本文へ移動
cccskills
無料GitHub で公開

pr

Create a GitHub Pull Request with full AI review. Human approves and merges.

日本語の概要は準備中です。原文の説明を表示しています。

連携ツールGitHub
インストール方法を見る

含まれるファイル(1)

  • SKILL.md4.1 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

PR — Create Pull Request with AI Review

Create a GitHub Pull Request with full AI review. Human approves and merges — do NOT merge automatically; always stop after PR creation and AI review.

Step 0 — Smart default: ensure feature branch

PROJECT_ROOT=$(git rev-parse --show-toplevel)
cd "$PROJECT_ROOT"
DEFAULT_BRANCH=$(git symbolic-ref refs/remotes/origin/HEAD 2>/dev/null | sed 's@^refs/remotes/origin/@@')
DEFAULT_BRANCH="${DEFAULT_BRANCH:-main}"
CURRENT_BRANCH=$(git branch --show-current)

If on the default branch: Run the branch workflow first to create a feature branch. Then continue.

If on a feature branch: Continue with PR creation.


Phase 1 — Pre-flight

Run the gate workflow. All gates must pass before creating a PR (Gates 1–3 always; Gates 4–5 when applicable).

If any gate fails → STOP. Fix issues first. Do NOT create a PR with failing gates.


Phase 2 — Push branch

git push -u origin "$CURRENT_BRANCH"

Phase 3 — Generate PR content

Title

  • Derive from branch name and commit messages
  • Under 70 characters
  • Use conventional format: feat: add user authentication

Body

Generate from the diff against the default branch:

git log "$DEFAULT_BRANCH"..HEAD --oneline
git diff "$DEFAULT_BRANCH"...HEAD --stat

Structure the body as:

## Summary
- [2-3 bullet points describing what changed and why]

## Changes
- [list of key files/areas modified]

## Test plan
- [ ] [How this was tested]
- [ ] [What to verify during review]

## Related issues
[Auto-detected from commit messages: "fixes #42", "closes #13", etc.]

Phase 4 — Create PR

gh pr create \
  --title "<generated title>" \
  --body "<generated body>" \
  --base "$DEFAULT_BRANCH" \
  --head "$CURRENT_BRANCH"

Capture the PR number and URL from the output.


Phase 5 — AI Review

Review the full diff and post findings as a PR comment.

What to review

# Get the full diff for review
git diff "$DEFAULT_BRANCH"...HEAD

Analyze the diff across 5 categories:

1. Code quality

  • Clean code, naming, complexity, DRY, dead code
  • Large functions or files that need splitting
  • Unclear logic that needs comments

2. Spec compliance

  • Does the code match the PR title and description
  • Are all claimed changes actually present
  • Are there unclaimed changes (scope creep)

3. Security

  • SQL injection, XSS, command injection risks
  • Hardcoded secrets, API keys, tokens
  • Authentication and authorization gaps
  • OWASP top 10 patterns

4. Test coverage

  • Are new code paths tested
  • Are edge cases covered
  • Test quality — do tests verify behavior or just mock everything

5. Breaking changes

  • API signature changes (added/removed/changed parameters)
  • Database schema changes
  • Configuration changes
  • Removed or renamed exports
  • Changed default behavior

Post review as PR comment

gh pr comment <PR_NUMBER> --body "<review content>"

Review format:

## 100x Dev — AI Review

### Summary
[1-2 sentence overall assessment]

### Findings

#### Critical (must fix before merge)
- [file:line] [description]

#### Important (should fix)
- [file:line] [description]

#### Minor (consider fixing)
- [file:line] [description]

### Checklist
- [ ] All critical findings addressed
- [ ] Tests cover new code paths
- [ ] No secrets in diff
- [ ] No breaking changes (or documented)

### Verdict: ✅ APPROVE / ⚠️ CHANGES REQUESTED / ❌ BLOCK

If no issues found:

## 100x Dev — AI Review

### Summary
Clean implementation. No issues found.

### Verdict: ✅ APPROVE

Phase 6 — Stop (Human-in-the-Loop)

DO NOT MERGE. Print the PR summary and stop — merge is the human's responsibility.

PULL REQUEST CREATED
PR:      #<number> — <title>
Branch:  <branch> → <default_branch>
Review:  AI review posted ✅ | Gate: ✅ all passed
URL:     <pr_url>
STATUS:  Awaiting human approval. DO NOT auto-merge.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

Act as a Senior Accessibility Engineer to audit a page, component, or design against WCAG 2.2 AA. Produces a triaged finding list (critical/serious/moderate), focus-order map, contrast report, ARIA decision tree, and a screen-reader test plan. Use when shipping new UI, hardening an existing flow, or preparing for VPAT/accessibility conformance.

日本語の概要は準備中です。原文の説明を表示しています。

rajitsaha/100xprism102026年10月14日 更新

When the user wants to plan, design, or implement an A/B test or experiment — "split test," "variant copy," "multivariate test," "hypothesis," "statistical significance," "how long should I run this test," or comparing two versions. For tracking implementation, see analytics-tracking. For page-level conversion optimization, see page-cro.

日本語の概要は準備中です。原文の説明を表示しています。

rajitsaha/100xprism102026年10月14日 更新

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, full variations — for any paid platform; 'ad copy variations,' 'RSA headlines,' 'bulk ad copy,' 'creative testing,' 'write me some ads.' For campaign strategy and targeting, see paid-ads. For landing page copy, see copywriting.

日本語の概要は準備中です。原文の説明を表示しています。

rajitsaha/100xprism102026年10月14日 更新

ai-seo

無料

When the user wants content cited by LLMs or surfaced in AI-generated answers — 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'AI Overviews,' 'optimize for ChatGPT/Perplexity/Claude,' 'AI citations,' 'zero-click search.' For traditional technical/on-page audits, see seo-audit. For structured data, see schema-markup.

日本語の概要は準備中です。原文の説明を表示しています。

rajitsaha/100xprism102026年10月14日 更新

When the user wants to set up, improve, or audit analytics tracking and measurement — "GA4," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "tracking plan," "attribution," "Mixpanel," "Segment," "are my events firing," or how to measure marketing results. For A/B test measurement, see ab-test-setup.

日本語の概要は準備中です。原文の説明を表示しています。

rajitsaha/100xprism102026年10月14日 更新

architect

無料

Architectural decision advisor for cloud, data, and SaaS distributed systems. Use when the user asks "should we use X or Y", weighs a tradeoff, or needs a decision matrix, scaling analysis, cost-at-scale review, data-tier design, multi-tenancy model, or API/resilience guidance. For full technical blueprints, use enterprise-design.

日本語の概要は準備中です。原文の説明を表示しています。

rajitsaha/100xprism102026年10月14日 更新

rajitsaha のスキルをすべて見る

このスキルの問題を報告する