Agent skill

PR

by softspark in softspark/ai-toolkit

Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits.

Apache-2.0Auto-check: notesDevelopment

Install PR

skills CLI
$ npx skills add softspark/ai-toolkit --skill pr -a claude-code

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

GitHub CLI
$ gh skill install softspark/ai-toolkit 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/softspark/ai-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/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
179
Token cost
~1.5k tokens
SKILL.md length
677 words
Files
2 (incl. scripts)
Skills in repo
112
Repo updated
First seen
Licence
Apache-2.0

At a glance

Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits.

  • Works in 2 steps: Pre-PR Checks → Create PR
  • Tasks that involve Pull requests
  • SKILL.md covers Project context, Usage, Automated PR Summary Generation and PR Creation Workflow, plus 6 more sections
  • Runs Python scripts from its folder; calls gh and python3

What it does

PR is an agent skill from softspark/ai-toolkit. Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits. Triggers: pr, pull request, create PR, ready to merge.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/pr-summary.py`).

It sits in Development, covering Pull requests. It works with GitHub. The repository describes itself as: Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI… The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Pull requests

Example prompts

  • “Use the pr skill to create GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits”
  • “/pr”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Bash, Read, Grep

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Pre-PR Checks
  2. Create PR

What it can do on your machine

Read from SKILL.md and the folder at commit d64db2b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • gh
    • python3

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

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    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 1.5k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 677 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Grep

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); the scripts in this folder are not scanned.

SKILL.md

The full file from softspark/ai-toolkit at commit d64db2b, republished under its Apache-2.0 licence (© softspark). 677 words, ~1,466 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
Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits. Triggers: pr, pull request, create PR, ready to merge.
allowed-tools
Bash, Read, Grep
effort
medium
disable-model-invocation
true
argument-hint
[title or branch]

Pull Request

$ARGUMENTS

Create or update the task's GitHub pull request after project-specific checks. When called by /autonomous-dev, preserve its run ID, branch, PR identity, approval history and evidence. This skill publishes the PR; the calling process owns subsequent review, QA and required-CI completion.

Project context

  • Inspect the actual repository, branch and working tree. Resolve the base from an existing PR first, then project configuration or the remote default branch. Do not assume a branch named main exists.

Usage

/pr [title]

Automated PR Summary Generation

Generate a structured PR summary from the commit history before writing the PR description:

bash
python3 ${CLAUDE_SKILL_DIR}/scripts/pr-summary.py [base_branch]
# Pass the resolved PR base explicitly, for example develop.

The script outputs JSON with:

  • title_suggestion: auto-generated PR title from dominant commit type and scope
  • commits[]: each commit parsed into type, scope, description (conventional commits)
  • groups: commits grouped by type (Features, Bug Fixes, etc.)
  • summary_bullets: ready-to-use summary lines for the PR body
  • has_breaking: whether any BREAKING CHANGE markers were found
  • breaking_changes[]: list of breaking change descriptions
  • files_changed: total files in the diff
  • test_files_changed: count of test files modified
  • has_tests: whether the PR includes test changes

Use the output to populate the PR template fields below.


PR Creation Workflow

1. Pre-PR Checks

Read the project's instructions, CI configuration and package/Make scripts. For an autonomous run, use the commands frozen in its plan from .ai-toolkit/autonomous.json. Run the actual lint, typecheck, test and build commands applicable to that project; a Python command is not a universal gate. Inspect every result and preserve evidence of the tested commit. Missing runtime services or failed commands are blockers, never successful checks.

Verify that the authorized changes are committed, the intended base exists, and the diff contains only the task's work. Use the resolved base with a triple-dot diff for PR scope. Preserve unrelated dirty work and report it.

2. Create PR

Verify the repository and active account. Search for an existing PR from the exact head branch before creation, including after an interrupted publication. Update that PR when it represents this task. Never open a duplicate merely because a previous assistant message omitted its URL.

Use the repository's template and write the exact body with an editing tool to an absolute temporary file outside the checkout. Pass it through a structured connector argument or gh --body-file, preserving real newlines. For example, with actual repository/branch values and the prepared body file:

bash
gh pr create --base develop --head feat/csv-export --title "feat: export filtered orders" --body-file /absolute/run/pr-body.md

Publishing must already be authorized by the task and allowed by the current host. A missing permission leaves a prepared, reviewable result and a concrete blocker. Creating a PR does not authorize merging it. Record the returned URL immediately in the autonomous run before continuing.

Show full SKILL.md (251 more words)Show less

PR Template

markdown
## Summary
<1-3 bullet points describing changes>

## Changes
- [ ] Feature implementation
- [ ] Tests added/updated
- [ ] Documentation updated

## Test plan
- [ ] CI checks pass (lint, typecheck, tests)
- [ ] Manual testing completed
- [ ] No regressions

## Screenshots
<if applicable>

PR Checklist

Before creating PR:

  • Project tests and required build pass for the current commit
  • Applicable linting and type checking pass
  • Actual base/head and repository are verified; an existing PR is reused
  • Documentation updated if needed
  • Commit messages follow conventional commits
  • Changes against the actual base are reviewed; merge conflicts are resolved

Useful gh Commands

bash
# View PR
gh pr view

# Check PR status
gh pr checks

# Inspect the current head and review state
gh pr view --json url,headRefOid,baseRefName,reviewDecision,mergeStateStatus

Rules

  • MUST run the project's applicable validation commands before opening the PR
  • NEVER force-push main or master
  • NEVER add AI co-authorship or generated-by signatures to commits or the PR body
  • CRITICAL: PR body must include a Test plan checklist — no exceptions
  • MANDATORY: commit messages follow conventional commits (feat:, fix:, docs: etc.)

Gotchas

  • gh defaults to github.com; for GitHub Enterprise the host must be set per-repo with gh auth login --hostname <host> and gh repo set-default. Silent failures on enterprise usually mean the wrong host.
  • Running gh pr create without --body opens an editor ($EDITOR or vi) — in non-interactive contexts this hangs indefinitely. Always pass --body or --body-file.
  • A local validation pass does not prove required remote CI or human approval. Report pending conditions; /autonomous-dev waits for them before completion.
  • A triple-dot diff uses the merge-base. Use the resolved PR base rather than substituting a hardcoded branch name.

When NOT to Use

  • For creating a commit (without a PR) — use /commit
  • For reviewing a PR someone else opened — use /review
  • For drafting release notes across many PRs — use /docs or a release script
  • When the branch has uncommitted changes — commit first, then open the PR

© softspark, Apache-2.0. 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 (scripts) in app/skills/pr of softspark/ai-toolkit.

  • SKILL.md
  • scripts/pr-summary.py

Open the folder on GitHubat commit d64db2b

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 skillsoftspark/ai-toolkit179—~1.5kAutomated safety check: NotesApache-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Pull Request Title and Body Writeropeninterpreter/openinterpreter69k2 repos~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed
  • Pull Request Title and Body Writer

    openinterpreter/openinterpreter

    Rewrites the title and body of one or more pull requests with gh, leading with why the change was made, then what changed, and describing only the net result.

    69k GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from softspark/ai-toolkit

All 112 skills in this repo
  • Prepare Test Env

    softspark/ai-toolkit

    Prepare or verify a project QA environment with source identity, readiness, browser access, evidence paths and owned cleanup.

    179 GitHub stars~1.8k tokensUpdated today
    Auto-check: notes
  • A11y Validate

    softspark/ai-toolkit

    Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. An agent skill from softspark/ai-toolkit.

    179 GitHub stars~3.8k tokensUpdated today
    Auto-check: notes
  • Analyze

    softspark/ai-toolkit

    Analyzes code quality, complexity, patterns across codebase.

    179 GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Autonomous Dev

    softspark/ai-toolkit

    Drives a brief, specification, issue or existing PR through implementation, review, tests and QA to a ready PR.

    179 GitHub stars~2.6k tokensUpdated today
    Auto-check: notes
  • Brand Voice

    softspark/ai-toolkit

    Direct technical voice for docs, README, user-facing text. An agent skill from softspark/ai-toolkit.

    179 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • CI

    softspark/ai-toolkit

    Detect/generate/debug CI pipeline config (GitHub Actions, GitLab CI).

    179 GitHub stars~1.1k tokensUpdated today
    Auto-check: notes

Works with

Categories

Questions about PR

What does PR do?

Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits. PR is an agent skill from softspark/ai-toolkit. Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits.

When should I use PR?

PR fits situations like: tasks that involve Pull requests.

How do I install PR in Claude Code?

Run `npx skills add softspark/ai-toolkit --skill pr -a claude-code`. Or copy the skill folder (app/skills/pr in softspark/ai-toolkit) 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 softspark/ai-toolkit --skill pr -a codex`. Or copy the skill folder (app/skills/pr in softspark/ai-toolkit) 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 softspark/ai-toolkit --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 Python for the scripts in its folder and the command-line tools its instructions call (gh and python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash, Read, Grep.

Does PR access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is PR safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does PR use?

PR is published under the Apache-2.0 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 1.5k tokens (SKILL.md is roughly 5.9k 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: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PR?

softspark (a GitHub user) maintains it in softspark/ai-toolkit, which has 179 GitHub stars. The repository holds 112 skills in this directory. The repository was last updated on October 7, 2026.

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