New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Repository

liangdabiao/Claude-Code-Deep-Research-main agent skills

Every skill in the liangdabiao/Claude-Code-Deep-Research-main repository on GitHub, ranked by score, with the commands to install them.
skills
5
GitHub stars
290

GitHub description: “利用claude code agent框架一步一步实现deep research！很强大很简单的skills。我一步一步介绍实现deep research，因为deep research就是agent框架第一应用，对比一下各个框架实现这个deep research，就知道哪个框架才是真厉害。简化版：https://github.com/liangdabiao/deep-research-agent-skill”

Stars
290 (45 forks)
Licence
No licence
Last push
Dec 2025
Created
Dec 2025
Homepage
deep-research-agent.liangdabiao.com
Source
github.com/liangdabiao/Claude-Code-Deep-Research-main
  • claude-code

Install all skills

skills CLI (any agent)
npx skills add liangdabiao/Claude-Code-Deep-Research-main

Add --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).

Skills in liangdabiao/Claude-Code-Deep-Research-main, ranked

Ranked by score. Sort bymost stars,trending,newest,recently updated

Skills in liangdabiao/Claude-Code-Deep-Research-main, ranked
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
1
1.Question Refiner

将原始研究问题细化为结构化的深度研究任务。通过提问澄清需求，生成符合 OpenAI/Google Deep Research 标准的结构化提示词。当用户提出研究问题、需要帮助定义研究范围、或想要生成结构化研究提示词时使用此技能。

liangdabiao/Claude-Code-Deep-Research-main2901 repo~1.4kAutomated safety check: PassNo licence9 mo ago
2
2.Citation Validator

验证研究报告中所有声明的引用准确性、来源质量和格式规范性。确保每个事实性声明都有可验证的来源，并提供来源质量评级。当最终确定研究报告、审查他人研究、发布或分享研究之前使用此技能。

liangdabiao/Claude-Code-Deep-Research-main290—~1.4kAutomated safety check: PassNo licence9 mo ago
3
3.Got Controller

Graph of Thoughts (GoT) Controller - 管理研究图状态，执行图操作（Generate, Aggregate, Refine, Score），优化研究路径质量。当研究主题复杂或多方面、需要策略性探索（深度 vs 广度）、高质量研究时使用此技能。

liangdabiao/Claude-Code-Deep-Research-main290—~1.6kAutomated safety check: PassNo licence9 mo ago
4
4.Research Executor

执行完整的 7 阶段深度研究流程。接收结构化研究任务，自动部署多个并行研究智能体，生成带完整引用的综合研究报告。当用户有结构化的研究提示词时使用此技能。

liangdabiao/Claude-Code-Deep-Research-main290—~1.2kAutomated safety check: PassNo licence9 mo ago
5
5.Synthesizer

将多个研究智能体的发现综合成连贯、结构化的研究报告。解决矛盾、提取共识、创建统一叙述。当多个研究智能体完成研究、需要将发现组合成统一报告、发现之间存在矛盾时使用此技能。

liangdabiao/Claude-Code-Deep-Research-main290—~1.6kAutomated safety check: PassNo licence9 mo ago

Questions, answered from the data.

What is the best skill in liangdabiao/Claude-Code-Deep-Research-main?

Question Refiner from liangdabiao/Claude-Code-Deep-Research-main ranks first of the 5 skills in liangdabiao/Claude-Code-Deep-Research-main listed here, with the highest score: its repository has 290 GitHub stars, 1 other GitHub owner carry a copy, its SKILL.md loads about 1.4k tokens and it passes the automated safety check with no findings. Next come Citation Validator and Got Controller.

Are the skills in liangdabiao/Claude-Code-Deep-Research-main official?

None yet. All 5 skills in liangdabiao/Claude-Code-Deep-Research-main listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.

How do I install all skills from liangdabiao/Claude-Code-Deep-Research-main?

Run npx skills add liangdabiao/Claude-Code-Deep-Research-main in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.

How are these skills ranked?

By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.

More from liangdabiao

Categories

Products these skills work with