Skip to content
Zenlix
Plugin

dsh-superpowers

codeAnqiang-ma121Updated 4d ago

Open on GitHub

Superpowers (obra/superpowers) as a DeepSeek Harness plugin: the methodology skills plus their session bootstrap

agent-skillsai-agentcode-reviewcoding-agentdeepseekdeepseek-harnessdshdsh-pluginskillssuperpowerstdd技能增强代码审查测试驱动

Practical score

80 / 100

Setup

Ready to use

License

NOASSERTION

Language

JavaScript

Install

Quick start

Copy the command, or hand the whole task to your harness agent.

git clone https://github.com/codeAnqiang-ma/dsh-superpowers.git
Install with your agent

Please install the DeepSeek Harness plugin "dsh-superpowers" for me. - GitHub repository: codeAnqiang-ma/dsh-superpowers (https://github.com/codeAnqiang-ma/dsh-superpowers) - Type: a Cordis plugin (installed into a DSH profile) - It should work out of the box…

From the README

A cleaned excerpt from the project's own documentation.

dsh-superpowers English 中文 dsh-superpowers adds obra/superpowers support to DeepSeek Harness. It registers 14 skills for brainstorming, planning, TDD, debugging, and code review, and keeps the using-superpowers bootstrap active throughout the session.…

Open on GitHub

Project details

Repository
codeAnqiang-ma/dsh-superpowers
by
codeAnqiang-ma
License
NOASSERTION
stars
12
Forks
1
Updated
Nov 7, 2026
Created
Aug 13, 2026
Language
JavaScript
Indexed from
topic

Related entries

Similar tools from the same corner of the ecosystem.

View all
Plugin

dsh-auto-memory

AskTheWay

Trustworthy memory for DeepSeek Harness — 4-state trust machine, evidence chains, audited injections. Zero servers, just Markdown.

agent-contextagent-harnessagent-memory
129Ready to use
85/100
Plugin

dsh-bigfish

gosomea

Animated DSH Web pet with model-adaptive output pacing, tool-state reactions, replaceable character packs, and a bundled skill for creating or extending pet animations.

agentagent-skillsai-agent
27Ready to use
85/100
Plugin

dsh-auto-review

PerryLink

Second-model AI auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

ai-agentai-agentsai-safety
248Needs setup
83/100