一键导入
pr
Create a GitHub Pull Request in Claude Code with Claude and Codex review requests and built-in polling workflow
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Create a GitHub Pull Request in Claude Code with Claude and Codex review requests and built-in polling workflow
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Run an ASO audit on canonical App Store metadata under `./metadata`, then a krankie-based competitor keyword-gap analysis (no Astro subscription). Krankie replacement for asc-aso-audit. Use after `asc metadata pull`.
Pull VivaDicta App Store keyword rankings via krankie (free, self-hosted), compare against the previous check, and write a dated rankings report to the Obsidian vault. Krankie-based replacement for asc-aso-rankings (no Astro subscription required).
Prepare a new VivaDicta release — version bump, What's New screen, App Store metadata, code sweep, and pre-submission checklist
Measure VivaDicta test code coverage from the terminal. Use when asked what the test coverage is, a module's or the whole-app coverage %, which lines/files are covered, to get coverage without opening Xcode, or to see coverage after writing tests. Covers both the fast per-SPM-module path (swift test + llvm-cov) and the canonical whole-app path (xcodebuild + xccov), and which first-party targets count.
Count Swift lines of code across the VivaDicta codebase and refresh the production-vs-test history chart. Use when asked how many LOC / lines of code the project has, for a codebase-size or LOC breakdown by SPM module / main app / extension, how big a module or extension is, the prod-vs-test ratio, or to update / regenerate the LOC growth chart embedded in documentation/Module-Architecture.md.
Writes, reviews, and improves Swift Testing code using modern APIs and best practices. Use when reading, writing, or reviewing projects that use Swift Testing.
| name | pr |
| description | Create a GitHub Pull Request in Claude Code with Claude and Codex review requests and built-in polling workflow |
| disable-model-invocation | true |
You are given the following context: $ARGUMENTS
This skill is the Claude Code-specific PR workflow. In Codex, use $prcdx instead.
Based on the provided context, create a pull request following these steps:
gh pr create with:
ALWAYS end your response with a clear summary that includes:
Format the PR link prominently so it's easy to find.
If no arguments are provided, create a PR with auto-generated title and description based on the commit history.
Use appropriate flags like --draft if the PR is work in progress.
After the PR is created, always do the following (skip only if the user explicitly says not to):
gh pr comment <PR_NUMBER> --body "@claude please review this PR"
gh pr comment <PR_NUMBER> --body "@codex please review this PR"
/loop 2m to check PR comments, PR reviews, and inline review comments every 2 minutes:
gh pr view <PR_NUMBER> --json comments,reviews,url
gh api repos/<owner>/<repo>/issues/<PR_NUMBER>/comments
gh api repos/<owner>/<repo>/pulls/<PR_NUMBER>/comments
When checking review feedback, do not rely only on top-level PR reviews or summary comments.
Suggested extra check:
gh api repos/<owner>/<repo>/pulls/<PR_NUMBER>/comments
If the user explicitly says merge, do not wait for CI to finish.
main.After the PR is merged, update the running What's New file in the Obsidian vault:
Projects/VivaDicta/what's new/whats-new-running.md in the vault at /Users/antonnovoselov/Library/Mobile Documents/iCloud~md~obsidian/Documents/Second Brain Vault/