Skip to main content

good-student

Communityv0.1.1

Wrong-question diagnosis and study-action loop for parents and students — deterministic local core (SQLite, no cloud), host-model recognition gated by parent confirmation. Portable Agent Plugins v1 package (mcp.json + skills/); good-student MCP server pinned to immutable commit 2469cbb over uvx, with the good-student workflow skill bundled. Needs Python 3.10+ via uv. No credentials required; all data stays on-device and nothing is uploaded.

Open in Hermes Desktop
hermes plugins install good-student

README

From the reviewed commit 021375c; it updates when the author re-pins.

hermes-plugin-good-student

English | 中文

English

Good-student is a wrong-question diagnosis and study-action plugin for Hermes Agent, built for parents and students: upload wrong-question materials, confirm AI-recognized candidates, analyze weak knowledge points, generate study plans, and run reassessments.

Design principle: the host model understands; Good-student is the trustworthy core. Recognition output is candidates only — nothing enters the child's learning profile until a parent explicitly confirms it. All data lives in a local SQLite database on your machine; nothing is uploaded, no API keys required.

What it provides

  • An MCP server (gs) exposing 15 good_student_* tools (profiles, scores, candidate confirmation, analysis, plans, reassessments, weekly brief, export, doctor).
  • A bundled good-student skill that walks the agent through the recognize → confirm → analyze → plan → reassess loop with parent-confirmation gates.
  • Data directory defaults to the plugin's own PLUGIN_DATA space (GOOD_STUDENT_DATA).

Install

hermes plugins install harrylabsj/hermes-plugin-good-student
hermes plugins enable good-student

Requirements: Python ≥ 3.10 and uv (uvx) on PATH — the MCP server is launched via uvx --from git+https://github.com/harrylabsj/good-student@v0.1.1[mcp], pinned to the exact tag. First launch resolves and caches the environment automatically.

The upstream repo's docs/privacy/minor-data-protection.md documents the minor-data handling rules (local storage, no cloud, parent-consent gating).

Why the server key is gs

The full wire name is mcp__agent-plugin-good-student-<hash>__gs__good_student_record_reassessment-shaped. Hermes clamps long MCP tool names to the 64-character provider limit with a hash suffix, but a short server key keeps more names human-readable. gs is the same convention the official snyk (sn) and kiwi (kb) entries use.

中文

**Good-student(错题教练)**是面向家长和学生的错题诊断与学习行动插件:上传错题材料 → AI 识别为候选 → 家长确认 → 薄弱点分析 → 学习计划 → 复测闭环。

设计原则:宿主模型负责理解,Good-student 负责可信。 识别结果只是“候选”,未经家长 确认绝不写入学习画像。全部数据保存在本机 SQLite(PLUGIN_DATA 目录),不上传、无需 API Key。

  • MCP server(gs)暴露 15 个 good_student_* 工具(档案/成绩/候选确认/分析/计划/复测/周报/导出/体检)。
  • 捆绑 good-student 技能,引导智能体按“识别 → 确认 → 分析 → 计划 → 复测”顺序驱动工具。
  • 启动命令 uvx --from git+…@v0.1.1 钉死版本;首次启动自动解析并缓存环境。
  • 未成年人数据保护说明见上游仓 docs/privacy/minor-data-protection.md

License

MIT — see LICENSE.

eatwise Community

Eatwise (外卖营养教练) — local-first Chinese dietary coach: deterministic meal nutrition reviews, personal daily energy/nutrient targets, and consented on-device profile and meal history through 9 MCP tools over a bundled open food database (TFND + USDA FNDDS). No network, no accounts, no payments; profile schema rejects name/phone/ID/medical fields by design. Engine pinned to an immutable git commit (cbc08f6) over npx stdio; Portable Agent Plugins v1 package (mcp.json + skills/), needs Node.js 22.5+ on PATH. Disclosure — the engine's MCP tool descriptions and error messages are Chinese-only while the skills are English-first.

Tools
kiwi Community 0

Source suppliers and negotiate purchases through the Kiwi Buyer MCP server — an open-source A2A commerce runtime (pinned @harrylabsj/kiwi@0.8.0 over npx stdio), with the kiwi-buyer sourcing workflow skill bundled. Portable Agent Plugins v1 package (mcp.json + skills/); needs Node.js/npm on PATH. No credentials required; Kiwi never handles payments.

Tools
reading-buddy Community

Local-first WeRead (微信读书) reading companion: syncs bookshelf, reading stats and notes to the local machine and turns them into private reading cards and weekly/monthly reviews through 8 MCP tools, with a built-in fictional demo mode for previews. Engine pinned to an immutable git commit (e5f6673) over npx stdio; Portable Agent Plugins v1 package (mcp.json + skills/), needs Node.js 20+ on PATH. All data stays in PLUGIN_DATA; never posts to WeRead — cards and reviews are local files saved only after user confirmation. Disclosure — live mode sends your WEREAD_API_KEY as a Bearer token plus book ids and paging cursors to i.weread.qq.com (Tencent's WeRead agent gateway) and nothing else; the engine's MCP tool descriptions and error messages are Chinese-only while the skills are English-first; the engine's npm dependencies resolve as caret ranges at first launch.

Tools
wechat-social-assistant Community

Local-first WeChat relationship memory assistant for macOS: captures only what is visible in the WeChat window via system OCR/Accessibility, stores everything in a local SQLite database (0600/0700 permissions, no cloud), and serves contact briefs, follow-up planning, outreach drafts and weekly relationship reports through 32 MCP tools. Engine pinned to the immutable PyPI release wechat-social-assistant==1.5.1 over uvx stdio; Portable Agent Plugins v1 package (mcp.json + skills/), needs uv on PATH. All data confined to PLUGIN_DATA via WSA_ALLOWED_ROOT + path enforcement. Never reads WeChat databases, never injects into WeChat, never sends messages — outreach is drafts for human review only. Disclosure — reads WeChat only by screenshotting/OCR-ing and walking the macOS Accessibility tree of the frontmost window (not WeChat's databases or a bot API), compiles bundled Swift helpers with swiftc into ~/Library/Caches/wechat-social-assistant/bin on first use, and needs Screen Recording (optionally Accessibility) permission for the host terminal; no network egress, never sends messages.

Tools

← Back to the catalog · catalog built Sep 24, 2026