#
ENJA

AgenticResearchWiki

HaowenHou/AgenticResearchWiki

AgenticResearchWiki provides an agent-native markdown wiki skeleton and set of instructions for managing long-horizon AI research projects. It allows coding agents to maintain persistent context, navigate documentation via wiki-style links, and automatically write back task outcomes.

29 4MITUpdated 2026-04-05

Overview

This skill framework equips AI assistants with a structured project wiki repository template. By establishing a central entry point at Overview.md and utilizing progressive disclosure principles, it prevents context overload and enables seamless multi-session tracking for data, training, and evaluation workflows.

Capabilities

  • Navigate project documentation using wiki-style [[ ]] links
  • Perform progressive disclosure by reading relevant domain overviews on demand
  • Automatically write back task outcomes, experiment logs, and records into corresponding markdown files
  • Import existing external notes and classify them into correct project directories

Best for

Managing long-horizon AI research projects with multiple coding agents, Providing persistent project memory and documentation for Claude Code, Cursor, and Codex, Auto-updating experiment records, training results, and data pipelines into a structured knowledge base

Works with

Claude CodeCodexCursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
73
Task usefulness20%77 → +15.4

実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 AIによるcapabilities/use-cases解析

Code quality15%90 → +13.5

実装・指示の品質。 AIによるSKILL.md/README解析

Maintenance15%70 → +10.5

リポジトリがどれだけ活発に保守されているか。 GitHub 最終push日時の新しさ

Documentation12%43 → +5.2

ドキュメントの充実度・分かりやすさ。 README/独自要約の情報量

Security15%80 → +12.0

危険・不審な挙動が無いか。 AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 AIによる独自性判定

Popularity8%39 → +3.1

コミュニティの採用度。 GitHub Stars/Forks(対数スケール)

Compatibility5%100 → +5.0

対応AIエージェントの広さ。 AIによる対応エージェント判定

Weighted total73.2 / 100

ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →

Security considerations

Operates locally on markdown files and repository scripts. Review any imported third-party notes or untrusted batch inputs before allowing agents to process them.

Categories

Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.