pr-ready
Prepares a feature branch for pull request. Runs all checks, generates PR description, verifies documentation is updated, creates changelog entry, and suggests labels.
Best use case
pr-ready is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Prepares a feature branch for pull request. Runs all checks, generates PR description, verifies documentation is updated, creates changelog entry, and suggests labels.
Teams using pr-ready 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/pr-ready/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How pr-ready Compares
| Feature / Agent | pr-ready | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Prepares a feature branch for pull request. Runs all checks, generates PR description, verifies documentation is updated, creates changelog entry, and suggests labels.
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
# Skill: PR Ready ## What This Skill Does Automates the final preparation steps before opening a PR: run checks, write PR description, update changelog, and verify documentation updates. ## When to Use - When the user says "ready for PR", "open a PR", or "prepare for review" - After completing an `implement-phase` cycle - Before running `diff-review` Do NOT use this for the actual code review — use `diff-review` for that. ## Execution Model - **Always**: the primary agent runs this skill directly. - **Rationale**: PR preparation requires terminal access (git, CI), file editing (changelog), and user interaction (confirm PR title). - **Output**: a PR opened (or ready to open) on GitHub. ## Workflow ### Step 1: Verify Branch State ```bash # Ensure we're on a feature branch, not main git branch --show-current # Check for uncommitted changes git status # Check for unpushed commits git log origin/$(git branch --show-current)..HEAD --oneline 2>/dev/null ``` If there are uncommitted changes, ask the user whether to commit them first. ### Step 2: Run All Checks Run the project's CI checks locally: 1. Read `AGENTS.md` or `Makefile` for the check commands 2. Run them in order (lint → typecheck → test → build) 3. If any fail, ask the user whether to run `fix-ci` first or continue ### Step 3: Analyze the Diff Get the diff against the target branch: ```bash git diff main..HEAD --stat git diff main..HEAD --shortstat ``` Categorize the changes (source, tests, docs, config, deps). ### Step 4: Check Documentation Impact Run `validate-docs` patterns (lightweight, git-based): - If source files changed → check if corresponding docs exist and are recent - If public API changed → flag for doc update - If new module/feature added → flag missing docs Report findings but don't block — include in PR description as "Documentation Impact" section. ### Step 5: Update Changelog If a `CHANGELOG.md` exists: 1. Read the `[Unreleased]` section 2. Add entry for this PR under the appropriate category (Added/Changed/Fixed/Removed) 3. Use the commit messages as source material ### Step 6: Generate PR Description Build the PR description from: - **Summary**: one paragraph from commit messages - **Type of Change**: checkboxes (feature, fix, docs, etc.) - **Changes**: bullet list of key changes - **Documentation Impact**: from Step 4 - **Testing**: what tests were added/modified - **Checklist**: CI status, docs updated, changelog updated Use the project's PR template (`.github/pull_request_template.md`) if it exists. ### Step 7: Suggest Labels Based on the diff analysis, suggest GitHub labels: - File paths → category labels (e.g., `skills/` → `skill`, `agents/` → `agent`) - Commit prefixes → type labels (`feat:` → `feature`, `fix:` → `bug`) - Size → size labels (S/M/L based on lines changed) ### Step 8: Open or Preview PR Ask the user: - Confirm PR title - Confirm target branch (default: `main`) - Preview or directly open? ```bash gh pr create --title "<title>" --body-file /tmp/pr-body.md --label "<labels>" ``` ## Rules 1. **Never push to main**: this skill operates on feature branches only. 2. **Checks before PR**: always run local checks. Don't create a PR that will immediately fail CI. 3. **Use existing templates**: if the project has a PR template, use it. Don't override. 4. **Changelog is optional**: only update if the project has a CHANGELOG.md. Don't create one. 5. **Ask before opening**: always confirm with the user before creating the PR. They may want to review the description first. 6. **No built-in explore agent**: do NOT use the built-in `explore` subagent type.
Related Skills
repo-story-time
Generate a comprehensive repository summary and narrative story from commit history
release-notes
Generates structured release notes from git history between two references (tags, commits, branches). Groups changes by type (features, fixes, docs, breaking), extracts PR references, and produces a publish-ready document.
release-it
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "timeout strategy", "deployment pipeline", or "chaos engineering". Covers capacity planning, health checks, and anti-fragility patterns. For data systems, see ddia-systems. For system architecture, see system-design.
pyzotero
Interact with Zotero reference management libraries using the pyzotero Python client. Retrieve, create, update, and delete items, collections, tags, and attachments via the Zotero Web API v3. Use this skill when working with Zotero libraries programmatically, managing bibliographic references, exporting citations, searching library contents, uploading PDF attachments, or building research automation workflows that integrate with Zotero.
pydicom
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
perf-theory-gatherer
Use when generating performance hypotheses backed by git history and code evidence.
open-source-maintainer
End-to-end GitHub repository maintenance for open-source projects. Use when asked to triage issues, review PRs, analyze contributor activity, generate maintenance reports, or maintain a repository. Triggers include "triage", "maintain", "review PRs", "analyze issues", "repo maintenance", "what needs attention", "open source maintenance", or any request to understand and act on GitHub issues/PRs. Supports human-in-the-loop workflows with persistent memory across sessions.
git:notes
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.
my-pull-requests
List my pull requests in the current repository
multi-stage-dockerfile
Create optimized multi-stage Dockerfiles for any language or framework
mermaid-studio
Expert Mermaid diagram creation, validation, and rendering with dual-engine output (SVG/PNG/ASCII). Supports all 20+ diagram types including C4 architecture, AWS architecture-beta with service icons, flowcharts, sequence, ERD, state, class, mindmap, timeline, git graph, sankey, and more. Features code-to-diagram analysis, batch rendering, 15+ themes, and syntax validation. Use when users ask to create diagrams, visualize architecture, render mermaid files, generate ASCII diagrams, document system flows, model databases, draw AWS infrastructure, analyze code structure, or anything involving "mermaid", "diagram", "flowchart", "architecture diagram", "sequence diagram", "ERD", "C4", "ASCII diagram". Do NOT use for non-Mermaid image generation, data plotting with chart libraries, or general documentation writing.
git:merge-worktree
Merge changes from worktrees into current branch with selective file checkout, cherry-picking, interactive patch selection, or manual merge