← Back to Skills Marketplace
89
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install research-summary
Description
英文卖方研报/行业报告转中文投研快讯。适合科技股、互联网、半导体赛道。 当用户提到"研报"、"研报总结"、"卖方报告"、"投行分析"、"research report"、"analyst"、"180k"、"投研快讯"、"预期差摘要"时激活。 输入：英文/中文研报内容、PDF、网页链接、截图。 输出：结构化中文投研...
Usage Guidance
This skill is internally consistent and carries no extra install or credential requests. Before using: (1) do not upload confidential or legally sensitive reports you don't want processed; (2) if you expect the agent to fetch links or parse PDFs/screenshots, ensure your agent environment actually provides web access, OCR, or PDF parsing — otherwise the skill may ask you to paste text; (3) verify extracted numbers and investment judgments before acting — the skill outputs opinionated, concise interpretations ("群聊风格") and intentionally omits the analyst's full reasoning; (4) be aware the skill will activate on the listed Chinese/English trigger words, so use triggers deliberately to avoid unintended runs.
Capability Analysis
Type: OpenClaw Skill
Name: research-summary
Version: 1.0.0
The skill bundle is a specialized prompt template designed to summarize financial research reports into concise Chinese investment newsletters. It contains no executable code, external dependencies, or instructions that attempt to exfiltrate data or bypass security controls. The logic is entirely focused on text analysis and formatting for financial reporting (SKILL.md).
Capability Assessment
Purpose & Capability
Name/description (convert/condense sell-side research into Chinese investment quicknotes) matches the SKILL.md instructions. The skill requests no binaries, env vars, or installs — appropriate for an instruction-only summarization skill.
Instruction Scope
SKILL.md prescribes how to extract metadata, classify report type, and produce a tightly formatted output. It also assumes the agent can accept/parse PDFs, webpages, and screenshots (e.g., '自动抓取内容' for links). That assumption is reasonable but depends on the agent/runtime providing web fetch, OCR or PDF parsing; the skill itself does not add any unrelated file or credential access.
Install Mechanism
No install spec and no code files — lowest-risk approach. Nothing is downloaded or written to disk by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested. All required inputs are user-provided report content, links, PDFs, or screenshots — proportional to the stated task.
Persistence & Privilege
always is false and the skill does not request persistent system privileges or modifications of other skills. Autonomous invocation is allowed (platform default) but not elevated by this skill's metadata.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install research-summary - After installation, invoke the skill by name or use
/research-summary - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
research-summary 1.0.0 — 首发版本上线
- 新增支持将英文/中文卖方研报、行业报告高密度转写为结构化中文投研快讯，聚焦科技股、互联网、半导体领域
- 输入支持全文、PDF、网页链接、截图等多种形式
- 自动识别并筛选“预期差、增量、催化剂、风险”等二级市场关心要素，突出关键数字与主线
- 输出格式适合微信群、知识星球传播，语言短硬、判断优先，仿资深投资人风格
- 适配不同类型报告，按内容自动选择提炼结构，强化可扫读标签与分层
- 内置多组激活关键词，便捷集成日常投研 workflow
Metadata
Frequently Asked Questions
What is research-summary?
英文卖方研报/行业报告转中文投研快讯。适合科技股、互联网、半导体赛道。 当用户提到"研报"、"研报总结"、"卖方报告"、"投行分析"、"research report"、"analyst"、"180k"、"投研快讯"、"预期差摘要"时激活。 输入：英文/中文研报内容、PDF、网页链接、截图。 输出：结构化中文投研... It is an AI Agent Skill for Claude Code / OpenClaw, with 89 downloads so far.
How do I install research-summary?
Run "/install research-summary" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is research-summary free?
Yes, research-summary is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does research-summary support?
research-summary is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created research-summary?
It is built and maintained by sid (@ambition0802); the current version is v1.0.0.
More Skills