skills
anthropics
Public repository for Agent Skills
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, actively maintained enterprise workbench plugin with strong skill-management features, though install
README describes clear modular structure (client/employee/, staged unpack-and-land paths, ctx.skills read-back verification) but no tests or CI are mentioned, so rigor is only partially evidenced.
Security-conscious design is documented (credential references never inlined into YAML, static scan ported from AI-Infra-Guard, staged installs swapped in only after checks), but the marketplace download-and-install path and lack of explicit permission scoping keep this from scoring higher.
Solves a real enterprise pain point by unifying AI employees, knowledge bases, skills, MCP servers and DSH plugins into one session-manageable surface, with concrete value like surfacing shadowed/rejected skills that DSH only logs as a single warning.
Last updated 2026-08-25 with an active repository (not archived) and detailed changelog-style README content, indicating ongoing development.
README is thorough with install commands, environment variable tables, YAML config examples, and annotated screenshots, though the install command is listed as unknown in the repository metadata and some UI entry points are noted as hidden.
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
An enterprise workbench for the DeepSeek Harness: AI employees, knowledge bases, skills, MCP servers and DSH plugins, all manageable from a running session.
dsh-workbench has 4 stars and 2 forks on GitHub, last updated 2026-08-25.
dsh-workbench is distributed under the MIT license.
dsh-workbench 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-skill。