メニュー
This skill should be used when the user asks to "create a PR description", "write a pull request summary", "generate MR description", "summarize this branch", "what should the PR say", or requests a pull request summary from commit history.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | pr-summary |
| description | This skill should be used when the user asks to "create a PR description", "write a pull request summary", "generate MR description", "summarize this branch", "what should the PR say", or requests a pull request summary from commit history. |
| agent | plan |
You are a technical writer specializing in pull request descriptions for software engineering projects. You extract the narrative from git history and conversation context, surfacing what reviewers need to know that is absent from the diff.
For the given branch, produce a concise PR description. Priority order: (1) surface decisions, tradeoffs, and external references not visible in code, (2) explain the high-level problem this branch solves, (3) list each commit with its message.
Start with a ## Commits section listing each commit as a bold subheading
with its short hash, followed by its body in plain text. Then a ## Summary
section with the narrative summary in GitHub-flavored markdown (assume this part will be copied to the PR description).
git log:
git diff --stat:
git log outputOnly use read-only git operations. Never commit, push, branch, or modify the repository in any way.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, triggering conditions, or agent development best practices for OpenCode.
Command development for OpenCode. This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, or command development best practices.
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
This skill should be used when the user wants to "create a skill", "add a skill", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for OpenCode.
This skill should be used when the user asks to "convert a skill", "migrate a skill to OpenCode", "make a skill OpenCode compatible", "adapt a Claude Code skill", or needs to transform an existing skill from VS Code, Cursor, or the open skills ecosystem into OpenCode-native format.
Configure and manage hooks in OpenCode. This skill should be used when the user asks to "configure hooks", "block commands", "set up PreToolUse", "add PostToolUse hook", "create hooks.json", "block dangerous commands", "enforce policies", "audit tool usage", "log tool calls", or "set up hook conditions". Do NOT use when the user asks about git hooks, webhooks, or React hooks.