performance（性能）

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

Understand Code First — HARD-GATE: Do NOT write, plan, or fix until you READ existing code. 1. Search 3+ similar patterns (grep/glob) — cite file:line evidence 2. Read existing files in target area — understand structure, base classes, conventions 3. Run python.claude/scripts/code_graph trace <file> --direction both --json when .code-graph/graph.db exists 4. Map dependencies via connections or callers_of — know what depends on your target 5. Write investigation to .ai/workspace/analysis/ for non-trivial tasks (3+ files) 6. Re-read analysis file before implementing — never work from memory alone 7. NEVER invent new patterns when existing ones work — match exactly or document deviation BLOCKED until: - [] Read target files - [] Grep 3+ patterns - [] Graph trace (if graph.db exists) - [] Assumptions verified with evidence

Evidence-Based Reasoning — Speculation is FORBIDDEN. Every claim needs proof. 1. Cite file:line, grep results, or framework docs for EVERY claim 2. Declare confidence: >80% act freely, 60-80% verify first, <60% DO NOT recommend 3. Cross-service validation required for architectural changes 4. "I don't have enough evidence" is valid and expected output BLOCKED until: - [] Evidence file path (file:line) - [] Grep search performed - [] 3+ similar patterns found - [] Confidence level stated Forbidden without proof: "obviously", "I think", "should be", "probably", "this is because" If incomplete → output: "Insufficient evidence. Verified: [...]. Not verified: [...]."

• docs/project-reference/domain-entities-reference.md — Domain entity catalog, relationships, cross-service sync (read when task involves business entities/models) (content auto-injected by hook — check for [Injected:...] header before reading)

Evidence Gate: MANDATORY IMPORTANT MUST ATTENTION — every claim, finding, and recommendation requires file:line proof or traced evidence with confidence percentage (>80% to act, <80% must verify first).

External Memory: For complex or lengthy work (research, analysis, scan, review), write intermediate findings and final results to a report file in plans/reports/ — prevents context loss and serves as deliverable.

Quick Summary

Goal: Analyze and optimize performance bottlenecks in database queries, API endpoints, or frontend rendering.

Workflow:

1. Profile — Identify bottlenecks using profiling data or metrics
2. Analyze — Trace hot paths and measure impact
3. Optimize — Apply targeted optimizations with before/after measurements

Key Rules:

• Analysis Mindset: measure before and after, never optimize blindly
• Evidence-based: every claim needs profiling data or benchmarks
• Focus on highest-impact bottlenecks first

$ARGUMENTS

Analysis Mindset (NON-NEGOTIABLE)

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

• Do NOT assume a bottleneck location — verify with actual code traces and profiling evidence
• Every performance claim must include file:line evidence
• If you cannot prove a bottleneck with a code trace, state "suspected, not confirmed"
• Question assumptions: "Is this really slow?" → trace the actual execution path and query plan
• Challenge completeness: "Are there other bottlenecks?" → check the full request pipeline
• No "should improve performance" without proof — measure before and after

[IMPORTANT] Database Performance Protocol (MANDATORY): 1. Paging Required — ALL list/collection queries MUST ATTENTION use pagination. NEVER load all records into memory. Verify: no unbounded GetAll(), ToList(), or Find() without Skip/Take or cursor-based paging. 2. Index Required — ALL query filter fields, foreign keys, and sort columns MUST ATTENTION have database indexes configured. Verify: entity expressions match index field order, database collections have index management methods, migrations include indexes for WHERE/JOIN/ORDER BY columns.

⚠️ MANDATORY: Confidence & Evidence Gate

MANDATORY IMPORTANT MUST ATTENTION declare Confidence: X% with profiling data + file:line proof for EVERY claim. 95%+ recommend freely | 80-94% with caveats | 60-79% list unknowns | <60% STOP — gather more evidence.

Activate arch-performance-optimization skill and follow its workflow.

CRITICAL: Present findings and optimization plan. Wait for explicit user approval before making changes.

Graph-Assisted Investigation — MANDATORY when .code-graph/graph.db exists. HARD-GATE: MUST ATTENTION run at least ONE graph command on key files before concluding any investigation. Pattern: Grep finds files → trace --direction both reveals full system flow → Grep verifies details | Task | Minimum Graph Action | | --- | --- | | Investigation/Scout | trace --direction both on 2-3 entry files | | Fix/Debug | callers_of on buggy function + tests_for | | Feature/Enhancement | connections on files to be modified | | Code Review | tests_for on changed functions | | Blast Radius | trace --direction downstream | CLI: python.claude/scripts/code_graph {command} --json. Use --node-mode file first (10-30x less noise), then --node-mode function for detail.

Run python.claude/scripts/code_graph query callers_of <function> --json on hot functions to understand call frequency.

Graph Intelligence (RECOMMENDED if graph.db exists)

If .code-graph/graph.db exists, enhance analysis with structural queries:

• Identify hot paths calling bottleneck: python.claude/scripts/code_graph query callers_of <function> --json
• Batch analysis: python.claude/scripts/code_graph batch-query file1 file2 --json

Graph-Trace for Hot Path Analysis

When graph DB is available, use trace to map execution paths for performance analysis:

• python.claude/scripts/code_graph trace <bottleneck-file> --direction both --json — full call chain: what triggers this code + what it triggers downstream
• python.claude/scripts/code_graph trace <bottleneck-file> --direction downstream --json — downstream cascade (N+1 queries, excessive event handlers)
• Cross-service MESSAGE_BUS edges reveal distributed performance bottlenecks

Workflow Recommendation

MANDATORY IMPORTANT MUST ATTENTION — NO EXCEPTIONS: If you are NOT already in a workflow, you MUST ATTENTION use AskUserQuestion to ask the user. Do NOT judge task complexity or decide this is "simple enough to skip" — the user decides whether to use a workflow, not you: 1. Activate quality-audit workflow (Recommended) — performance → sre-review → test 2. Execute /performance directly — run this skill standalone

Next Steps

MANDATORY IMPORTANT MUST ATTENTION — NO EXCEPTIONS after completing this skill, you MUST ATTENTION use AskUserQuestion to present these options. Do NOT skip because the task seems "simple" or "obvious" — the user decides:

• "/sre-review (Recommended)" — Production readiness review after optimization
• "/changelog" — Document performance changes
• "Skip, continue manually" — user decides

Closing Reminders

MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting. MANDATORY IMPORTANT MUST ATTENTION validate decisions with user via AskUserQuestion — never auto-decide. MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality. MANDATORY IMPORTANT MUST ATTENTION READ the following files before starting:

• MANDATORY IMPORTANT MUST ATTENTION search 3+ existing patterns and read code BEFORE any modification. Run graph trace when graph.db exists.
• MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim. Confidence >80% to act, <60% = do NOT recommend.
• MANDATORY IMPORTANT MUST ATTENTION run at least ONE graph command on key files when graph.db exists. Pattern: grep → graph trace → grep verify.