A Python skill-store that indexes AI agent skills — including DeepSeek Harness / dsh plugins — from many upstream sources, auto-synced every 24h and exportable to JSON / CSV.
DSH integration
Ecosystem-related
Author-claimed
Safety audit
Unaudited
Last verified
2026-09-02
License
Not specified by the author
01What can it help you accomplish?
Browse a continuously-updated catalog of AI agent skills — including DeepSeek Harness / dsh plugins — and pick one to install
A browsable, categorized skill directory (by function, source and Star count) plus exportable JSON / CSV data snapshots
Developers and agent users who want a single, fresh index of skills across Anthropic, Vercel, Cloudflare, Google Labs, Hugging Face and the DSH plugin ecosystem
Keep a local skills catalog auto-synced and export it for secondary development
A local clone that runs `python main.py` to crawl/refresh every 24h, with `--stats` and `--export skills.csv` outputs you can query or build on
Self-hosters and analysts who want an offline, automated, up-to-date skill registry instead of relying on a single upstream list
02How to install into DeepSeek Harness
Prerequisites
- Python 3 with pip — the README's install steps run `pip install -r requirements.txt` and `python main.py`
- Git, to clone the repo (`git clone https://github.com/anbeime/skill.git`)
Installation steps
- 01
Clone the repo: `git clone https://github.com/anbeime/skill.git` then `cd skill`
$ git clone https://github.com/anbeime/skill.git
- 02
Install dependencies: `pip install -r requirements.txt`
- 03
Run an update: `python main.py --once` for a one-time refresh, or `python main.py --daemon` to start the scheduled 24h crawler
Verify the integration
- `python main.py --stats` prints the collected statistics
- `python main.py --export skills.csv` writes the catalog to CSV you can open
03DSH integration and capability boundaries
Adjacent to the DSH ecosystem: the store lists DeepSeek Harness and dsh plugins as catalog sources, but it is a standalone Python skill aggregator (clone + `python main.py`), not a dsh plugin itself.
Curated dual skill library
Upstream sources: OpenAI Skills, VoltAgent awesome-agent-skills, Awesome DSH Plugin, and more→244 cataloged skills — 182 official (Anthropic, Vercel, Cloudflare, Google Labs, Hugging Face) + 62 local Chinese skills, tagged by function / source / Star
24-hour auto-update crawler
Upstream skill repositories→A refreshed catalog synced from upstream every 24h; run `python main.py --daemon` for the scheduled crawler
runs a scheduled crawler / daemon that fetches upstream repos every 24hJSON / CSV data export
The local catalog database→Exportable JSON and CSV snapshots for analysis and secondary development
04Who is it for? When not to use it?
Good for
- Developers and agent users who want a single, fresh index of skills across Anthropic, Vercel, Cloudflare, Google Labs, Hugging Face and the DSH plugin ecosystem
- Self-hosters and analysts who want an offline, automated, up-to-date skill registry instead of relying on a single upstream list
05Compatibility, maintenance and safety notes
- The catalog is built by crawling upstream repos and needs network access; it also depends on third-party sources (Anthropic, Vercel, Hugging Face, DSH plugin repos) that may change or go offline.
- It runs as a Python CLI (clone + `pip install -r requirements.txt` + `python main.py`); there is no packaged binary or desktop app — you operate it from source.
- The repo badge states CC BY 4.0, but the store is an index — each cataloged skill keeps its own upstream license, which the store does not re-license.
Python project, no release tag published (latest_release: null); README says the catalog auto-crawls upstream every 24h
06Frequently asked questions
Does the Skill Store include DeepSeek Harness / dsh plugins?
Yes — the catalog's data sources list Awesome DSH Plugin and deepseek-harness (the official deepseek-ai/deepseek-harness repo), and many dsh-* plugins appear as cataloged skills.
How do I install and run the Skill Store locally?
Clone the repo (`git clone https://github.com/anbeime/skill.git`), install dependencies with `pip install -r requirements.txt`, then run `python main.py --once` for a one-time update or `python main.py --daemon` for scheduled updates.
How fresh is the catalog, and can I verify it?
The README states the catalog auto-crawls upstream sources every 24 hours. After running, `python main.py --stats` shows collected statistics and `python main.py --export skills.csv` writes the catalog to CSV.
Can I export the catalog for my own use?
Yes — the store supports JSON and CSV export 'for data analysis and secondary development' (per README) once you run it locally.
What skill sources does the store aggregate?
It aggregates official skills from Anthropic, Vercel, Cloudflare, Google Labs and Hugging Face (182 official) plus 62 local Chinese skills, with 244 skills total and smart tagging by function, source and Star count.
07Related DSH workflows
archify
by tt-a1i
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
openviking
by volcengine
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
nocobase
by nocobase
NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of production-proven infrastructure and a WYSIWYG no-code interface, so you get both speed and reliability.
learn-harness-engineering
by walkinglabs
Harness engineering beginner tutorial, from 0 to 1
08Data and sources
- [Awesome DSH Plugin](https://github.com/awesome-dsh-plugin/awesome-dsh-plugin)
- [deepseek-harness](https://github.com/deepseek-ai/deepseek-harness)
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-02. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.