跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Ara Rigor Reviewer

技能 已验证 活跃

Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, methodological rigor) and producing a constructive, severity-ranked report with a Strong Accept-to-Reject recommendation. Use after Level 1 structural validation passes, when an ARA needs an objective epistemic critique before publication or release.

目的

To provide an objective, automated critique of the epistemic soundness of AI research artifacts, ensuring rigor before publication or release.

功能

  • Performs semantic epistemic review (Level 2)
  • Scores six dimensions of research rigor
  • Produces severity-ranked findings and reports
  • Outputs a Strong Accept-to-Reject recommendation
  • Operates on Agent-Native Research Artifacts

使用场景

  • Use after Level 1 structural validation passes on an ARA.
  • When an ARA needs objective epistemic critique before publication.
  • To ensure evidence relevance, falsifiability, scope calibration, argument coherence, exploration integrity, and methodological rigor.

非目标

  • Performing Level 1 structural validation.
  • Executing code or fetching external URLs.
  • Re-checking reference resolution or field presence.
  • Replacing human expert review entirely; provides a calibrated critique.

Practical Utility

  • info:Usage examplesWhile the SKILL.md details the procedure and findings format, concrete end-to-end examples of input ARA structure and resulting JSON reports are not explicitly provided.

安装

请先添加 Marketplace

/plugin marketplace add Orchestra-Research/AI-Research-SKILLs
/plugin install AI-Research-SKILLs@ai-research-skills

质量评分

已验证
95 /100
1 day ago 分析

信任信号

最近提交17 days ago
星标8.3k
许可证MIT
状态
查看源代码

类似扩展

ARA Research Manager

100

Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.

技能
Orchestra-Research

TradeMemory Protocol

100

Evolution Engine 的领域知识 — 支持 LLM 从原始 OHLCV 数据中自主发现策略。涵盖生成-回测-选择-进化循环、向量化回测、样本外验证和策略梯度。在发现交易模式、运行回测、进化策略或审查进化日志时使用。由“evolve”、“discover patterns”、“backtest”、“evolution”、“strategy generation”、“candidate strategy”触发。

技能
mnemox-ai

Gdpr Dsgvo Expert

100

GDPR and German DSGVO compliance automation. Scans codebases for privacy risks, generates DPIA documentation, tracks data subject rights requests. Use for GDPR compliance assessments, privacy audits, data protection planning, DPIA generation, and data subject rights management.

技能
alirezarezvani

Ship Gate

100

Pre-production audit that scans a codebase for security, database, deployment, code quality, AI/LLM, dependency, frontend, and observability issues. Intercepts deploy commands and blocks until critical items pass. Stack-agnostic. Use for "run ship gate", "am I ready to ship", "pre-launch audit", "can I deploy", "push to production", "go live checklist", "preflight check". Not for CI/CD setup or infra provisioning.

技能
alirezarezvani

Refactor Plan

100

Prioritized redesign action plan covering quick wins, medium effort, major rework

技能
Aboudjem

Type Audit

100

Typography-only audit covering font selection, type scale, readability, hierarchy, performance

技能
Aboudjem