← 返回 Skills 市场

Meyhem Researcher

Name: Meyhem Researcher
Author: c5huracan

作者 c5huracan · GitHub ↗ · v0.2.5 · MIT-0

cross-platform ✓ 安全检测通过

698

总下载

当前安装

版本数

在 OpenClaw 中安装

/install meyhem-researcher

功能描述

Multi-query research tool with LLM-ranked results and freshness control. Breaks a topic into focused queries, previews top results. No API key.

使用说明 (SKILL.md)

Meyhem Deep Researcher

Multi-query research tool. Breaks a topic into focused queries, searches via api.rhdxm.com with LLM-ranked results, and previews top results.

No API key. No signup. No rate limits.

Why Meyhem Researcher?

LLM-ranked results: every result scored for relevance by an LLM prior
Freshness control: request real-time, hourly, daily, or weekly freshness
Multi-query workflow: break a topic into multiple queries, search, preview top results

Quick Start

python3 researcher.py "transformer attention mechanism"
python3 researcher.py "kubernetes networking" -n 3 -q 5
python3 researcher.py "AI regulation 2026" --freshness realtime
python3 researcher.py "climate policy updates" --freshness hour --agent my-researcher

Quick Start (REST)

Full API docs: https://api.rhdxm.com/docs

curl -s -X POST https://api.rhdxm.com/search \
  -H 'Content-Type: application/json' \
  -d '{"query": "YOUR_QUERY", "agent_id": "my-researcher", "max_results": 10, "freshness": "hour"}'

Freshness options: realtime (never cached), hour, day, week, or omit for default (1hr cache).

MCP

You can also connect via MCP at https://api.rhdxm.com/mcp/ for richer integration.

Data Transparency

This skill sends your search query, an agent identifier, and any selected URLs to api.rhdxm.com. The skill does not access local files, environment variables, or credentials on its own, but anything you include in the query or agent_id will be transmitted. Avoid sending sensitive or proprietary content.

Source code: https://github.com/c5huracan/meyhem

安全使用建议

This skill behaves as advertised: it sends your queries, an agent identifier, and any selected URLs to a third-party API (api.rhdxm.com). Before installing or using it: (1) Don't include secrets, proprietary text, or internal identifiers in queries or the agent_id. (2) Consider whether sending search terms and clicked URLs to an external service is acceptable for your data policy. (3) If you need stronger privacy, review the GitHub source yourself or run a local/offline research workflow instead. (4) Test with non-sensitive queries first and inspect returned previews/URLs for unexpected behavior.

功能分析

Type: OpenClaw Skill Name: meyhem-researcher Version: 0.2.5 The skill is a straightforward research tool that queries an external API (api.rhdxm.com) to retrieve and rank search results. The Python script (researcher.py) uses standard libraries, contains no obfuscation, and does not attempt to access sensitive local files or environment variables. The documentation (SKILL.md) includes a clear data transparency notice regarding the transmission of queries to the third-party service, and there are no signs of malicious prompt injection or unauthorized execution.

能力评估

✓ Purpose & Capability

Name/description (multi-query research with LLM-ranked results) aligns with included code and SKILL.md: the Python script issues HTTP requests to api.rhdxm.com, breaks topics into sub-queries, and previews results. Required binary (python3) and lack of credentials are appropriate.

ℹ Instruction Scope

SKILL.md and researcher.py explicitly send the user's query, agent_id, and selected URLs to https://api.rhdxm.com (including a follow-up select call to fetch preview content). The README warns not to include sensitive or proprietary content; this network transmission is within the skill's stated purpose but is the primary privacy risk.

✓ Install Mechanism

No install spec; the skill is instruction-only with a small Python script. No downloads or archive extraction—lowest install risk.

✓ Credentials

The skill requests no environment variables, no credentials, and accesses only argv. This is proportionate to its functionality. Note: the agent_id argument can leak identifying information if set to an organization-specific value.

✓ Persistence & Privilege

The skill does not request always:true and does not modify system or other skills' configuration. It runs only when invoked.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install meyhem-researcher
安装完成后，直接呼叫该 Skill 的名称或使用 /meyhem-researcher 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v0.2.5

- Introduced LLM-ranked search results for higher relevance. - Added freshness control: choose realtime, hourly, daily, or weekly result freshness. - Updated CLI and REST usage to support freshness options. - Enhanced documentation for new features.

v0.2.4

Align description and claims with actual code behavior

v0.2.3

Honest data transparency section

v0.2.2

Remove auto-outcome, align SKILL.md with script

v0.2.1

Republish for HIGH CONFIDENCE security scan

v0.2.0

- Updated skill version to 0.2.0. - Made changes to researcher.py.

v0.1.9

- Added researcher.py script for direct command-line usage. - Updated SKILL.md with new Python3 command-line quick start examples. - Changed system requirements: now depends on python3 instead of curl and pip packages. - Updated REST usage example (new "max_results" parameter). - General documentation improvements and clarified instructions.

v0.1.8

- Bumped version to 0.1.8 in SKILL.md. - No functional or documentation changes besides version update.

v0.1.7

- Expanded description and overview to highlight multi-engine, full-content search and synthesis capabilities. - Added installation and usage instructions for both Python and REST clients. - Introduced a new dependency: the Python package `meyhem` (via pip). - Clarified data transparency, specifying exactly what data is sent, stored, and used for. - Updated workflow explanations and examples, emphasizing user privacy and outcome-based improvements.

v0.1.6

- Updated the description and introduction for greater clarity about deep research and multi-query search. - Emphasized the process: search, select results, synthesize, and track outcomes. - Adjusted for consistency with the latest features and streamlined instructions. - No changes to usage or privacy details.

v0.1.5

- Updated SKILL.md to clarify API usage and data transparency - Added a dedicated Data Transparency section explaining what is and isn't sent to Meyhem - Condensed and simplified workflow instructions for clearer usage - Removed step-by-step breakdown and workflow summary for brevity - Version number corrected to 0.1.5 in metadata

v0.1.4

Version 1.0.0 is a major release with improved usability and shareability. - Added support for generating shareable, cited research reports with a public URL. - Updated description and documentation to emphasize public report sharing and broad use cases (e.g., competitive intel, market analysis). - Removed the README.md file; all documentation is now consolidated in SKILL.md. - Clarified privacy and workflow details; reinforced no API key or login required.

v0.1.3

- Updated skill description to emphasize outcome-driven ranking and smarter results with usage. - Highlighted key features in the description: multi-angle search and cited reports, with no API key required. - No changes to workflow or functionality; update is informational/documentation only.

v0.1.2

- Added a Privacy section to SKILL.md describing data handling and privacy practices. - Clarified that no API key, login, or personally identifiable information is required or collected. - Noted that queries are used to improve search rankings for all agents. - Included reference to the API documentation for further details.

v0.1.1

- Version number changed from 1.0.0 to 0.1.0 in SKILL.md - No other content or workflow changes detected

v0.1.0

No changes detected in this version. - Version remains at 1.0.0 - No file or documentation updates identified - No new features, bug fixes, or workflow modifications

v1.0.0

Initial release of Meyhem Deep Researcher: - Introduces a multi-step research workflow powered by Meyhem search. - Automatically decomposes questions into multiple focused search queries covering different angles. - Searches Meyhem, selects the most relevant results, and fetches full page content for analysis. - Synthesizes a comprehensive research report with full citations and a Sources section. - Reports usefulness of each result to continuously improve search relevance.

元数据

Slug meyhem-researcher

版本 0.2.5

许可证 MIT-0

累计安装 6

当前安装数 5

历史版本数 17

常见问题