Qiushi Skill
Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done. 求是Skill——从经典唯物辩证法与实践哲学中提炼出一条总原则和九大方法论工具武装AI大脑。
Qiushi Skill is an open-source agent skill by HughYau, written mainly in JavaScript, with 3,846 GitHub stars and the MIT license. Its code was last updated Oct 1, 2026. The latest npm release is qiushi-skill 2.0.0, published Sep 6, 2026, with 25 downloads last week.
Scan summary: scanned Nov 5, 2026 at commit 5ace717. No capabilities flagged by our checks. Scan policy
What Qiushi Skill can touch
- Our checks did not find this. The tool may still do it.Run shell commandsNot seen in this scan
- Our checks did not find this. The tool may still do it.Run dynamic codeNot seen in this scan
- Our checks did not find this. The tool may still do it.Read or write filesNot seen in this scan
- Our checks did not find this. The tool may still do it.Read environment and secretsNot seen in this scan
- Our checks did not find this. The tool may still do it.Control a web browserNot seen in this scan
- Our checks did not find this. The tool may still do it.Connect to databasesNot seen in this scan
- Our checks did not find this. The tool may still do it.Read or send messagesNot seen in this scan
- Our checks did not find this. The tool may still do it.Touch money or tradingNot seen in this scan
- Our checks did not find this. The tool may still do it.Connect to the internetNot run in this scan
"Not seen" means our checks did not find it, and the tool may still do it. Covers commit 5ace717, Nov 5, 2026. See the scan policy.
Before you install Qiushi Skill
AgenticMart scanned Qiushi Skill on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.
What it can access
- A skill is instructions plus optional scripts. The instructions steer your agent; any scripts run on your machine when the agent uses the skill.
Before you install
- Pin the version you reviewed instead of always installing the latest release.
- Read the tool list or scripts before the first run, and keep approval prompts on for actions that write, send or delete.
- Maintained by HughYau on GitHub, 3,846 stars and 286 forks. Popularity is not proof of safety.
- Last code change: Oct 1, 2026.
- Open-source license: MIT.
Qiushi Skill is an open-source agent skill by HughYau, written mainly in JavaScript. Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done. 求是Skill——从经典唯物辩证法与实践哲学中提炼出一条总原则和九大方法论工具武装AI大脑。
At a glance
- Stars
- 3.8k
- Forks
- 286
- Language
- JavaScript
- License
- MIT
- Created
- Mar 2026
- Last update
- Oct 1, 2026
- Type
- Agent Skill
- Price
- Free
Topics
Questions about Qiushi Skill
What is Qiushi Skill?
Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done. 求是Skill——从经典唯物辩证法与实践哲学中提炼出一条总原则和九大方法论工具武装AI大脑。
Who maintains Qiushi Skill?
Qiushi Skill is maintained by HughYau on GitHub (HughYau/qiushi-skill). AgenticMart lists it from public repository data.
Is Qiushi Skill safe to use?
AgenticMart scanned Qiushi Skill on Nov 5, 2026 with automated checks for hidden code, known-malicious packages, leaked secrets and vulnerable dependencies. The result covers one commit under our scan policy, so review what access you give it and check any advisories shown here.
What license does Qiushi Skill use?
It is published under the MIT license.
Qiushi Skill alternatives
View more →Similar agent skills in Productivity & Workflow, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Qiushi Skill (this page) HughYau | 3.8k | MIT | Oct 1, 2026 | Scanned, no flagged issues |
| Eigent eigent-ai | 16k | Apache-2.0 | Nov 1, 2026 | Scanned, no flagged issues |
| Kami tw93 | 12k | MIT | Nov 1, 2026 | Scanned, no flagged issues |
| Skill anbeime | 9k | None found | Nov 1, 2026 | Not scanned yet |
| Refly refly-ai | 7.5k | None found | Oct 21, 2026 | Not scanned yet |
| N8n Skills czlonkowski | 6.6k | MIT | Oct 24, 2026 | Scanned, no flagged issues |