deep-research
When a topic needs thorough investigation from multiple sources → multi-source search + evidence assembly + structured report.
Skill by cklxx
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/cklxx-deep-research
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/deep-research
What's inside
- Skill name
deep-research- Description
- When a topic needs thorough investigation from multiple sources → multi-source search + evidence assembly + structured report.
- License
- MIT
- Instructions
- 27 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- SKILL.md
- run.py
- __init__.py · tests/
- test_deep_research.py · tests/
SKILL.md (first lines)
# deep-research 多源检索 + 证据汇编 + 结构化报告。 ## 调用 ```bash python3 skills/deep-research/run.py --topic '研究主题' --queries '["关键词1","关键词2"]' --max_results 5 --depth basic ``` ## 参数 | 参数 | 类型 | 必填 | 说明 | |------|------|------|------| | topic | string | 是 | 研究主题 | | queries | string[] | 否 | 搜索关键词，默认自动生成 3 条 | | max_results | int | 否 | 每条 query 结果数，默认 5 | | depth | string | 否 | "basic" 或 "advanced" | | fetch_urls | string[] | 否 | 额外抓取全文的 URL | ## 输出 返回 JSON，包含 `searches`（搜索结果）、`fetched_pages`（抓取页面）、`summary_prompt`（综合提示）。 LLM 拿到结果后，按「问题→发现/证据→置信度→影响/建议」结构化整理。
From cklxx/elephant.ai, MIT.
More from cklxx/elephant.ai
- 0.479score
feishu-bitable
cklxx
When 飞书多维表格 (Bitable) needs CRUD or management → create/query/edit apps, records, fields, views with advanced filtering and batch ops.
SkillDFreshness: D★ 11Claude Code +9 - 0.477score
moltbook-posting
cklxx
When the user wants to interact with Moltbook (AI agent social network) → post, browse, comment, vote, search via shell curl.
SkillDFreshness: D★ 11Claude Code +9 - 0.476score
anygen
cklxx
When user needs AnyGenIO content generation → unified CLI for task execution with progressive disclosure.
SkillDFreshness: D★ 11Claude Code +9 - 0.476score
notebooklm-cli
cklxx
When the user needs NotebookLM operations → unified CLI (command/op) returning structured results.
SkillDFreshness: D★ 11Claude Code +9 - 0.476score
audio-tts
cklxx
When the user wants text-to-speech audio → generate voice files locally (macOS say + afconvert, outputs m4a).
SkillDFreshness: D★ 11Claude Code +9 - 0.474score
code-review
cklxx
When coding is done and changes need review → multi-dimensional code review (SOLID, security, quality, edge cases), outputs structured report.
SkillDFreshness: D★ 11Claude Code +9 - 0.474score
browser-use
cklxx
When you need to interact with web pages using the user's logged-in browser → control Chrome via @playwright/cli daemon, reusing cookies/session with…
SkillDFreshness: D★ 11Claude Code +9 - 0.471score
diagram-to-image
cklxx
When a Mermaid diagram needs to be shared as an image → render to PNG/SVG.
SkillDFreshness: D★ 11Claude Code +9 - 0.471score
feishu-troubleshoot
cklxx
When 飞书 plugin errors or auth failures occur → troubleshoot with FAQ and authorization diagnostics.
SkillDFreshness: D★ 11Claude Code +9 - 0.471score
feishu-task
cklxx
When 飞书任务 (tasks/todos) need managing → CRUD tasks, subtasks, and task lists.
SkillDFreshness: D★ 11Claude Code +9 - 0.471score
feishu-im-read
cklxx
When 飞书 chat history needs reading → fetch group/DM messages, thread replies, and download attached files/images.
SkillDFreshness: D★ 11Claude Code +9 - 0.471score
feishu-calendar
cklxx
When 飞书日历 events or meetings need managing → CRUD calendar events, manage attendees, query free/busy status.
SkillDFreshness: D★ 11Claude Code +9
Signals
- Stars
- 11
- Forks
- 2
- Open issues
- 1
- Last commit (this folder)
- Mar 23, 2026 (7 months ago)
- Last release
- Feb 16, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/cklxx/elephant.ai
- Website
- cklxx.github.io/elephant.ai/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from cklxx
- 0.479score
feishu-bitable
cklxx
When 飞书多维表格 (Bitable) needs CRUD or management → create/query/edit apps, records, fields, views with advanced filtering and batch ops.
SkillDFreshness: D★ 11Claude Code +9 - 0.477score
moltbook-posting
cklxx
When the user wants to interact with Moltbook (AI agent social network) → post, browse, comment, vote, search via shell curl.
SkillDFreshness: D★ 11Claude Code +9 - 0.476score
audio-tts
cklxx
When the user wants text-to-speech audio → generate voice files locally (macOS say + afconvert, outputs m4a).
SkillDFreshness: D★ 11Claude Code +9 - 0.476score
anygen
cklxx
When user needs AnyGenIO content generation → unified CLI for task execution with progressive disclosure.
SkillDFreshness: D★ 11Claude Code +9 - 0.476score
notebooklm-cli
cklxx
When the user needs NotebookLM operations → unified CLI (command/op) returning structured results.
SkillDFreshness: D★ 11Claude Code +9 - 0.474score
code-review
cklxx
When coding is done and changes need review → multi-dimensional code review (SOLID, security, quality, edge cases), outputs structured report.
SkillDFreshness: D★ 11Claude Code +9
Cite this page
deep-research skill. Agent Mart. https://agentmart.dev/skills/cklxx-deep-research (last updated 2026-10-24)