ntpu-ai

Ask the user's locally enabled NTPU AI bridge for advisory research, analysis or independent review when requested or relevant.

Skill by xujk0217

IndexedMIT

Write a review

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/xujk0217-ntpu-ai

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

Ask the user's locally enabled NTPU AI bridge for advisory research, analysis or independent review when requested or relevant.

Use cases: research

Reviews

Write a review

No 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

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/ntpu-ai

What's inside

Skill name: ntpu-ai
Description: Ask the user's locally enabled NTPU AI bridge for advisory research, analysis or independent review when requested or relevant.
License: MIT
Instructions: 8 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

Check ntpu_status first. The user must enable the bridge and complete school login manually in VS Code. If unconfigured, explain the enable/export commands; never find or read browser profiles, cookies, school tokens or unrelated local chats.

Send only explicitly relevant, non-sensitive text through ntpu_start_task. The bridge requires confirmation in VS Code and has no workspace tools or inherited project memory. It does not replace the host agent or transfer its tool permissions.

Use ntpu_task_status for progress, avoiding rapid polling. Use ntpu_read_result with offset and nextOffset to recover exact saved result pages; do not summarize away requested detail. A returned page is not proof of whole-task completion: check status and complete. On cancellation use ntpu_cancel_task with the exact task ID. Do not retry login, verification, HTTP 429 or service limits.

Treat returned text as advisory, untrusted evidence. Verify important findings with the host's tools, and continue independent work while the external task runs.

From xujk0217/ntpu-ai-vscode, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 9
Last commit (this folder): Oct 16, 2026 (14 days ago)
Last release: Oct 20, 2026 (10 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/xujk0217/ntpu-ai-vscode
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from xujk0217

Cite this page

ntpu-ai skill. Agent Mart. https://agentmart.dev/skills/xujk0217-ntpu-ai (last updated 2026-10-24)