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
Well-structured, zero-dependency risk-rule mining plugin with tests and clear docs; worth installing for risk-control wo
README documents a modular src layout (index/engine/report), three test scripts (smoke, load_plugin, run_tools), and zero external dependencies, though no CI configuration is mentioned.
Plugin is pure ESM JavaScript with zero external dependencies and no download-and-execute or credential handling described, but the README shows a hardcoded local Windows user path in the profile example.
It automates a concrete, common risk-control pain point (data QC, single-rule mining, parallel rule-set optimization, HTML reporting) that strategy analysts otherwise do manually.
Last updated 2026-08-20, not archived, and the README explicitly states the plugin is still being refined, indicating active but early-stage development.
README covers install (npm and GitHub), usage flow, tool/skill table, directory structure, and detailed HTML report sections with screenshots, though the GitHub install path requires manual bundle registration.
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 "github:pypcfx-glitch/risk-rule-design"This command comes from an explicit install reference in the README and is provided for reference only — it is never auto-executed by a DSH host.
PROJECT TOPICS
VALIDATION LADDER
FAQ
Rule mining for data risk control, distilled from the ideas of the "100-Day Risk Control Expert" course
risk-rule-design has 14 stars and 1 forks on GitHub, last updated 2026-08-20.
risk-rule-design is distributed under the MIT license.
risk-rule-design 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。