pr
Create pull requests with conventional titles using gh CLI. Use when creating PRs, opening pull requests, or pushing branches for review.
Best use case
pr is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Create pull requests with conventional titles using gh CLI. Use when creating PRs, opening pull requests, or pushing branches for review.
Teams using 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/pr/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How pr Compares
| Feature / Agent | pr | 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?
Create pull requests with conventional titles using gh CLI. Use when creating PRs, opening pull requests, or pushing branches for review.
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 pull requests with conventional commit-style titles using the `gh` CLI. Never add co-author labels. ## Title Format ``` <type>(<scope>): <subject> ``` Same types and scopes as conventional commits — see `/commit` skill for the full list. Keep titles under 72 characters. Use the description for details, not the title. ## Rules 1. **No co-author labels** — never add `Co-Authored-By` lines anywhere 2. Title follows conventional commit format: imperative mood, lowercase, no period 3. Description uses the structured template below 4. Always push the branch before creating the PR 5. Base branch defaults to `master` unless specified otherwise ## Steps 1. Check the current branch and understand the scope of changes: ```bash git branch --show-current git status git log --oneline master..HEAD git diff master...HEAD --stat ``` 2. **If on `master`** — you cannot push directly. Create a new branch first: ```bash git checkout -b <type>/<short-description> ``` Branch naming: `feat/add-report-notifications`, `fix/cron-duplicate`, `chore/bump-ui-kit`, etc. If there are uncommitted changes, they will carry over to the new branch. 3. If the branch has not been pushed yet: ```bash git push -u origin HEAD ``` 4. Analyze **all** commits on the branch (not just the latest) to draft the title and summary 4. Create the PR using a HEREDOC for the body: ```bash gh pr create --title "type(scope): subject line here" --body "$(cat <<'EOF' ## Summary - Brief bullet points explaining the changes ## Test plan - [ ] How to verify these changes work EOF )" ``` 5. Return the PR URL to the user ## Description Template ```markdown ## Summary - 1-3 bullet points describing what changed and why ## Test plan - [ ] Steps or checks to verify the changes ``` Keep it concise. No fluff, no emojis, no generated-by footers. ## Examples **Title examples:** ``` feat(console-ui): add scheduled report notifications fix(console-server): prevent duplicate cron triggers refactor(cloud-router): extract auth middleware into module chore: bump ui-kit to v0.15.0 across packages fix(ai-engineer): handle streaming timeout on large contexts ``` **Full example:** ```bash gh pr create --title "feat(console-ui): add scheduled report notifications" --body "$(cat <<'EOF' ## Summary - Add email and Slack notifications for scheduled report runs - Support configurable notification channels per report - Handle delivery failures with retry logic ## Test plan - [ ] Create a scheduled report and verify notification is sent - [ ] Test failure retry by simulating a delivery error - [ ] Verify notification preferences persist across sessions EOF )" ``` ## Options - To target a different base branch: `gh pr create --base <branch> ...` - To create as draft: `gh pr create --draft ...` - To add reviewers: `gh pr create --reviewer user1,user2 ...` - To add labels: `gh pr create --label "bug,priority" ...`
Related Skills
commit
Create conventional commit messages without co-author labels. Use when committing code changes or formatting git history.
codex-review
Run OpenAI Codex code review on current changes or review a plan/design. Use when user asks to review code, review implementation, or run codex review.
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
ui-demo
Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.
token-budget-advisor
Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: "token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or "token" refers to auth/session/payment tokens rather than response size.
skill-comply
Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines
santa-method
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.
safety-guard
Use this skill to prevent destructive operations when working on production systems or running agents autonomously.
repo-scan
Cross-stack source code asset audit — classifies every file, detects embedded third-party libraries, and delivers actionable four-level verdicts per module with interactive HTML reports.
project-flow-ops
Operate execution flow across GitHub and Linear by triaging issues and pull requests, linking active work, and keeping GitHub public-facing while Linear remains the internal execution layer. Use when the user wants backlog control, PR triage, or GitHub-to-Linear coordination.
product-lens
Use this skill to validate the "why" before building, run product diagnostics, and pressure-test product direction before the request becomes an implementation contract.
openclaw-persona-forge
为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡， 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。 如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。 当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。 不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Agent。 触发词：龙虾灵魂、虾魂、OpenClaw 灵魂、养虾灵魂、龙虾角色、龙虾定位、 龙虾剧本杀角色、龙虾游戏角色、龙虾 NPC、龙虾性格、龙虾背景故事、 lobster soul、lobster character、抽卡、随机龙虾、龙虾 SOUL、gacha。