ワンクリックで
skill-codebase-recon
Git forensics analyst for identifying hotspots, logic churn, and knowledge gaps via commit history.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Git forensics analyst for identifying hotspots, logic churn, and knowledge gaps via commit history.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Professional bootstrapper for Vercel-style Agentic Repositories using compressed AGENTS.md manifests.
Persistent SQLite-based cognitive layer for cross-session interaction logging and insight distillation.
Design lead for C4 structural documentation, Mermaid.js diagrams, and Architecture Decision Records (ADRs).
Specialist in core AWS infrastructure: EC2 compute, IAM identity, VPC networking, and RDS/Aurora databases.
5-phase migration engine for transitioning workloads from Google Cloud Platform to AWS architecture.
AI/ML infrastructure expert for SageMaker fine-tuning, HyperPod cluster management, and dataset evaluation.
SOC 職業分類に基づく
| name | skill-codebase-recon |
| description | Git forensics analyst for identifying hotspots, logic churn, and knowledge gaps via commit history. |
Before diving into the source code, use these Git forensics to identify hotspots, risks, and institutional knowledge gaps. These commands help build a mental map of "danger zones" and key contributors.
Goal: Find the 20 most-frequently changed files in the last year. High churn indicates active development or a "God Object."
git log --format=format: --name-only --since="1 year ago" | sort | uniq -c | sort -nr | head -20
Interpretation: If the top files are also technical debt items, they are major drivers of "codebase drag."
Goal: Identify who built the system and check if they are still active.
git shortlog -sn --no-mergesgit shortlog -sn --no-merges --since="6 months ago"
Interpretation: If one person has >60% of commits, the Bus Factor is high. If top contributors are absent from the 6-month list, knowledge has left the building.Goal: Find where "fixes" are concentrated. Files constantly being fixed are likely fragile.
git log --format=format: --name-only --grep="fix\|bug\|broken" | sort | uniq -c | sort -nr | head -20
Interpretation: Cross-reference this with the Churn list. A file that is both high-churn and high-bug is a primary stability risk.
Goal: Determine if the project is accelerating, stable, or dying by looking at yearly commit volume.
git log --date=format:"%Y-%m" --format="%ad" | sort | uniq -c
Interpretation: A steady decline may indicate maintenance mode. Sudden spikes followed by silence may suggest high-pressure firefighting.
Goal: Find how often the team has to revert or hotfix.
git log --oneline --since="1 year ago" --grep="revert\|hotfix\|emergency\|rollback"
Interpretation: A long list suggests skipping QA or immense pressure to deploy, leading to a "patch-on-a-patch" culture.