RadarTopicsBuildersWeeklyReads
Open Source Radar
JuneYaooo/

nihaisha-nishi-tcm

GitHub

Nihaisha-nishi-tcm is a Python-based Agent Skill that enables retrieval and traceable analysis of Ni Haisha TCM course materials, with features for formula-pattern lookup, acupoint references, learning notes, and screenshot evidence indexing.

1.9kstars
415forks
2issues
2026since
Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap
browser-act/
skills

Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms when stuck. Parallel multi-task execution, independent multi-session operation, isolated multi-account browsing.

5.2k244Python
sickn33/
agentic-awesome-skills
328/wk

AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,000+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

44k6.5kPython
alirezarezvani/
claude-skills
422/wk

345 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 330+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.

24k3.3kPython
wuyoscar/
GPT-Image2-Skill

GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

4.1k356Python
VoltAgent/
awesome-agent-skills
426/wk

A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

30k3.2k
OthmanAdi/
planning-with-files
158/wk

Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Claude Code, Codex, Cursor, Kiro, OpenCode and 60+ agents via the Agent Skills standard.

26k2.2kShell
Reviewgenerated from repository data · Aug 5, 2026

What it is

A Claude Code / Codex / OpenClaw Skill packaged to be loaded into an agent. It enables natural language search across Ni Haisha TCM course materials, supports anatomy of conclusions, and indexes screenshot evidence.

How it works

The project provides course distillation methods and evidence indexing across PDFs, text notes, and screenshot references. It supports retrieval by symptoms, formulas, acupoints, course modules, lessons, or screenshot content, and it can produce learning-oriented synthesis, comparative notes on formulas and herbs, study plans, and indexed evidence.

Getting started

Installation

[See README installation section]

Instructions indicate default lightweight mode (no automatic downloads of extra models/assets) and that you can install by providing a prompt to clone and place the skill in the agent's skills directory. Example prompt:

帮我安装 nihaisha skill:
https://github.com/JuneYaooo/nihaisha-nishi-tcm

After installation, restart the agent to reload metadata.

Usage examples

用 nihaisha 帮我整理太阳中风和太阳伤寒的区别。
用 nihaisha 查桂枝汤、麻黄汤、葛根汤的方证分水岭。
用 nihaisha 按白话解释:为什么有的人感冒怕冷无汗,有的人怕风有汗?
用 nihaisha 找天纪里命宫、四化相关板书证据。

Notes: screenshot evidence is returned as relative paths under assets/screenshots; PDF evidence is formatted as pdf-evidence:<doc_id>#p<page>; non-PDF text evidence uses text-evidence:<doc_id>#s<section>.

Recent releases

The latest release entry is none; there are no numbered releases listed in the provided data.

Traction

Stars: 1883, Forks: 415, Open issues: 2.

Behind the repo

Linked organization or startup information is not provided in the data.

Caveats

License: none listed. Created: 2026-05-27. Last push: 2026-08-03. Language: Python. Topics include acupuncture, agent-skills, codex-skill, nihaisha, tcm, and related terms.

Safety/usage boundaries: The project explicitly states it is for course study, material retrieval, and theory整理, not for personal diagnosis, prescriptions, or dosing decisions. It emphasizes safety boundaries and non-clinical use.

SharePost on XLinkedIn
All trending reposRevenue-verified startups →