菜单
Research technical solutions and analyze architectures. Acts as a command facade to trigger the 'researcher' subagent for multi-source verification and deep report synthesis.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Delegate implementation tasks from Claude Code to external CLI agents (Codex or Grok). Covers task-brief authoring, non-interactive dispatch, permission setup, background monitoring, resume, and independent verification of the returned work.
Analyze images/audio/video/documentation with Gemini API. Use for vision analysis, transcription, OCR, design extraction, and deep multimodal understanding.
Create, edit, analyze .docx Word documents. Use for document creation, tracked changes, comments, formatting preservation, text extraction, template modification.
Create polished frontend interfaces from designs/screenshots/videos. Use for web components, 3D experiences, replicating UI designs, quick prototypes, immersive interfaces, avoiding AI slop.
Extract text/tables, create, merge, split PDFs. Fill PDF forms programmatically. Use for PDF processing, generation, form filling, document analysis, batch operations.
Create, edit, analyze .pptx PowerPoint files. Use for presentations, slides, layouts, speaker notes, template modification, content extraction, slide generation.
| name | hapo:research |
| description | Research technical solutions and analyze architectures. Acts as a command facade to trigger the 'researcher' subagent for multi-source verification and deep report synthesis. |
| user-invocable | true |
| when_to_use | Invoke for deep technical research and solution evaluation before building. |
| category | research |
| keywords | ["research","evaluation","analysis","solutions"] |
| argument-hint | <topic_or_question> |
| metadata | {"author":"haposoft","version":"2.0.0"} |
Mantra: YAGNI, KISS, DRY. Be brutal, straight to the point, and strictly authoritative.
This skill acts as a Command Facade. When invoked, the main Orchestrator MUST NOT attempt to run WebSearch itself. Instead, it must instantly delegate the operation to the Specialized Subagent.
Before delegating, briefly assess the [topic].
Call the Agent tool to invoke the researcher subagent. Use TaskCreate only for task-list tracking when the workflow needs persistent task state.
Instructions to pass to Researcher:
Conduct comprehensive research on: [topic]
Constraint 1: ALWAYS use native `WebSearch` as the primary search method.
Constraint 2: Validate key claims with multiple credible sources. Prioritize official docs, maintainers, release notes, and strong production references.
Constraint 3: Use direct `WebFetch` only when search results are insufficient or raw source inspection is required.
Constraint 4: Limit total search calls to a maximum of 5 distinct queries.
Constraint 5: Stop excessive "chain-searching". Synthesize decisively once the evidence is sufficient.
Output Format: Must strictly follow the 'Standard Research Report' layout.
The subagent MUST return the findings formatted EXACTLY according to the built-in specification template.
Instruct the Researcher Subagent with this strict requirement:
"Sử dụng nguyên bản template tại
packages/spec/src/claude/skills/specs/templates/research.md. Tuyệt đối không tự ý đẻ thêm các đề mục ngoài phạm vi file template này."
Once the researcher completes the Task and returns the Markdown output, save it based on context:
| Context | Save to | Example |
|---|---|---|
Active spec exists (specs/<feature>/) | specs/<feature>/research.md | specs/auth-login/research.md |
| No active spec (system-wide / general) | specs/_shared/Research-<slug>-<date>.md | specs/_shared/Research-mv3-best-practices-2026-04-11.md |
specs/<feature>/ doesn't exist yet, create it.specs/_shared/. Create the directory if it doesn't exist.plans/reports/ or docs/. All research belongs in specs/.