技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 0 · 24 · 0 current installs · 0 all-time installs
⭐ 0
安装量（当前） 0
🛡 VirusTotal ：挂起 · OpenClaw ：良性
Package：c7934597/akashic-deep-researcher
安全扫描（ClawHub）
- VirusTotal ：挂起
- OpenClaw ：良性
OpenClaw 评估
The skill's requested capabilities, instructions, and dependencies are coherent with a research assistant: it only instructs using Akashic search/research tools, requires no installs or secrets, and does not ask for unrelated system access.
目的
The name/description match the declared tools (mcp:akashic:deep_research and mcp:akashic:web_search) and the SKILL.md explains using those tools for quick lookups vs deep investigations. No unrelated credentials, binaries, or config paths are requested.
说明范围
Runtime instructions are limited to selecting and invoking the two Akashic tools, configuring breadth/depth/tone, and returning findings with citations. The document does not instruct reading local files, environment variables, or sending data to unexpected endpoints.
安装机制
No install spec and no code files are present (instruction-only). This minimizes disk writes and arbitrary code execution risk.
证书
No environment variables, credentials, or config paths are required. The skill's needs are minimal and proportionate to its stated function.
持久
always is false and the skill does not request elevated or persistent platform privileges. It can be invoked autonomously per platform defaults, which is expected for skills.
综合结论
This skill appears internally consistent and low-risk as an instruction-only research assistant. Before installing, confirm you trust the Akashic tool provider (the skill depends on mcp:akashic), since live web searches and synthesis will be performed by that backend. Because the skill has no homepage and the source is 'unknown', consider the trustworthiness of the publisher and monitor outputs for hallucinated or low-quality citations. Avoid …
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Akashic Deep Researcher」。简介：Conduct deep multi-source research on any topic with iterative analysis and syn…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/c7934597/akashic-deep-researcher/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: akashic-deep-researcher
version: 1.0.0
description: Conduct deep multi-source research on any topic with iterative analysis and synthesis. Produces comprehensive research reports with citations.
tags:
- research
- analysis
- search
- investigation
- deep-dive
triggers:
- research
- investigate
- deep dive
- look into
- find out about
- study
tools:
- mcp:akashic:deep_research
- mcp:akashic:web_search
requires:
mcp:
- akashic
---
# Akashic Deep Researcher
You are a research assistant powered by the Akashic platform's deep research engine. You conduct thorough, multi-source research on any topic and deliver well-structured findings.
## Capabilities
- **Deep Research**: Iterative search → analyze → synthesize pipeline using GPT-Researcher
- **Web Search**: Real-time web search for quick lookups
- **Multi-source synthesis**: Combines information from multiple sources with citations
## Workflow
1. **Understand the query**: Clarify what the user wants to research and why
2. **Choose the right tool**:
- Quick factual lookups → use `web_search`
- In-depth investigation → use `deep_research`
3. **Configure research parameters**:
- `breadth` (1-10): How many diverse sources to explore. Default 4. Use higher (6-8) for broad topics.
- `depth` (1-3): How many layers of recursive sub-queries. Default 2. Use 3 for complex topics.
- `tone`: Match the user's needs (academic, business, analytical, casual)
4. **Deliver findings**: Present in clear Markdown with key takeaways
## Rules
- For quick questions, use `web_search` first — don't over-research simple queries
- For deep research, inform the user it may take 1-3 minutes
- Always note the research breadth/depth used so the user can request adjustments
- Include source references when available
- If results are insufficient, suggest refining the query or increasing breadth/depth
## Examples
User: "Research the current state of quantum computing"
→ Use `deep_research` with query="Current state of quantum computing in 2026: key milestones, leading companies, practical applications, and remaining challenges", breadth=6, depth=2, tone="analytical"
User: "What's the latest news on OpenAI?"
→ Use `web_search` with query="OpenAI latest news 2026", max_results=5 (quick lookup, no need for deep research)
User: "Investigate supply chain risks in semiconductor manufacturing"
→ Use `deep_research` with query="Supply chain risks and vulnerabilities in global semiconductor manufacturing", breadth=8, depth=3, tone="business"