メニュー
Diagnose a codebase through its git history before reading any code. Surfaces churn hotspots, bus factor risks, bug clusters, velocity trends, and firefighting patterns. Only invoked directly via /navvy — does not auto-trigger.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SOC 職業分類に基づく
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/andrewgleave/skills --skill navvyコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
| name | navvy |
| description | Diagnose a codebase through its git history before reading any code. Surfaces churn hotspots, bus factor risks, bug clusters, velocity trends, and firefighting patterns. Only invoked directly via /navvy — does not auto-trigger. |
Five git commands, run in under a minute, that tell you more about a codebase than an hour of reading code. Commit history is diagnostic data — it reveals team dynamics, risk concentration, and maintenance patterns that the code itself cannot.
Run all five commands, then synthesize the results into a diagnostic report.
Run these in parallel where possible. Adjust --since to match the project's age — use 1 year ago for active projects, extend for slower-moving ones.
git log --format=format: --name-only --since="1 year ago" | sort | uniq -c | sort -nr | head -20
The 20 most-modified files in the past year. High churn on a file that nobody wants to own is the clearest signal of codebase drag — these files have unpredictable blast radius and inflate estimates.
git shortlog -sn --no-merges
Ranks contributors by commit count. Look for bus factor risk: if one person accounts for 60%+ of commits, knowledge is dangerously concentrated. Also check whether core contributors are still active.
git log -i -E --grep="fix|bug|broken" --name-only --format='' | sort | uniq -c | sort -nr | head -20
Files most frequently touched in bug-related commits. Files appearing in both this list and the churn hotspots are highest-risk code — they keep breaking and keep getting patched.
git log --format='%ad' --date=format:'%Y-%m' | sort | uniq -c
Commit counts by month across the full history. A steady rhythm is healthy. Sharp declines suggest departures or loss of momentum. Sporadic spikes suggest batched releases rather than continuous delivery.
git log --oneline --since="1 year ago" | grep -iE 'revert|hotfix|emergency|rollback'
Reverts and hotfixes. Frequent occurrences signal the team doesn't trust its deploy process — a symptom of deeper issues with testing or deployment reliability.
After running all five commands, write a short diagnostic report. Structure it around what the data reveals, not around the commands themselves.
# Codebase Diagnostic: [repo name]
## Key Findings
[2-4 bullet points: the most important things to know before touching this code]
## Churn Hotspots
[Top files, what they are, whether they overlap with bug clusters]
## Team & Ownership
[Bus factor assessment, active vs inactive contributors]
## Health Signals
[Velocity trend interpretation, firefighting frequency]
## Recommendations
[Where to focus attention, what to investigate further]
Keep it concise. The point is orientation, not exhaustive analysis. A reader should finish the report knowing where the bodies are buried and where to tread carefully.
Review code for readability, then simplify it to be easy to follow and understand. Use this skill when the user wants to simplify code, improve readability, clean up for handoff, make code skimmable, reduce complexity, refactor for clarity, strip boilerplate, prepare code for future maintainers, or make a codebase easier to pick up. Trigger liberally — any request touching readability, simplification, cleanup, or "make this easier to understand" should use this skill. Also trigger when the user says things like "review this", "clean this up", "tidy this", "make this simpler", "reduce complexity", "flatten this", "strip the noise", or "I want to understand this code quickly next time I open it".
Challenges requirements, removes unnecessary work, and simplifies design before writing code. Activates when asked to build, implement, automate, add a feature, create a service, migrate, or replace a process. Does not activate for general code writing, bug fixes, or simple edits.
Use when someone asks to write, rewrite, review, or improve text that appears inside a product or interface. Examples: "review the UX copy", "is there a better way to phrase this", "rewrite this error message", "write copy for this screen/flow/page", reviewing button labels, improving CLI output messages, writing onboarding copy, settings descriptions, or confirmation dialogs. Trigger whenever the request involves wording shown to end users inside software — apps, web, CLI, email notifications, modals, tooltips, empty states, or alerts. Also trigger for vague requests like "review the UX" where interface copy review is implied. Do NOT trigger for content marketing, blog posts, app store listings, API docs, brand guides, cover letters, or interview questions — this is a technical writing skill for interface language.