Prompt Sensei Agent Skill
by chengzhongweiLocal-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analyzes local history with explicit consent.
Prompt Sensei is an open-source agent skill by chengzhongwei, written mainly in JavaScript, with 109 GitHub stars and the Apache-2.0 license. Its code was last updated Jul 13, 2026.
Scan summary: scanned Nov 5, 2026 at commit ea1e381. Seen able to read environment and secrets. Scan policy
What Prompt Sensei 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
- Seen in this scan, either in the code or while it ran.Read environment and secretsFound in the code by our 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 ea1e381, Nov 5, 2026. See the scan policy.
Before you install Prompt Sensei
AgenticMart scanned Prompt Sensei 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 chengzhongwei on GitHub, 109 stars and 10 forks. Popularity is not proof of safety.
- Last code change: Jul 13, 2026.
- Open-source license: Apache-2.0.
Prompt Sensei is an open-source agent skill by chengzhongwei, written mainly in JavaScript. Local-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analyzes local history with explicit consent.
At a glance
- Stars
- 109
- Forks
- 10
- Language
- JavaScript
- License
- Apache-2.0
- Created
- Apr 2026
- Last update
- Jul 13, 2026
- Type
- Agent Skill
- Price
- Free
Topics
Questions about Prompt Sensei
What is Prompt Sensei?
Local-first prompt coach for Claude Code and Codex that improves prompts, observes prompting habits, and analyzes local history with explicit consent.
Who maintains Prompt Sensei?
Prompt Sensei is maintained by chengzhongwei on GitHub (chengzhongwei/Prompt-sensei). AgenticMart lists it from public repository data.
Is Prompt Sensei safe to use?
AgenticMart scanned Prompt Sensei 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 Prompt Sensei use?
It is published under the Apache-2.0 license.
Prompt Sensei alternatives
View more →Similar agent skills in Research & Analysis, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.
| Name | Stars | Licence | Last updated | Scan |
|---|---|---|---|---|
| Prompt Sensei (this page) chengzhongwei | 109 | Apache-2.0 | Jul 13, 2026 | Scanned, no flagged issues |
| RuView ruvnet | 102k | MIT | Nov 1, 2026 | Scanned, no flagged issues |
| AI Research SKILLs Orchestra-Research | 14k | MIT | Oct 11, 2026 | Scanned, no flagged issues |
| Auto Empirical Research Skills brycewang-stanford | 4.9k | None found | Oct 30, 2026 | Not scanned yet |
| Council Of High Intelligence 0xNyk | 4.7k | MIT | Oct 26, 2026 | Scanned, no flagged issues |
| Serenity Skill muxuuu | 4.1k | MIT | Oct 11, 2026 | Scanned, no flagged issues |