メニュー
API cost & performance scanner — identify expensive operations and optimization opportunities
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。
SOC 職業分類に基づく
| name | optimize |
| description | API cost & performance scanner — identify expensive operations and optimization opportunities |
| argument-hint | Optional focus area (e.g., "ai", "caching", "queries", "latency") |
You are scanning this project's API and infrastructure for cost and performance optimization opportunities.
!sh .adlc/partials/ethos-include.sh 2>/dev/null || sh ~/.claude/skills/partials/ethos-include.sh
cat .adlc/context/architecture.md 2>/dev/null || echo "No architecture context found"cat .adlc/context/project-overview.md 2>/dev/null || echo "No project overview found"Focus: $ARGUMENTS
Before proceeding, verify that .adlc/context/architecture.md and .adlc/context/project-overview.md exist. If any of these files are missing, stop and tell the user: "The .adlc/ structure hasn't been initialized. Run /init first to set up the project context."
.adlc/context/architecture.md for current caching and optimization patternsLaunch 3 formal scanner agents in parallel using the Agent tool. Each agent is defined in ~/.claude/agents/ with its full scanning checklist and model selection (sonnet for deep analysis).
Each agent returns structured findings with estimated impact, effort, and risk.
| Service | Est. Monthly Usage | Est. Monthly Cost | Top Optimization |
|---|---|---|---|
| Claude Sonnet | X calls | $X | ... |
| Claude Haiku | X calls | $X | ... |
| Gemini Flash | X calls | $X | ... |
| SerpAPI | X calls | $X | ... |
| Firestore | X reads/writes | $X | ... |
| GCS | X operations | $X | ... |
Rank endpoints by estimated latency, highlighting:
For each opportunity:
/spec)Parallel pipeline orchestrator — launch multiple /proceed sessions concurrently across REQs, monitor progress, and report status. Use when the user says "sprint", "run these REQs in parallel", "proceed with all approved REQs", "launch a sprint", or wants to advance multiple requirements simultaneously.
Codebase health audit — identify technical debt, quality issues, and improvement opportunities
End-to-end ADLC pipeline that takes a requirement from spec through to deployed. Takes a REQ number as argument and runs validate → fix → architect → fix → implement → verify (reflect + review) → create PR → wrapup (merge, deploy, knowledge capture). Use when the user says "proceed", "proceed with REQ-xxx", "run the pipeline", "take REQ-xxx to completion", "implement REQ-xxx end to end", or wants to advance a drafted requirement all the way through to deployment in one shot.
Write requirement specs from feature requests
Close out a completed feature — update ADLC artifacts, log knowledge, and summarize
Bootstrap .adlc/ structure in a new repo or subdirectory