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 local-first, human-in-the-loop skill generator for DSH that is well documented and actively maintained, though version
README references a CHANGELOG, architecture baseline, design docs, a compatibility probe directory, and a CONTRIBUTING guide, indicating structured engineering, but no CI or test suite is visible in the provided information.
The README states it stores no model keys, does not copy full sessions, filters/truncates/redacts content before model analysis, requires explicit user approval before writing skills, and never guesses storage locations, which are concrete low-risk design choices.
It addresses a real and common pain point of repeatedly re-teaching agents the same corrections, constraints, and workflows across sessions, and produces portable native DSH Skills that survive uninstall.
Last updated 2026-08-25 with a documented 0.4.0 release, explicit version compatibility notes, and a fallback install path for older DSH versions, indicating active maintenance.
The README covers install, usage, review flow, learning scope, opt-out, data retention, update/uninstall, and troubleshooting with error codes, plus linked deeper docs, though it is primarily in Chinese with an English variant.
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INSTALL REFERENCE
dsh plugin --profile web add dsh-run2skill@0.3.0This command passed the install-plan safety check and can be executed by a DSH host; verification status is not equivalent to a security audit or official背书。
PROJECT TOPICS
VALIDATION LADDER
FAQ
Automatically turn successful DeepSeek Harness sessions into reusable, reviewable Agent Skills.
dsh-run2skill has 10 stars and 2 forks on GitHub, last updated 2026-08-25.
dsh-run2skill is distributed under the MIT license.
dsh-run2skill 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:agent-skills、automatic-skill-learning、run-to-skill、skill-generator、agent-learning。
Tiger3807861189
DeepSeek V4 × J-Space capability realization report — benchmark evidence that J-Space reduces capability-realization loss on DeepSeek V4.
alaliqing
📖 Cross-agent research paper toolkit for Claude Code, Codex, OpenCode, and DeepSeek Harness—quick summaries, deep study materials, code demos, and a local web viewer.
pingfanfan
From scratch, understand DeepSeek Harness's 'everything can be a plugin' — zero-basis plugin development tutorial (with 22 Chinese Skill examples) | Zero-to-plugin tutorial for DeepSeek Harness
xmutfyh
DeepSeek Harness (DSH) academic writing guard for papers — remove AI flavor from papers / AI-writing style detection, evidence preservation, journal-fit calibration, manuscript proofreading, writing_audit & automatic checks. Local, zero network, zero LLM.
maddogfinance
Trading research workbench for DeepSeek Harness (dsh): typed market-data seam, deterministic indicators, interactive chart cards ｜ Trading research workbench plugin: data seam · deterministic indicators · interactive K-line cards
literaf
AI4Scholar for DeepSeek Harness (dsh): 38 native academic tools — Semantic Scholar, PubMed, Google Scholar, arXiv, bioRxiv/medRxiv, DOI, full text, auto-cite, figures, unified search. Powered by ai4scholar.net