PRD-driven-context-engineering
mattgierhart/PRD-driven-context-engineering
This skill implements a PRD-driven context engineering framework that turns product documentation into a structured knowledge graph for AI agents. It ensures reproducible, high-context development through gated workflows and unique identification nodes.
193 9MITUpdated 2026-08-13
81
GreatOverview
PRD-driven context engineering solves AI amnesia and context drift by treating project documentation as live infrastructure. Using unique identifiers, plain markdown files, and progressive validation gates, it connects high-level product requirements directly to code implementation. The repository provides standardized workflows, readiness scoring, and agent coordination mechanisms to maintain high context density across multiple sessions.
Capabilities
- ▸Markdown-based knowledge graph management
- ▸Progressive PRD gated workflow execution
- ▸Source-of-truth ID tracking (BR-, UJ-, API-)
- ▸Deterministic readiness and quality scoring
- ▸Context density optimization for LLM prompt caching
Best for
Structuring product requirement documents for AI-assisted development, Maintaining long-term project memory and preventing AI context drift, Enforcing gated product development lifecycles from ideation to release, Tracing source code back to verified design specifications and business rules
Works with
Claude Code
Evoa Score breakdown= Σ (score × weight)
81Task usefulness20%88 → +17.6
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%100 → +15.0
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%47 → +5.6
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%100 → +15.0
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%58 → +4.6
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%25 → +1.3
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 total81.1 / 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 entirely within local repository files using standard file manipulation tools without requiring external network connections or API keys.
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.