aiskillstore/marketplace / skills/0tarof/create-pr
create-pr
VerifiedGitHubのプルリクエスト(PR)を作成する際に使用します。変更のコミット、プッシュ、PR作成を含む完全なワークフローを日本語で実行します。「PRを作って」「プルリクエストを作成」「pull requestを作成」などのリクエストで自動的に起動します。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.4 KB |
| skill-report.json | config | 32.7 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-04T16:35:41.626Z",
"slug": "0tarof-create-pr",
"source_url": "https://github.com/0tarof/dotfiles/tree/main/claude/skills/create-pr",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "67af0ad17ba29905a627f2c8e30ce677b727f0d8e64803c550f5331f36f5bf3b",
"tree_hash": "78b79e30bd9b11acefb98329de8dfaa5ca580f3add13485ee71ae96bb5a5a76d",
"provenance": {
"model_requested": "gpt-5.5:high",
"model_effective": "codex:gpt-5.5:high",
"fallback_chain": [
{
"agent": "codex",
"model": "gpt-5.5",
"effort": "high",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "create-pr",
"description": "Automates a Japanese-language GitHub pull request workflow, including change review, explicit staging, commits, pushes, and PR creation with GitHub CLI.",
"summary": "Create reviewed GitHub pull requests with Japanese guidance for checks, commits, pushes, and PR descriptions.",
"icon": "📦",
"version": "1.0.0",
"author": "0tarof",
"license": "MIT",
"tags": [
"github",
"pull-request",
"git",
"automation",
"japanese"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands",
"network"
],
"category": "devops"
},
"security_audit": {
"risk_level": "medium",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "Most static backtick and URL alerts are Markdown examples or attribution links. Real risks remain where the workflow runs repo-controlled commands, commits, pushes, and creates GitHub pull requests. No prompt injection, exfiltration intent, or obfuscated payload was found in SKILL.md.",
"remediation": [
{
"issue": "Repository-controlled command execution",
"suggestion": "Treat CLAUDE.md and repo-local scripts as untrusted. Ask the user before running any command that is not listed in the skill.",
"severity": "medium"
},
{
"issue": "Repository and remote mutation",
"suggestion": "Show the exact file list, commit message, push branch, PR title, and PR body before executing write commands.",
"severity": "medium"
},
{
"issue": "Shell quoting in generated commands",
"suggestion": "Build commit messages and PR bodies with temporary files or safe argument arrays. Avoid inserting unescaped user text into shell strings.",
"severity": "medium"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 23,
"line_end": 32
},
{
"file": "SKILL.md",
"line_start": 32,
"line_end": 38
},
{
"file": "SKILL.md",
"line_start": 38,
"line_end": 43
},
{
"file": "SKILL.md",
"line_start": 43,
"line_end": 51
},
{
"file": "SKILL.md",
"line_start": 51,
"line_end": 58
},
{
"file": "SKILL.md",
"line_start": 58,
"line_end": 62
},
{
"file": "SKILL.md",
"line_start": 62,
"line_end": 73
},
{
"file": "SKILL.md",
"line_start": 73,
"line_end": 75
},
{
"file": "SKILL.md",
"line_start": 75,
"line_end": 81
},
{
"file": "SKILL.md",
"line_start": 81,
"line_end": 83
},
{
"file": "SKILL.md",
"line_start": 83,
"line_end": 93
},
{
"file": "SKILL.md",
"line_start": 93,
"line_end": 96
},
{
"file": "SKILL.md",
"line_start": 96,
"line_end": 105
},
{
"file": "SKILL.md",
"line_start": 105,
"line_end": 116
},
{
"file": "SKILL.md",
"line_start": 116,
"line_end": 120
},
{
"file": "SKILL.md",
"line_start": 120,
"line_end": 125
},
{
"file": "SKILL.md",
"line_start": 125,
"line_end": 133
},
{
"file": "SKILL.md",
"line_start": 133,
"line_end": 133
},
{
"file": "SKILL.md",
"line_start": 63,
"line_end": 66
},
{
"file": "SKILL.md",
"line_start": 121,
"line_end": 124
},
{
"file": "SKILL.md",
"line_start": 62,
"line_end": 73
},
{
"file": "SKILL.md",
"line_start": 120,
"line_end": 125
}
]
},
{
"factor": "network",
"evidence": [
{
"file": "SKILL.md",
"line_start": 68,
"line_end": 68
},
{
"file": "SKILL.md",
"line_start": 115,
"line_end": 115
}
]
}
],
"static_findings": [
{
"id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 23,
"line_end": 32,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 32,
"line_end": 38,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 38,
"line_end": 43,
"snippet": "1. リポジトリルートの`CLAUDE.md`を確認し、プロジェクト固有の要件を確認"
},
{
"id": "external_commands:SKILL.md:43:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 43,
"line_end": 51,
"snippet": "- Brewfileが変更された場合:`bin/brew-check`を実行して検証"
},
{
"id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 51,
"line_end": 58,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 58,
"line_end": 62,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 62,
"line_end": 73,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 73,
"line_end": 75,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 75,
"line_end": 81,
"snippet": "コミットメッセージのスタイルは、`git log`で確認した既存のコミット履歴に合わせてください。"
},
{
"id": "external_commands:SKILL.md:81:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 81,
"line_end": 83,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 83,
"line_end": 93,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:93:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 93,
"line_end": 96,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:96:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 96,
"line_end": 105,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:105:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 105,
"line_end": 116,
"snippet": "```markdown"
},
{
"id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 116,
"line_end": 120,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:120:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 120,
"line_end": 125,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:125:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 125,
"line_end": 133,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:133:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 133,
"line_end": 133,
"snippet": "3. **明示的なファイルパスでステージング**:`git add .`や`git add -A`は絶対に使用しない"
},
{
"id": "external_commands:SKILL.md:63:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "SKILL.md",
"line_start": 63,
"line_end": 66,
"snippet": "git commit -m \"$(cat <<'EOF'"
},
{
"id": "external_commands:SKILL.md:121:shell-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Shell command substitution",
"file": "SKILL.md",
"line_start": 121,
"line_end": 124,
"snippet": "gh pr create --title \"<PRのタイトル>\" --body \"$(cat <<'EOF'"
},
{
"id": "external_commands:SKILL.md:62:template-literal-with-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Template literal with command substitution",
"file": "SKILL.md",
"line_start": 62,
"line_end": 73,
"snippet": "```bash"
},
{
"id": "external_commands:SKILL.md:120:template-literal-with-command-substitution",
"category": "external_commands",
"severity": "medium",
"pattern": "Template literal with command substitution",
"file": "SKILL.md",
"line_start": 120,
"line_end": 125,
"snippet": "```bash"
},
{
"id": "network:SKILL.md:68:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 68,
"line_end": 68,
"snippet": "🤖 Generated with [Claude Code](https://claude.com/claude-code)"
},
{
"id": "network:SKILL.md:115:hardcoded-url",
"category": "network",
"severity": "low",
"pattern": "Hardcoded URL",
"file": "SKILL.md",
"line_start": 115,
"line_end": 115,
"snippet": "🤖 Generated with [Claude Code](https://claude.com/claude-code)"
},
{
"id": "obfuscation:SKILL.md:1:heuristic-high-file-entropy-6-98-bits-possible-b",
"category": "obfuscation",
"severity": "high",
"pattern": "[HEURISTIC] High file entropy (6.98 bits) - possible binary/encrypted content",
"file": "SKILL.md",
"line_start": 1,
"line_end": 1,
"snippet": "File: SKILL.md"
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.88,
"reason": "The Markdown bash fence shows read-only Git inspection commands: status, diff, and log. They do not include user-controlled shell interpolation or remote changes."
},
{
"id": "external_commands:SKILL.md:32:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This finding points at a Markdown code fence boundary and surrounding prose. There is no executable Ruby backtick or shell substitution at this location."
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.76,
"severity": "medium",
"reason": "The skill instructs the agent to read CLAUDE.md and run tests, linters, or build steps listed by the repository. Repository documentation can be untrusted and may cause arbitrary command execution."
},
{
"id": "external_commands:SKILL.md:43:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.72,
"severity": "medium",
"reason": "The workflow instructs running the repo-local bin/brew-check script when Brewfile changes. Repo-local scripts can execute arbitrary code if the repository or change set is untrusted."
},
{
"id": "external_commands:SKILL.md:51:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.78,
"reason": "The block mostly documents forbidden broad staging commands and recommends explicit file paths. Explicit-path staging reduces accidental inclusion, and no command injection vector is shown."
},
{
"id": "external_commands:SKILL.md:58:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "This location is a Markdown fence boundary before prose about commit message format. It is not an executable backtick or shell command by itself."
},
{
"id": "external_commands:SKILL.md:62:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.82,
"severity": "medium",
"reason": "The block shows a git commit command that writes repository history. The quoted heredoc reduces injection risk, but the command has real repository side effects."
},
{
"id": "external_commands:SKILL.md:73:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.94,
"reason": "This finding points at a Markdown fence close and prose about matching commit style. The commit command risk is already represented by the line 62 finding."
},
{
"id": "external_commands:SKILL.md:75:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.86,
"reason": "The inline git log reference is used to inspect existing commit style. That operation is read-only and does not create a command injection path."
},
{
"id": "external_commands:SKILL.md:81:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.9,
"severity": "medium",
"reason": "The git push command publishes the local branch to the origin remote. This is intended behavior, but it can expose accidental changes if run without review."
},
{
"id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This location is the end of a Markdown command block and explanatory prose. The actual push command risk is captured by the line 81 finding."
},
{
"id": "external_commands:SKILL.md:93:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.88,
"reason": "The listed ls command only checks for a pull request template file. It is read-only and uses a fixed path with no user-controlled interpolation."
},
{
"id": "external_commands:SKILL.md:96:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "This finding points at a Markdown fence boundary and prose. There is no executable command or dangerous interpolation at this location."
},
{
"id": "external_commands:SKILL.md:105:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The block is a Markdown template for the pull request body, not a shell command. It contains user-facing sections and an attribution link only."
},
{
"id": "external_commands:SKILL.md:116:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "This location is a Markdown fence close before the PR creation command section. The actual GitHub CLI command risk is captured by the line 120 finding."
},
{
"id": "external_commands:SKILL.md:120:ruby-shell-backtick-execution",
"verdict": "confirmed",
"confidence": 0.86,
"severity": "medium",
"reason": "The gh pr create command creates a GitHub pull request and sends the title and body to GitHub. It needs review because it publishes repository metadata and text."
},
{
"id": "external_commands:SKILL.md:125:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "This finding points at a Markdown fence close and follow-up prose. The PR creation command itself is covered by the line 120 finding."
},
{
"id": "external_commands:SKILL.md:133:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The inline commands appear in a warning that explicitly forbids git add . and git add -A. This is protective guidance, not an instruction to run them."
},
{
"id": "external_commands:SKILL.md:63:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.84,
"reason": "The command substitution uses cat with a single-quoted heredoc delimiter for a multiline commit message. The heredoc content is not expanded by the shell."
},
{
"id": "external_commands:SKILL.md:121:shell-command-substitution",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "The command substitution is used to pass a multiline PR body through a quoted heredoc. The GitHub publication risk is tracked separately on the gh pr create command."
},
{
"id": "external_commands:SKILL.md:62:template-literal-with-command-substitution",
"verdict": "false_positive",
"confidence": 0.83,
"reason": "This is a Markdown shell example using a quoted heredoc, not a JavaScript template literal. The commit side effect is already represented by the line 62 command finding."
},
{
"id": "external_commands:SKILL.md:120:template-literal-with-command-substitution",
"verdict": "false_positive",
"confidence": 0.82,
"reason": "This is a Markdown shell example using a quoted heredoc, not a template literal execution path. The PR creation side effect is covered by the line 120 command finding."
},
{
"id": "network:SKILL.md:68:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is an attribution link in a commit message template. It does not make a network request or transmit user data."
},
{
"id": "network:SKILL.md:115:hardcoded-url",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "The URL is an attribution link in a PR body template. It does not make a network request or transmit user data."
},
{
"id": "obfuscation:SKILL.md:1:heuristic-high-file-entropy-6-98-bits-possible-b",
"verdict": "false_positive",
"confidence": 0.92,
"reason": "SKILL.md is readable Markdown with Japanese prose and shell examples, not binary or encrypted content. The entropy heuristic is plausibly caused by multilingual text and symbols."
}
],
"semantic_findings": [
{
"title": "Repository-Controlled Command Guidance",
"description": "The skill tells the agent to read CLAUDE.md and run test, lint, or build steps described by the repository. A malicious repository can use that guidance to steer the agent toward unsafe commands.",
"severity": "medium",
"locations": [
{
"file": "SKILL.md",
"line_start": 38,
"line_end": 40
},
{
"file": "SKILL.md",
"line_start": 131,
"line_end": 132
}
],
"confidence": 0.75,
"confidence_reasoning": "The file explicitly requires checking CLAUDE.md and not skipping its listed preparation steps. The risk depends on repository trust, so confidence is high but not absolute."
}
],
"critical_findings": [],
"high_findings": [],
"medium_findings": [
{
"title": "Ruby/shell backtick execution",
"description": "1. リポジトリルートの`CLAUDE.md`を確認し、プロジェクト固有の要件を確認",
"locations": [
{
"file": "SKILL.md",
"line_start": 38,
"line_end": 43
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.76,
"confidence_reasoning": "The skill instructs the agent to read CLAUDE.md and run tests, linters, or build steps listed by the repository. Repository documentation can be untrusted and may cause arbitrary command execution."
},
{
"title": "Ruby/shell backtick execution",
"description": "- Brewfileが変更された場合:`bin/brew-check`を実行して検証",
"locations": [
{
"file": "SKILL.md",
"line_start": 43,
"line_end": 51
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.72,
"confidence_reasoning": "The workflow instructs running the repo-local bin/brew-check script when Brewfile changes. Repo-local scripts can execute arbitrary code if the repository or change set is untrusted."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 62,
"line_end": 73
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.82,
"confidence_reasoning": "The block shows a git commit command that writes repository history. The quoted heredoc reduces injection risk, but the command has real repository side effects."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 81,
"line_end": 83
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.9,
"confidence_reasoning": "The git push command publishes the local branch to the origin remote. This is intended behavior, but it can expose accidental changes if run without review."
},
{
"title": "Ruby/shell backtick execution",
"description": "```bash",
"locations": [
{
"file": "SKILL.md",
"line_start": 120,
"line_end": 125
}
],
"review_kind": "capability",
"source_category": "external_commands",
"source_severity": "medium",
"confidence": 0.86,
"confidence_reasoning": "The gh pr create command creates a GitHub pull request and sends the title and body to GitHub. It needs review because it publishes repository metadata and text."
},
{
"title": "Repository-Controlled Command Guidance",
"description": "The skill tells the agent to read CLAUDE.md and run test, lint, or build steps described by the repository. A malicious repository can use that guidance to steer the agent toward unsafe commands.",
"locations": [
{
"file": "SKILL.md",
"line_start": 38,
"line_end": 40
},
{
"file": "SKILL.md",
"line_start": 131,
"line_end": 132
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "medium",
"confidence": 0.75,
"confidence_reasoning": "The file explicitly requires checking CLAUDE.md and not skipping its listed preparation steps. The risk depends on repository trust, so confidence is high but not absolute."
}
],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 1,
"total_lines": 142,
"audit_model": "codex",
"audited_at": "2026-07-04T16:35:41.626Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Create GitHub Pull Requests in Japanese",
"value_statement": "Manual PR setup can miss changed files, tests, or repository conventions. This skill guides a Japanese-language workflow for review, commit, push, and GitHub PR creation.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"GitHub pull request",
"PR automation",
"Git workflow",
"gh CLI",
"Japanese workflow",
"developer productivity",
"code review"
],
"actual_capabilities": [
"Reviews git status, diff, and recent commits before staging.",
"Checks project instructions, tests, linting, and build steps before committing.",
"Stages files by explicit path instead of broad add commands.",
"Creates commits with a structured message and Claude Code attribution.",
"Pushes the branch and creates a GitHub pull request with gh."
],
"limitations": [
"Requires Git, GitHub CLI, repository access, and push permissions.",
"May run commands described in repository documentation, so user confirmation is important.",
"Cannot fix test failures without enough project context.",
"Communicates in Japanese by design."
],
"use_cases": [
{
"title": "Feature Branch PR",
"description": "Prepare a reviewed branch, run checks, commit approved files, and open a PR.",
"target_user": "Application developer"
},
{
"title": "Dotfiles Maintenance",
"description": "Validate Brewfile or script changes before creating a pull request.",
"target_user": "Repository maintainer"
},
{
"title": "Japanese Review Workflow",
"description": "Keep PR preparation, error explanations, and confirmation requests in Japanese.",
"target_user": "Japanese-speaking team"
}
],
"prompt_templates": [
{
"title": "Create a Simple PR",
"scenario": "Beginner workflow",
"prompt": "Create a pull request for my current branch. Review the diff first, then ask before staging, committing, pushing, and opening the PR."
},
{
"title": "Run Checks Before Commit",
"scenario": "Intermediate workflow",
"prompt": "Prepare this branch for a PR. Read the project instructions, identify required checks, run approved checks, and stop if any check fails."
},
{
"title": "Use the PR Template",
"scenario": "Structured PR workflow",
"prompt": "Create a PR using the repository template. Fill each section from the current changes and ask me to confirm the title and body."
},
{
"title": "Coordinate a Release PR",
"scenario": "Advanced workflow",
"prompt": "Create a release pull request from these changes. Group the summary by feature, fix, and maintenance work, then verify tests before pushing."
}
],
"output_examples": [
{
"input": "Create a PR for the current changes.",
"output": "The skill reviews changed files, asks for staging confirmation, creates a commit, pushes the branch, and returns the PR link."
},
{
"input": "Use the repository PR template.",
"output": "The skill checks for a template, drafts each required section from the diff, and asks for title and body approval."
},
{
"input": "A required check fails before commit.",
"output": "The skill stops the workflow, explains the failure in Japanese, and suggests the next repair step."
}
],
"best_practices": [
"Review the diff before approving staging or commit creation.",
"Run required tests and linters before pushing the branch.",
"Confirm the PR title, body, and branch before creation."
],
"anti_patterns": [
"Do not stage every file without reviewing the diff.",
"Do not skip failing checks to create a PR faster.",
"Do not use it where push access is not intended."
],
"faq": [
{
"question": "Does this skill create commits?",
"answer": "Yes. It can create a commit after reviewing changes and staging explicit files."
},
{
"question": "Does it push branches to GitHub?",
"answer": "Yes. It pushes the current branch to origin before creating a pull request."
},
{
"question": "Does it use the GitHub CLI?",
"answer": "Yes. It uses gh to create the pull request after preparing the title and body."
},
{
"question": "Can it use an existing PR template?",
"answer": "Yes. It checks for a repository PR template and uses it when present."
},
{
"question": "What language does it use with users?",
"answer": "The skill instructs the assistant to communicate with users in Japanese."
},
{
"question": "What should users review before approval?",
"answer": "Users should review changed files, staged paths, the commit message, push target, and PR body."
}
]
},
"file_structure": [
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 142
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |