ワンクリックで
research-methodology
Thorough multi-angle research exploration with evidence requirements and structured output
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。
メニュー
Thorough multi-angle research exploration with evidence requirements and structured output
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 | research-methodology |
| description | Thorough multi-angle research exploration with evidence requirements and structured output |
| when_to_use | during dual-verification research, when exploring topics comprehensively, when evidence-based findings are required |
| version | 1.0.0 |
Conduct thorough research by exploring topics from multiple angles with rigorous evidence standards.
Announce at start: "I'm using the research-methodology skill for comprehensive exploration."
/cipherpowers:verify researchApproach the topic from at least 3 different angles:
Every finding MUST include:
Finding: [clear statement]
Source: [file path, line number, or documentation reference]
Confidence: HIGH | MEDIUM | LOW
Evidence: [quote or specific reference supporting the finding]
Confidence Levels:
Explicitly document:
Use consistent report format:
# Research Findings - [Topic]
## Metadata
- Date: {YYYY-MM-DD HH:mm:ss}
- Topic: [description]
- Angles Explored: [list]
## Findings
### [Category 1]
[Findings with evidence]
### [Category 2]
[Findings with evidence]
## Gaps and Unanswered Questions
[What couldn't be determined]
## Summary
[Key takeaways]
Save findings to: .work/{YYYY-MM-DD}-verify-research-{HHmmss}.md
Announce file path in final response.
End with:
STATUS: COMPLETE - Research finished, all angles explored, findings documentedSTATUS: INCOMPLETE - Research blocked, unable to complete explorationUse boolean decision trees instead of imperatives for 100% compliance under pressure
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches cipherpowers:code-review-agent subagent to review implementation against plan or requirements before proceeding
Establish workflow boundary checklists with clear pass/fail criteria and escalation procedures
Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification