skills
anthropics
Public repository for Agent Skills
Electricitysheep/dsh-handbook
dsh-handbook is a tool for DeepSeek Harness. DeepSeek Harness (dsh) from 0 to 1 in-depth handbook: installation/plugin development/performance tuning/real-world cases/multi-Agent comparison with the same model (Chinese + English PDF)

REVIEW SCORECARD
✓ 无Risky检出 · 自动化扫描结果仅供参考,非官方背书
AI DEEP REVIEW
A well-documented Chinese-first handbook for DeepSeek Harness, valuable for onboarding but not an installable plugin its
README describes 15 chapters with runnable commands and a plugin template, but no CI, test suite, or source code structure is shown since the repo is HTML-based documentation.
No install command is provided and the README only shows the official `npx -y @deepseek-ai/dsh web` command plus a CC-BY-NC-SA license badge, so risk cannot be assessed from the given information.
It directly addresses the stated gap that official dsh docs are architecture-focused with no zero-to-one onboarding path, offering a 3-day roadmap, plugin dev tutorial, benchmarks, and a 1804-plugin ecosystem report.
Last updated 2026-09-07, not archived, and the README cites an active feedback pipeline with 19 trackable items plus ongoing discussion-forum updates.
The README provides a full 15-chapter table of contents, quickstart commands, learning path, cheatsheet, bilingual EN/PDF links, and inline content previews.
Generated by AI after reading the project README, as a decision aid; neutral scores are given when information is thin. Not an official endorsement.
正在读取 GitHub README...
README 暂时无法读取。
前往仓库PROJECT TOPICS
VALIDATION LADDER
FAQ
DeepSeek Harness (dsh) from 0 to 1 in-depth handbook: installation/plugin development/performance tuning/real-world cases/multi-Agent comparison with the same model (Chinese + English PDF)
dsh-handbook has 752 stars and 42 forks on GitHub, last updated 2026-09-07.
dsh-handbook is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
System reads GitHub Topics first, then compares against the in-site category dictionary and word-root rules. Current match:No valid category tags。