openup-create-pr

Create a pull request with proper description linking to roadmap task context

6 stars

Best use case

openup-create-pr is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Create a pull request with proper description linking to roadmap task context

Teams using openup-create-pr should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/openup-create-pr/SKILL.md --create-dirs "https://raw.githubusercontent.com/GermanDZ/open-up-for-ai-agents/main/docs-eng-process/.claude-templates/skills/openup-create-pr/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/openup-create-pr/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How openup-create-pr Compares

Feature / Agentopenup-create-prStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Create a pull request with proper description linking to roadmap task context

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Create Pull Request

Create a PR with a structured description linked to roadmap task context.

## Process

### 1. Detect Current State

1. Use `$ARGUMENTS[branch]` or `git rev-parse --abbrev-ref HEAD`.
2. Check for unmerged commits: `git log <trunk>..HEAD --oneline`. Exit if none.
3. Detect platform: `command -v gh` (GitHub) or `command -v glab` (GitLab).
4. Verify remote: `git remote get-url origin`.

### 2. Prepare Commits

1. **Trunk guard**: If on trunk (main/master/detected), create and switch to a feature branch (`git checkout -b feature/...` or `fix/...`).
2. **Check uncommitted changes**: `git status --porcelain`. If clean, skip to step 3.
3. **Organize atomic commits**: Group changes into logical units. Commit in dependency order (deps/config → types/interfaces → core logic → dependent features). Follow format from `docs-eng-process/conventions.md`.
4. **Apply test strategy**: Bundle tests with feature commits. For bug fixes, commit failing test first, then the fix.
5. **Lint before committing**: Run linter/formatter before each commit. Skip if none configured.
6. Full rules: `commit-procedure.md` in `complete-task/`.

### 3. Extract Task Context

1. Get task_id from `$ARGUMENTS[task_id]` or extract from branch name (regex `([Tt]-?\d+)`).
2. Read `docs/roadmap.md`, find task section, extract description/priority/status.
3. Generate title: `[<task_id>] <description>` or use `$ARGUMENTS[title]`.

### 4. Detect Trunk Branch

Use `$ARGUMENTS[base]` if provided; otherwise follow trunk detection in `docs-eng-process/agent-workflow.md` (Branching SOP). Record detected trunk in run log.

### 5. Generate PR Description

Use template from `docs-eng-process/templates/pr-description.md` and populate:
- Summary, Task Context (id, description, priority), Changes Made (git diff/log)
- Testing Performed, Review Checklist, Related Issues, Breaking Changes, Notes

### 6. Push Branch and Create PR

```bash
git push -u origin <branch>
# GitHub:
gh pr create --base <base> --title "<title>" --body "<description>" --label "task:<task_id>"
# GitLab:
glab mr create --base <base> --title "<title>" --description "<description>" --label "task:<task_id>"
```

### 7. Update Documentation (Optional)

- `docs/roadmap.md`: Add PR URL to task entry
- `docs/project-status.md`: Note PR in Active Work Items

## Common Errors

| Error | Cause | Solution |
|-------|-------|----------|
| No unmerged commits | Branch up to date with trunk | Inform user no PR needed |
| No remote configured | Git remote not set up | `git remote add origin <url>` |
| CLI not installed | gh/glab not available | `brew install gh` or `brew install glab` |
| No task_id found | Branch name has no task ID | Proceed without task context or provide manually |
| Roadmap not found | docs/roadmap.md missing | Proceed without task context, inform user |
| PR already exists | Branch already has open PR | Inform user of existing PR URL |
| On trunk branch | Working directly on main/master | Auto-create feature branch before committing |

## References

- Branching SOP: `docs-eng-process/agent-workflow.md`
- PR Description Template: `docs-eng-process/templates/pr-description.md`
- Roadmap: `docs/roadmap.md`

## See Also

- [openup-complete-task](../complete-task/SKILL.md) - Complete task and create PR
- [openup-start-iteration](../start-iteration/SKILL.md) - Start iteration with branch creation

Related Skills

openup-transition

6
from GermanDZ/open-up-for-ai-agents

Initialize and manage Transition phase activities - deploy to users

openup-tdd-workflow

6
from GermanDZ/open-up-for-ai-agents

Guide Test-Driven Development cycle adapted for AI agents with a pragmatic approach

openup-sync-spec

6
from GermanDZ/open-up-for-ai-agents

Back-propagate pure refactors to stale artifacts; classify the diff, refuse behaviour-changes, propose targeted edits for approval (read-only by default)

openup-start-iteration

6
from GermanDZ/open-up-for-ai-agents

Begin a new OpenUP iteration with proper phase context and task selection

openup-shared-vision

6
from GermanDZ/open-up-for-ai-agents

Create shared technical vision for team alignment

openup-retrospective

6
from GermanDZ/open-up-for-ai-agents

Generate iteration retrospective with feedback and action items

openup-request-input

6
from GermanDZ/open-up-for-ai-agents

Create an input request document for asynchronous stakeholder communication

openup-readiness

6
from GermanDZ/open-up-for-ai-agents

Compute the change-folder dependency DAG and print READY/BLOCKED/collision report for PM intake

openup-quick-task

6
from GermanDZ/open-up-for-ai-agents

Fast iteration mode for small changes - simplified workflow with minimal overhead

openup-plan-feature

6
from GermanDZ/open-up-for-ai-agents

Generate iteration plan and roadmap entry for a feature idea

openup-phase-review

6
from GermanDZ/open-up-for-ai-agents

Check phase completion criteria and prepare for phase review

openup-orchestrate

6
from GermanDZ/open-up-for-ai-agents

Run a full orchestrated iteration — PM decomposes the goal, delegates to specialist roles, collects outputs, and synthesizes results