Specify a webhook-driven task for OpenClaw
Describe event inputs, validation, deduplication, and intended actions before integration work.
Efficiently answer question about GitHub issue
--- name: answer-issue description: Efficiently answer question about GitHub issue --- Efficiently answer question about GitHub issue $ARGUMENTS ## Prerequisites - $ARGUMENTS format: `<issue_number> <user_prompt>` - Example: `123 この問題の原因を調査して` - Example: `456 どのファイルが関連しているか教えて` ## Purpose Efficiently investigate and answer questions about structured GitHub issues without necessarily implementing fixes. Optimized for issues created by `/structure-issue` or `/restructure-issue`. ## Process 1. Parse arguments: extract issue number and user prompt - Split `$ARGUMENTS` by first space: `issue_number = first_token`, `user_prompt = remaining_text` - Example: `"123 この問題の原因を調査して"` → issue_number=`"123"`, user_prompt=`"この問題の原因を調査して"` - If no space found: treat entire `$ARGUMENTS` as issue_number, prompt user for question 2. Fetch issue: `gh issue view <issue_number> --json title,body,labels,comments` 3. Parse structured issue content: - Bug: 概要、再現手順、期待される動作、実際の動作、エラーメッセージ、環境情報 - Feature: 概要、背景・目的、期待される動作 - Enhancement: 概要、現状の問題点、期待される改善結果 4. Based on user prompt, determine investigation type: - Root cause analysis: "原因を調査" - Related files search: "関連ファイル", "どこを修正" - Implementation approach: "実装方法", "どうやって直す" - Impact assessment: "影響範囲", "副作用" - General questions: その他の質問 5. Use appropriate tools efficiently: - For codebase exploration (finding files by concept/feature): Use Task tool with subagent_type=Explore - For specific file/function search (known name): Use Grep/Glob directly - For reading file contents: Use Read tool - For log pattern analysis: Use Grep tool with specific patterns 6. Provide structured answer: ``` ## 調査結果 [direct answer to user prompt] ## 関連情報 [supporting details, file locations with line numbers, code snippets] ## 推奨される次のステップ [actionable recommendations] ``` 7. If fix is needed, suggest: `/work-on-issue <issue_number>` ## Notes - Optimize for speed (do not over-investigate) - Provide actionable answers with file:line references - Stay focused on user's prompt (do not implement unless asked)--- name: answer-issue description: Efficiently answer question about GitHub issue --- Efficiently answer question about GitHub issue $ARGUMENTS ## Prerequisites - $ARGUMENTS format: `<issue_number> <user_prompt>` - Example: `123 この問題の原因を調査して` - Example: `456 どのファイルが関連しているか教えて` ## Purpose Efficiently investigate and answer questions about structured GitHub issues without necessarily implementing fixes. Optimized for issues created by `/structure-issue` or `/restructure-issue`. ## Process 1. Parse arguments: extract issue number and user prompt - Split `$ARGUMENTS` by first space: `issue_number = first_token`, `user_prompt = remaining_text` - Example: `"123 この問題の原因を調査して"` → issue_number=`"123"`, user_prompt=`"この問題の原因を調査して"` - If no space found: treat entire `$ARGUMENTS` as issue_number, prompt user for question 2. Fetch issue: `gh issue view <issue_number> --json title,body,labels,comments` 3. Parse structured issue content: - Bug: 概要、再現手順、期待される動作、実際の動作、エラーメッセージ、環境情報 - Feature: 概要、背景・目的、期待される動作 - Enhancement: 概要、現状の問題点、期待される改善結果 4. Based on user prompt, determine investigation type: - Root cause analysis: "原因を調査" - Related files search: "関連ファイル", "どこを修正" - Implementation approach: "実装方法", "どうやって直す" - Impact assessment: "影響範囲", "副作用" - General questions: その他の質問 5. Use appropriate tools efficiently: - For codebase exploration (finding files by concept/feature): Use Task tool with subagent_type=Explore - For specific file/function search (known name): Use Grep/Glob directly - For reading file contents: Use Read tool - For log pattern analysis: Use Grep tool with specific patterns 6. Provide structured answer: ``` ## 調査結果 [direct answer to user prompt] ## 関連情報 [supporting details, file locations with line numbers, code snippets] ## 推奨される次のステップ [actionable recommendations] ``` 7. If fix is needed, suggest: `/work-on-issue <issue_number>` ## Notes - Optimize for speed (do not over-investigate) - Provide actionable answers with file:line references - Stay focused on user's prompt (do not implement unless asked)
Imported from the listed AgentSkill.sh category. Complete supplied package files and notices are retained. Required external tools and credentials are not installed. No bundled code was executed during import. Individual agent task behavior has not been tested.