EverOS
EverMind-AI
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
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
Useful skill-comparison harness with broad scenario coverage, but install steps and engineering rigor are unclear from t
README shows a Mermaid workflow and capability matrix but no tests, CI badges, or dev setup, so engineering rigor cannot be verified.
No install command is given and the README mentions downloading a skill zip and optional image rendering, but no plaintext secrets or excessive permissions are visible, so a neutral score applies.
It addresses a real pain point by running baseline plus multiple candidate skills on the same task and producing a local HTML report with side-by-side outputs and a winner handoff.
Last updated 2026-08-19, not archived, and the README documents a v1.1 feature addition, indicating active development.
The README explains triggers, workflow, and a detailed scenario/candidate matrix, but the install command is listed as unknown and DSH plugin installation is only linked, not shown.
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
Compare multiple skills on the same task and pick the winner.
forkprobe has 71 stars and 5 forks on GitHub, last updated 2026-08-19.
forkprobe is distributed under the MIT license.
forkprobe 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:skill-comparison、skills、agent-workflow、claude-code、research-writing。