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
Ambitious multi-plugin AGI accountability harness with tests and clear licensing, but install docs are external and unve
README documents a node --test test suite, a CHANGELOG, and a structured multi-plugin layout with a preset directory.
No download-and-execute or plaintext-secret patterns are shown; the optional DEEPSEEK_API_KEY is read from environment, but the NOASSERTION license field and bundled third-party model warrant caution.
Targets a real gap by externalizing honesty, resource-requesting, and cross-session memory that single-shot model training cannot enforce.
Last updated 2026-09-07 with a CHANGELOG and tested DSH versions 0.1.2-rc.1 and 0.1.3-alpha.2, indicating active development.
README explains concepts and components well, but the actual install command is unknown and installation is deferred to an external docs/INSTALL.md not shown here.
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
AGI harness: accountability loop, reputation, externalized learning (DSH plugin suite)
dsh-agi-harness has 4 stars and 0 forks on GitHub, last updated 2026-09-07.
dsh-agi-harness 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。