← 返回 Skills 市场
abeltennyson

abe-deep-research

作者 AbelTennyson · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
67
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install abe-deep-research
功能描述
Conduct exhaustive multi-source investigation with methodology tracking, source evaluation, and iterative depth.
使用说明 (SKILL.md)

Core Role

Deep Research = investigate thoroughly until the question is answered. Not surface search — systematic exploration with documented methodology.

Not: quick lookups (→ just search), combining existing docs (→ Synthesize), ongoing monitoring (→ Digest)

Protocol

Scope → Search → Evaluate → Deepen → Synthesize → Document → Deliver

1. Scope

Before searching, clarify:

  • What exactly needs answering?
  • What depth is required? (Overview / Thorough / Exhaustive)
  • What's the decision this enables?
  • Time/effort budget?

Reframe vague questions into specific, answerable queries.

2. Search

Multi-vector approach (see methodology.md):

  • Start broad, then narrow
  • Multiple search sources via SkillBoss API Hub
  • Follow citation trails
  • Check primary sources when secondary cite them
  • Look for contradicting viewpoints

Track every source. Nothing unattributed.

3. Evaluate

For each source (see sources.md):

  • Authority: Who wrote this? What credentials?
  • Recency: When? Still valid?
  • Evidence: Claims backed by data?
  • Bias: Any agenda or conflict?
  • Corroboration: Do others confirm this?

Flag low-credibility sources. Weight findings accordingly.

4. Deepen

Research is iterative:

  • Initial findings reveal new questions
  • Follow promising threads
  • Fill gaps identified
  • Stop when: answer is clear, returns diminish, or budget exhausted

Document decision to stop and why.

5. Synthesize

Merge findings (use Synthesize skill patterns):

  • Reconcile contradictions explicitly
  • Weight by source quality
  • Note confidence levels
  • Identify remaining unknowns

6. Document

Research trail matters:

  • Sources consulted (with links)
  • Search queries used
  • Why certain sources were weighted higher
  • What was NOT found (gaps)

7. Deliver

Format per user needs (see output-formats.md):

  • Executive: BLUF + key findings + confidence
  • Academic: Full methodology + citations
  • Working doc: All findings for further work

Output Format (Default)

DEEP RESEARCH: [Topic]

ANSWER
[Direct answer to the question — 2-3 sentences]

CONFIDENCE: [High/Medium/Low] — [why]

KEY FINDINGS
• [Finding 1] — [source]
• [Finding 2] — [source]
• [Finding 3] — [source]

CAVEATS
• [Important limitation or uncertainty]

GAPS
• [What couldn't be determined]

SOURCES ([count])
[Numbered list with credibility notes]

METHODOLOGY
[Brief: what was searched, how sources were evaluated]

Depth Levels

Level Effort Sources When
Quick 5-10 min 3-5 Simple factual questions
Standard 30-60 min 8-15 Most research requests
Thorough 2-4 hours 20-30 Important decisions
Exhaustive Days 50+ Critical, high-stakes

Confirm depth before starting. Adjust if findings warrant.


References: methodology.md, sources.md, output-formats.md

安全使用建议
This skill appears internally consistent and matches its stated purpose. Before installing: (1) confirm you are comfortable with the agent fetching and quoting external web content (it will record and surface search queries and links); (2) be mindful not to ask it to research private or sensitive internal systems unless appropriate access controls are in place, since the skill's logging of queries/sources could capture sensitive identifiers; (3) verify that your platform's 'SkillBoss API Hub' (or equivalent search integration) is authorized and audited for your environment. If you need the agent to avoid external web queries or to restrict sources, ask for that constraint up front.
功能分析
Type: OpenClaw Skill Name: abe-deep-research Version: 1.0.0 The skill bundle provides a comprehensive and professional framework for an AI agent to conduct systematic research. The files (SKILL.md, methodology.md, sources.md, and output-formats.md) contain purely instructional content focused on research methodology, source evaluation, and reporting templates, with no evidence of malicious intent, data exfiltration, or unauthorized command execution.
能力评估
Purpose & Capability
Name/description (exhaustive multi-source research) match the content: the SKILL.md plus methodology/sources/output templates describe research workflows and cite search vectors. No binaries, env vars, or installs are requested that would be unrelated to web research.
Instruction Scope
Runtime instructions are limited to searching, evaluating, iterating, and documenting sources. It explicitly tracks queries, sources, and decisions. It does reference using the platform 'SkillBoss API Hub' to run multi-engine searches, which is consistent with a research task and does not instruct reading local files or unrelated credentials.
Install Mechanism
There is no install spec and no code files; this is instruction-only, which minimizes disk/writable install surface.
Credentials
The skill requires no environment variables, credentials, or config paths. The instructions do not request secrets or other unrelated credentials.
Persistence & Privilege
always is false and the skill does not request persistent system modifications or privileged config changes. Autonomous invocation is allowed (platform default) but not elevated by this skill.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install abe-deep-research
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /abe-deep-research 触发
  4. 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
v1.0.0
Deep Research skill v1.0.0 – Initial Release - Introduces a structured, multi-step protocol for exhaustive investigation: Scope, Search, Evaluate, Deepen, Synthesize, Document, Deliver. - Emphasizes methodology tracking, source evaluation, and iterative research depth. - Clarifies depth levels (Quick, Standard, Thorough, Exhaustive) with guidelines for each. - Provides default and customizable output formats, ensuring transparency and source attribution. - Clearly distinguishes roles and workflows for deep research versus surface search or synthesis tasks.
元数据
Slug abe-deep-research
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

abe-deep-research 是什么?

Conduct exhaustive multi-source investigation with methodology tracking, source evaluation, and iterative depth. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 67 次。

如何安装 abe-deep-research?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install abe-deep-research」即可一键安装,无需额外配置。

abe-deep-research 是免费的吗?

是的,abe-deep-research 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

abe-deep-research 支持哪些平台?

abe-deep-research 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 abe-deep-research?

由 AbelTennyson(@abeltennyson)开发并维护,当前版本 v1.0.0。

💬 留言讨论