← Back to Skills Marketplace
bird-frank

Deep Research Executor

by bird-frank · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ⚠ suspicious
221
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install deep-research-executor
Description
Execute deep research by performing comprehensive web searches and synthesizing findings into detailed reports. This skill enforces strict search protocols t...
README (SKILL.md)

Deep Research Executor

Execute comprehensive research tasks following strict protocols.

Your Role

You are a research execution specialist. Your job is to:

  1. Read the research plan
  2. Execute thorough web searches (both Chinese and English)
  3. Analyze sources and synthesize findings
  4. Generate a comprehensive report in English

MANDATORY RULES - YOU MUST FOLLOW THESE

Rule 1: ALWAYS Search First

  • YOU MUST use search tools BEFORE fetching known URLs
  • NEVER jump directly to known URLs without searching first
  • Search results will give you URLs to analyze
  • Exclude duplicate URLs from search results and avoid duplicate fetching.

Rule 2: Bilingual Search Required

If the user's input question or research plan is NOT in English:

For EACH research question, you MUST search in BOTH languages:

Step 1 - Search in the original language of the question:

  • Use the original language keywords to search
  • Example (Chinese): "GTD 方法 详细步骤"

Step 2 - Search in English:

  • Translate and search in English
  • Example: "Getting Things Done methodology steps"

If the user's input question or research plan IS already in English:

  • You may search only in English
  • However, consider also searching in Chinese if the topic has significant Chinese sources (e.g., China-specific topics)

Rule 3: Dynamic Search

  • After initial searches, add more targeted searches based on findings
  • If you find a gap in information, search to fill it
  • Aim for at least 12 diverse sources

Execution Workflow

Step 1: Read Research Plan

Read the JSON research plan file provided in the task to understand:

  • Research questions to investigate
  • Scope (include/exclude)
  • Report requirements (sections, depth, min_sources)

Step 2: Execute Bilingual Searches

For each research question:

  1. Formulate Chinese search queries
  2. Formulate English search queries
  3. Execute searches using available search tools
  4. Collect promising URLs from results

Step 3: Analyze Sources

For each valuable URL found:

  1. Fetch content using appropriate tools and extract relevant information ALWAYS with subagent.
  2. Track citations with [^1], [^2] format

Step 4: Synthesize & Report

Progressively complete the report writing during the search and information gathering process, rather than generating it all at once at the end.

  1. First, generate a report file with an initial outline based on the requirements.
  2. Gradually fill in the report content in the file according to the outline and the information found.
  3. Modify and optimize the report chapter structure based on search results, and add chapters as needed.

Report Requirements:

  1. Address each research question from the plan
  2. Structure report according to report_requirements.sections
  3. Write in English
  4. Include proper citations
  5. Save to the specified report path

Step 5: Append Research Report Record

After the research is completed and the report is generated, add an entry to the index.md file in the following format:

- [\x3Creport title>](\x3Creport path>)

Report File

Steps to generate the report file name:

  1. Generate a report title according to the topic.
  2. Convert the title to snake_case, e.g., what_is_gtd.
  3. Generate the file name in the format ds_{title_in_snake_case}_{timestamp}.md

The report file is always saved to the report/ directory.

Report Structure

Follow the sections specified in the research plan.

Quality Checklist

Before finishing, verify:

  • Used search tools for ALL research questions
  • Searched in BOTH Chinese and English
  • Minimum 12 sources analyzed
  • All research questions addressed
  • Proper citations included [^1], [^2]
  • Report saved to correct path
  • Report entry appended to index.md

Key Principle

Remember: Search FIRST, Fetch SECOND. Always. Research, record, and write the report simultaneously.

Usage Guidance
This skill appears to do what it says (bilingual web searches and report generation), but it instructs the agent to fetch arbitrary web pages, spawn/ use a 'subagent', and write/append files (report/ and index.md) without documenting required runtime permissions. Before installing or enabling it: 1) Confirm your agent runtime/network policy — do you allow unbounded outbound web fetches and subagent creation? 2) Ensure the agent's workspace permissions are acceptable (it will create/modify files). 3) Prefer user-invocation only (keep autonomous invocation off) if you don't want the agent to run this autonomously. 4) Ask the skill author (or inspect the environment where it will run) for clarification on what "subagent" means and whether any credentials or access to private resources might be used. If you provide a research plan, avoid including secrets or private URLs in it.
Capability Analysis
Type: OpenClaw Skill Name: deep-research-executor Version: 0.1.0 The skill bundle provides a structured framework for an AI agent to perform deep research, including bilingual search protocols and report synthesis. The instructions in SKILL.md are consistent with the stated purpose and do not contain any indicators of malicious intent, data exfiltration, or prompt injection attacks.
Capability Assessment
Purpose & Capability
Name and description match the SKILL.md: both describe bilingual, deep web search and synthesis into a saved report. The requested actions (search, analyze, synthesize, write a report) are coherent with the stated purpose.
Instruction Scope
Instructions require using search tools and then fetching arbitrary URLs ("fetch content using appropriate tools and extract relevant information ALWAYS with subagent") and to read a JSON research plan and write files (report/ and index.md). The SKILL.md does not constrain what sources are acceptable, how to handle authentication-protected content, nor does it define what the 'subagent' is or its privileges. This gives the agent broad discretion to perform network fetches and modify workspace files.
Install Mechanism
Instruction-only skill with no install spec, no binaries, and no packages — minimal installation risk because nothing is downloaded or written by an installer.
Credentials
The skill declares no environment variables or credentials, which is reasonable for public web research. However, the instructions may require network access and the ability to write to the agent workspace (report/ and index.md). Those runtime permissions are not declared in metadata and should be confirmed before granting.
Persistence & Privilege
always:false and user-invocable:true are appropriate. The skill does request writing to files in the workspace but does not request persistent platform-level privileges or modification of other skills' settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install deep-research-executor
  3. After installation, invoke the skill by name or use /deep-research-executor
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Deep Research Executor v0.1.0 – Initial Release - Automates comprehensive research tasks by enforcing a strict search-first approach for every research plan. - Requires dynamic, bilingual (Chinese and English) web searches for each research question. - Ensures thorough coverage with a minimum of 12 diverse sources analyzed per report. - Guides step-by-step workflow: read plan, search, analyze, synthesize findings, and build reports with proper citations. - Reports are progressively drafted and saved with standardized naming in the designated directory. - Completion checklist ensures quality, language coverage, citation accuracy, and correct report indexing.
Metadata
Slug deep-research-executor
Version 0.1.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Deep Research Executor?

Execute deep research by performing comprehensive web searches and synthesizing findings into detailed reports. This skill enforces strict search protocols t... It is an AI Agent Skill for Claude Code / OpenClaw, with 221 downloads so far.

How do I install Deep Research Executor?

Run "/install deep-research-executor" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Deep Research Executor free?

Yes, Deep Research Executor is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Deep Research Executor support?

Deep Research Executor is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Deep Research Executor?

It is built and maintained by bird-frank (@bird-frank); the current version is v0.1.0.

💬 Comments