New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

PR

by n0an in n0an/VivaDicta

Create a GitHub Pull Request in Claude Code with Claude and Codex review requests and built-in polling workflow

MITAuto-check passedMobile

Install PR

skills CLI
$ npx skills add n0an/VivaDicta --skill pr -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install n0an/VivaDicta pr --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/n0an/VivaDicta.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/pr .claude/skills/pr && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pr
GitHub stars
126
Token cost
~1.2k tokens
SKILL.md length
639 words
Files
2
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

Create a GitHub Pull Request in Claude Code with Claude and Codex review requests and built-in polling workflow

  • Works in 6 steps: First, check the current git status and… → If there are uncommitted changes, ask if… → Ensure the current branch is not… → …
  • Mobile work in your project
  • SKILL.md covers Task: Create a GitHub Pull…, IMPORTANT: Final Summary, Post-PR: Request Review and Poll and IMPORTANT: Review Inspection…, plus 3 more sections
  • Calls gh

What it does

PR is an agent skill from n0an/VivaDicta. Create a GitHub Pull Request in Claude Code with Claude and Codex review requests and built-in polling workflow

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Mobile. It works with GitHub. The repository describes itself as: iOS & watchOS speech-to-text app with AI voice keyboard, on-device RAG, and chat with your notes - powered by Apple Foundation Models, WhisperKit, NVIDIA Parakeet, and 20+ AI…. The licence is MIT.

When your agent uses it

  • Mobile work in your project

Example prompts

  • “/pr”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. First, check the current git status and uncommitted changes
  2. If there are uncommitted changes, ask if they should be committed first
  3. Ensure the current branch is not main/master
  4. Push the current branch to remote if needed
  5. Create the pull request using gh pr create with
  6. Return the PR URL when complete

What it can do on your machine

Read from SKILL.md and the folder at commit b141304. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

PR loads about 1.2k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 639 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from n0an/VivaDicta at commit b141304, republished under its MIT licence (© n0an). 639 words, ~1,195 tokens.

Download SKILL.mdSave it as .claude/skills/pr/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
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

pr

You are given the following context: $ARGUMENTS

Task: Create a GitHub Pull Request in Claude Code

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:

  1. First, check the current git status and uncommitted changes
  2. If there are uncommitted changes, ask if they should be committed first
  3. Ensure the current branch is not main/master
  4. Push the current branch to remote if needed
  5. Create the pull request using gh pr create with:
    • A clear, descriptive title
    • A comprehensive description including:
      • Summary of changes
      • Testing performed
      • Any breaking changes or notes
  6. Return the PR URL when complete

IMPORTANT: Final Summary

ALWAYS end your response with a clear summary that includes:

  • What was done (branch created, commits made, etc.)
  • The PR URL (e.g., "PR #123: https://github.com/owner/repo/pull/123")
  • Whether Claude review was requested
  • Whether Codex review was requested
  • The PR is ready for review

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.

Post-PR: Request Review and Poll

After the PR is created, always do the following (skip only if the user explicitly says not to):

  1. Request reviews by posting two comments on the PR:
    gh pr comment <PR_NUMBER> --body "@claude please review this PR"
gh pr comment <PR_NUMBER> --body "@codex please review this PR"
  2. Start polling for Claude and Codex review using /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
  3. Do not stop polling just because Claude replied first. Codex review usually takes longer.
  4. Keep polling until you see a real Codex comment or review, not just "in progress" status, or until a reasonable bounded wait expires.
  5. Show the returned review feedback to the user and ask "WDYT?" to discuss the findings before acting on them. If Claude replied but Codex has not yet replied, say that Codex review is still pending and keep polling until the bounded wait is reached.
Show full SKILL.md (297 more words)Show less

IMPORTANT: Review Inspection Hygiene

When checking review feedback, do not rely only on top-level PR reviews or summary comments.

  • Always inspect inline review comments / file-level threads too.
  • A generic top-level review body can still coexist with actionable inline comments.
  • Inline comments may be attached to an older reviewed commit on the same branch and still be worth evaluating.
  • Before dismissing a review as empty or boilerplate, check:
    • issue comments
    • PR reviews
    • pull request review comments / inline comments

Suggested extra check:

bash
gh api repos/<owner>/<repo>/pulls/<PR_NUMBER>/comments

Handling Review Feedback

  • Real critical bugs (regressions, data loss, crashes, security issues): fix them immediately without asking.
  • Everything else (style, theoretical issues, nice-to-haves, non-critical improvements): present to the user with your assessment and ask before fixing.

Merge Requests

If the user explicitly says merge, do not wait for CI to finish.

  • Merge the PR immediately using a regular merge commit.
  • Do not block on pending checks unless the user explicitly asks to wait.
  • If you see ongoing GitHub Actions build jobs for that PR or branch, submit a cancel request after merging instead of leaving them running.
  • Do not wait for GitHub to confirm the cancellation. One cancel request is enough unless the user explicitly asks you to verify.
  • Right after the merge, switch the local repository back to main.

Post-Merge: Update What's New

After the PR is merged, update the running What's New file in the Obsidian vault:

  • File: Projects/VivaDicta/what's new/whats-new-running.md in the vault at /Users/antonnovoselov/Documents/Vault/
  • Skip if the PR is a one-liner simple fix, bug fix, refactor, or minor cleanup that users wouldn't notice.
  • Add a concise, user-facing bullet point when the PR introduces a new feature or notable improvement. Write it from the user's perspective (what they can now do), not technical details. This file feeds into App Store Connect "What's New" release notes.

© n0an, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/pr of n0an/VivaDicta.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit b141304

Compare with similar skills

PR next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

PR compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PR this skilln0an/VivaDicta126—~1.2kAutomated safety check: PassMIT
Maa Issue Log AnalysisMaaAssistantArknights/MaaAssistantArknights24k—~4kAutomated safety check: PassAGPL-3.0
Workbuddy Skin Studiocdredfox/workbuddy-skin-studio196—~1.5kAutomated safety check: PassMIT
Fix CrashMartinStyk/apk-analyzer368—~2.5kAutomated safety check: PassGPL-3.0
Frb PR Chain Splitfzyzcjy/flutter_rust_bridge5.4k—~1.9kAutomated safety check: PassMIT
TriageK9i-0/ccpocket1.1k—~334Automated safety check: PassMIT

Similar skills

  • Maa Issue Log Analysis

    MaaAssistantArknights/MaaAssistantArknights

    分析 MaaAssistantArknights 上游仓库公开 Issue（https://github.com/MaaAssistantArknights/MaaAssistantArknights/issues/...

    24k GitHub stars~4k tokensUpdated today
    MobileAuto-check passed

  • Workbuddy Skin Studio

    cdredfox/workbuddy-skin-studio

    Apply a reversible theme/skin to the WorkBuddy desktop app (Tencent AI office agent) via local Chromium DevTools Protocol (CDP) injection.

    196 GitHub stars~1.5k tokensUpdated 2 mo ago
    MobileAuto-check passed

  • Fix Crash

    MartinStyk/apk-analyzer

    A skill your agent uses to fix a specific production crash or non-fatal — pulling its Crashlytics data, finding the linked GitHub issue, root-causing it, reproducing it, fixing it, and verifying the…

    368 GitHub stars~2.5k tokensUpdated 2 days ago
    MobileAuto-check passed

  • Frb PR Chain Split

    fzyzcjy/flutter_rust_bridge

    A skill your agent uses when an FRB PR contains independently landable work that should be extracted into predecessor PRs and connected as a GitHub PR chain without wasting full automatic CI.

    5.4k GitHub stars~1.9k tokensUpdated yesterday
    MobileAuto-check passed

  • Triage

    K9i-0/ccpocket

    GitHub Issueの対応判断と、PRの調査・手直し・検証・マージを行う。PR指定時は取り込みまで進めるのが既定. An agent skill from K9i-0/ccpocket.

    1.1k GitHub stars~334 tokensUpdated 5 days ago
    MobileAuto-check passed

  • Release Asc CLI

    rorkai/App-Store-Connect-CLI

    Publish and verify a new release of the App-Store-Connect-CLI repository.

    7.7k GitHub stars~2.4k tokensUpdated yesterday
    MobileAuto-check passed

More from n0an/VivaDicta

All 20 skills in this repo

  • Swiftdata Pro

    n0an/VivaDicta

    Writes, reviews, and improves SwiftData code using modern APIs and best practices.

    126 GitHub starsUsed in 1 repo~930 tokens
    Auto-check passed

  • iOS Simulator Skill

    n0an/VivaDicta

    21 production-ready scripts for iOS app testing, building, and automation.

    126 GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed

  • Asc Metadata Sync

    n0an/VivaDicta

    Sync and validate App Store metadata and localizations with asc, including legacy metadata format migration.

    126 GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed

  • Asc Aso Rankings

    n0an/VivaDicta

    Pull current keyword rankings from Astro MCP, compare against the previous rankings check, and save a new rankings file to the vault.

    126 GitHub stars~985 tokensUpdated 2 days ago
    Auto-check passed

  • Coverage Report

    n0an/VivaDicta

    Measure VivaDicta test code coverage from the terminal. An agent skill from n0an/VivaDicta.

    126 GitHub stars~1.2k tokensUpdated 2 days ago
    Auto-check passed

  • Loc Report

    n0an/VivaDicta

    Count Swift lines of code across the VivaDicta codebase and refresh the production-vs-test history chart.

    126 GitHub stars~825 tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about PR

What does PR do?

Create a GitHub Pull Request in Claude Code with Claude and Codex review requests and built-in polling workflow. PR is an agent skill from n0an/VivaDicta.

When should I use PR?

PR fits situations like: mobile work in your project.

How do I install PR in Claude Code?

Run `npx skills add n0an/VivaDicta --skill pr -a claude-code`. Or copy the skill folder (.agents/skills/pr in n0an/VivaDicta) into .claude/skills/pr in your project. Claude Code loads it when a task matches its description.

How do I install PR in Codex?

Run `npx skills add n0an/VivaDicta --skill pr -a codex`. Or copy the skill folder (.agents/skills/pr in n0an/VivaDicta) into .agents/skills/pr in your project. Codex loads it when a task matches its description.

Can I use PR in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add n0an/VivaDicta --skill pr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pr, .gemini/skills/pr, .github/skills/pr and .opencode/skills/pr in your project.

What does PR need to run?

Going by SKILL.md and its folder, PR needs the command-line tools its instructions call (gh).

Does PR access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is PR safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does PR use?

PR is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does PR use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to PR?

Skills that share tags, products or a category with PR: Maa Issue Log Analysis (MaaAssistantArknights/MaaAssistantArknights, 24k stars), Workbuddy Skin Studio (cdredfox/workbuddy-skin-studio, 196 stars), Fix Crash (MartinStyk/apk-analyzer, 368 stars) and Frb PR Chain Split (fzyzcjy/flutter_rust_bridge, 5.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PR?

n0an (a GitHub user) maintains it in n0an/VivaDicta, which has 126 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 5, 2026.

Source: n0an/VivaDicta on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.