subagent and delegate_subagent_status.
SkillAFreshness: A★ 1Claude Code +9 - 0.497score
prompt-vars
judepayne
Use prompt vars for the active plan and design files, plus merged project/global agent-mode vars.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
planning-workflow
judepayne
Use a structured planning workflow to produce an implementation-ready Builder handoff grounded in the actual repository.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
automode-designer
judepayne
Designer-mode automode handoff rules for explicit user-started Design → Plan → Build automation.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
automode-planner
judepayne
Planner-mode automode rules for turning the active design into a Builder-ready plan and handing off to Builder.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
partner-reviewer
judepayne
Run the bounded Partner Reviewer workflow for implementations that changed five or more unique files.
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
automode-builder
judepayne
Builder-mode automode rules for implementing the active plan and clearing automode on stop.
SkillCFreshness: C★ 1Claude Code +9 - 0.426score
karpathy-coding-discipline
judepayne
Behavioral guidelines to reduce common LLM coding mistakes.
SkillDFreshness: D★ 1Claude Code +9
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
- Repository
- github.com/judepayne/picode
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from judepayne
- 0.587score
orchestrate-subagents
judepayne
Use mediated subagent delegation through delegate_subagent and delegate_subagent_status.
SkillAFreshness: A★ 1Claude Code +9 - 0.497score
prompt-vars
judepayne
Use prompt vars for the active plan and design files, plus merged project/global agent-mode vars.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
planning-workflow
judepayne
Use a structured planning workflow to produce an implementation-ready Builder handoff grounded in the actual repository.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
automode-designer
judepayne
Designer-mode automode handoff rules for explicit user-started Design → Plan → Build automation.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
automode-planner
judepayne
Planner-mode automode rules for turning the active design into a Builder-ready plan and handing off to Builder.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
partner-reviewer
judepayne
Run the bounded Partner Reviewer workflow for implementations that changed five or more unique files.
SkillCFreshness: C★ 1Claude Code +9
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.
Cite this page
pr-management skill. Agent Mart. https://agentmart.dev/skills/judepayne-pr-management (last updated 2026-10-24)