Skip to content

Comments

Feature/review workflow#2659

Closed
0h-n0 wants to merge 107 commits intocotes2020:masterfrom
0h-n0:feature/review-workflow
Closed

Feature/review workflow#2659
0h-n0 wants to merge 107 commits intocotes2020:masterfrom
0h-n0:feature/review-workflow

Conversation

@0h-n0
Copy link

@0h-n0 0h-n0 commented Feb 15, 2026

Type of change

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Improvement (refactoring and improving code)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • Documentation update

Description

Additional context

0h-n0 and others added 28 commits February 15, 2026 19:24
@0h-n0 @claude
refactor: 既存記事の構造改善 - 概要をトップに配置
d088d2e 
- h1タイトル削除（重複解消）
- 論文概要/ブログ概要を最初のセクションに移動
- Zenn記事リンクを概要内に配置
- 情報源を2番目のセクションに移動

対象記事（2026-02-14の5件）:
- techblog-aws-bedrock-structured-outputs.md
- paper-2601-09929.md
- paper-2512-23712.md
- conf-minicheck-emnlp2024.md
- conf-haloscope-neurips2024.md

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0
Merge pull request #14 from 0h-n0/refactor/improve-article-structure
a93ae67 
記事構造改善: 概要をトップに配置しタイトル重複を解消
@0h-n0 @claude
feat: arXiv論文解説 - OPRO (Large Language Models as Optimizers)
bf3a6fc 
Zenn記事「Claude Codeプロンプト管理術」の深掘り記事

## 内容
- OPRO手法の詳細解説（自然言語による最適化）
- 数式・アルゴリズム実装
- Claude Code CLAUDE.md最適化への応用例

## 関連Zenn記事
https://zenn.dev/0h_n0/articles/21f1740dc0ddd9

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0
Merge pull request #15 from 0h-n0/article/paper-opro-2309-03409
08c3cce 
arXiv論文解説: Large Language Models as Optimizers (OPRO)
@0h-n0 @claude
fix: add math and mermaid flags to existing articles (#37)
1fc0c29 
Adds math: true and mermaid: true to frontmatter of technical articles
containing LaTeX equations to enable proper MathJax rendering.

Affected articles:
- 2026-02-15-paper-opro-llm-optimizers.md (8 math blocks)
- 2026-02-14-paper-2512-23712.md (add missing mermaid flag)

Fixes broken equation rendering (raw LaTeX → formatted equations).

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: NVIDIA研究解説 エージェントAIのコード実行セキュリティ (#36)
979402d 
CVE-2024-12366を題材にしたAIコード生成の脆弱性と防御戦略。
サニタイゼーションの限界、サンドボックス実装、多層防御の詳細解説。

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: NeurIPS論文解説 AvaTaR - LLMエージェントツール使用最適化 (#35)
e9b23b6 
対比推論によるエージェント性能改善手法。
Actor-Comparatorアーキテクチャ、7タスクで平均14%向上の詳細解説。

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: 論文解説 Infini-attention - 無限長コンテキスト実現 (#34)
449898c 
Google DeepMindによる長文脈Transformer最適化手法。
圧縮メモリ機構、線形メモリ増加、1M-token処理の詳細解説。

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: Anthropic研究解説 プロンプトインジェクション防御の最前線 (#33)
387a5b4 
Claude Opus 4.5の強化学習ベースプロンプトインジェクション対策。
3層防御アーキテクチャ（RL、分類器、レッドチーム）とASR 1%達成の詳細解説。

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: 論文解説 AgentBench - LLMエージェント評価ベンチマーク (#32)
e6f4dae 
Zenn記事 a32342e48355ae の深掘り記事。
8環境でのエージェント評価、失敗パターン分析、実装詳細を解説。

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: Anthropic Agent Skills解説 - Progressive Disclosure、コンテキスト効率化、セキュ…
fb57492 
…リティ統合の3原則 (#31)

Zenn記事 'Claude Codeスキル作成完全ガイド' の深掘り記事

## 情報源
- 種別: tech_blog
- URL: https://claude.com/blog/equipping-agents-for-the-real-world-with-agent-skills
- ドメイン: anthropic.com

## 記事概要
Anthropic公式のAgent Skills設計思想を修士レベルで解説。Progressive Disclosure（83%トークン削減）、Code Execution Integration、セキュリティベストプラクティスを数式・実装例で詳説。

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: new article 'HyPA-RAG: ハイブリッド検索のパラメータ適応最適化' (#30)
31af08b 
arXiv 2409.09046 / NAACL 2025のHyPA-RAGを解説。
BM25 + Dense + Knowledge Graphのハイブリッド検索と
クエリ複雑度に応じたパラメータ適応で法律ドメインRAGを最適化。

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: new article 'FAISS完全ガイド: 大規模ベクトル検索の実装と最適化' (#29)
47f58de 
Meta AI FAIRのFAISSライブラリ（arXiv 2401.08281）の技術詳細を解説。
HNSW、IVF、Product Quantizationによる10億規模ベクトル検索の実現と
RAGシステムへの統合パターンを網羅。

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: new article 'Speculative RAG: Draftingで推論を高速化する最新手法' (#28)
9de4506 
Google ResearchのSpeculative RAGの技術詳細を深掘り解説。
並列ドラフト生成と検証を組み合わせた新しいRAGアーキテクチャにより、
51%の遅延削減と12.97%の精度向上を実現。

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: RAG Architectures & Robustness Survey (#27)
4183238 
arXiv 2506.00054の詳細解説記事

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: RAG Comprehensive Survey - Evolution and State-of-the-Art (#26)
34994c2 
arXiv 2410.12837の詳細解説記事

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: arxiv paper deep-dive for LLM cost optimization (#25)
94394b5 
Added detailed analysis of research paper related to Zenn article cc2c10a61cfeac

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: arxiv paper deep-dive for LLM cost optimization (#24)
3709041 
Added detailed analysis of research paper related to Zenn article cc2c10a61cfeac

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: arxiv paper deep-dive for LLM cost optimization (#23)
e052e89 
Added detailed analysis of research paper related to Zenn article cc2c10a61cfeac

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: arxiv paper deep-dive for LLM cost optimization (#22)
016d632 
Added detailed analysis of research paper related to Zenn article cc2c10a61cfeac

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: arxiv paper deep-dive for LLM cost optimization (#21)
48e508e 
Added detailed analysis of research paper related to Zenn article cc2c10a61cfeac

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: arxiv article SE 3.0: AI-Nativeソフトウェア工学 (#20)
659c0af 
関連Zenn記事: AIネイティブ開発で生産性10倍 (32981c687ab3cf)

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: techblog article Google DeepMind CodeMender解説 (#19)
86889b4 
関連Zenn記事: AIネイティブ開発で生産性10倍 (32981c687ab3cf)

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: techblog article Meta Code Llama解説 (#18)
1fa2c7e 
関連Zenn記事: AIネイティブ開発で生産性10倍 (32981c687ab3cf)

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: arxiv article AI-NativeソフトウェアライフサイクルとV-Bounceモデル (#17)
cf4071f 
関連Zenn記事: AIネイティブ開発で生産性10倍 (32981c687ab3cf)

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: arxiv article LLMベースのコード生成エージェント完全サーベイ (#16)
fe70e01 
関連Zenn記事: AIネイティブ開発で生産性10倍 (32981c687ab3cf)

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
fix: HTMLProoferエラー修正 - 架空リンクをコード表記に変更
085475d 
- [reference.md](reference.md) → `reference.md`
- [examples.md](examples.md) → `examples.md`

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
@0h-n0 @claude
feat: add PR review workflow and template
bfd2447 
- Add GitHub Actions workflow for automated validation
  - Jekyll build check
  - htmlproofer for link validation
  - Math block pairing check
  - Frontmatter validation

- Add PR template with review checklist
  - Visual confirmation (math, Mermaid, markdown)
  - Content quality checks
  - Structure consistency validation
  - Technical validity checks

These automated checks ensure article quality before human review.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
@github-actions github-actions bot closed this Feb 15, 2026
@github-actions
Copy link

github-actions bot commented Feb 15, 2026

Oops, it seems you've opened an invalid pull request. No worries, we'll close it for you.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@0h-n0