create-pr

Included with Lifetime

$97 forever

Use this skill when the prompt asks to create, open, or submit a pull request in the bigquery-etl repository. Handles branch creation, staging, committing, pushing, and opening a draft PR with a structured description. Triggered by phrases like "create a PR", "open a PR", "submit a PR", "push and open a PR".

AI Agents

What this skill does


# create-pr

Create a pull request in the mozilla/bigquery-etl repository.

## When to Use

Invoke this skill when:
- The prompt contains "create a PR", "open a PR", "submit a PR", "push and open a PR"
- A workflow has produced files that are ready for review and need to be published

## Workflow

### Step 1: Determine Branch Name

Derive a branch name from the calling agent and table identifier:
- Format: `{agent-slug}/{table-slug}`, where `{agent-slug}` is the kebab-case name of the calling agent (e.g. `schema-creation-agent`, `query-writer`)
- If the calling agent is unknown or not applicable, use `feat` as the prefix
- `{table-slug}` is the table name with underscores replaced by hyphens, lowercase; include the dataset prefix only when needed for disambiguation
- Example: `cfs_ga4_attr_v1` in `firefox_desktop_derived` with agent `schema-creation-agent` → `schema-creation-agent/cfs-ga4-attr-v1`

Check if already on a feature branch:
```bash
git branch --show-current
```
If already on a non-`main` branch, skip branch creation. If on `main`, stash any uncommitted changes, pull latest, create the branch, then restore:
```bash
git stash
git pull origin main
git checkout -b {agent-slug}/{table-slug}
git stash pop
```

If there are no uncommitted changes, skip `git stash` and `git stash pop`.

### Step 2: Stage Generated Files

Stage only the files produced by the calling workflow. The calling agent specifies which files to stage. Stage each file explicitly — never use `git add -A` or `git add .`:

```bash
git add {file1}
git add {file2}
# ... for each file produced by the workflow
```

Omit any file that does not exist.

### Step 3: Commit

Derive the commit message from the work done by the calling workflow. Use the appropriate [conventional commit](https://www.conventionalcommits.org/) type (`feat`, `fix`, `chore`, etc.) as specified by the calling agent, defaulting to `feat` if not specified:

```bash
git commit -m "$(cat <<'EOF'
{type}({scope}): {short description of what was done}

- {one bullet per file or change}

Co-Authored-By: {model-name} <[email protected]>
EOF
)"
```

Replace `{model-name}` with the LLM used by the calling agent, not the model running this skill. The calling agent should pass this explicitly (e.g. the value of `model:` in its frontmatter, or `$ANTHROPIC_MODEL` if set).

### Step 4: Push

```bash
git push -u origin {agent-slug}/{table-slug}
```

If the push is rejected because the branch already exists on the remote and the local branch is ahead, use `--force-with-lease`:

```bash
git push -u origin {agent-slug}/{table-slug} --force-with-lease
```

### Step 5: Open Draft PR

Check if a PR already exists for this branch:

```bash
gh pr view --json url --jq '.url' 2>/dev/null
```

If a PR already exists, skip creation and use the returned URL. Otherwise, always open as a **draft** PR. Derive the title and body from the work done by the calling workflow:

```bash
gh pr create --draft \
  --title "{type}({scope}): {short description}" \
  --body "$(cat <<'EOF'
## Summary

{brief description of what was done and why}

## Changes

- `{file1}` — {what changed and why}
- `{file2}` — {what changed and why}

🤖 Generated with [Claude Code](https://claude.com/claude-code)
EOF
)"
```

Add one line per file produced by the workflow, following this format:
```
- `{file}` — {description}
```

Capture the PR number for use in Step 6 — run this regardless of whether the PR was just created or already existed:
```bash
gh pr view --json number --jq '.number'
```

### Step 6: Add Reviewers

Add all reviewers passed by the calling agent:

```bash
# for each reviewer passed by the calling agent:
gh pr edit {PR-number} --add-reviewer mozilla/{team-name}
# or for an individual:
gh pr edit {PR-number} --add-reviewer {github-username}
```

Then check the reviewers already added and add `mozilla/aero` if not among them:

```bash
gh pr view {PR-number} --json reviewRequests --jq '.reviewRequests[] | (.login // .slug)'
# if "aero" (the slug for mozilla/aero) is not in the output:
gh pr edit {PR-number} --add-reviewer mozilla/aero
```

## Output

Return to the user:
- The PR URL
- A summary of what was committed and which files were included

## Integration

This skill can be used as the final step in any agent workflow that produces files ready for review. The calling agent is responsible for completing its work before invoking this skill.

Files: 1

Size: 4.7 KB

Complexity: 10/100

Category: AI Agents

Source: https://github.com/mozilla/bigquery-etl-skills/tree/main/skills/create-pr

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts