---

name: perf-ops description: "Performance profiling and optimization orchestrator - diagnoses symptoms, dispatches profiling to language experts, manages before/after comparisons. Triggers on: performance, profiling, flamegraph, pprof, py-spy, clinic.js, memray, heaptrack, bundle size, webpack analyzer, load testing, k6, artillery, vegeta, locust, benchmark, hyperfine, criterion, slow query, EXPLAIN ANALYZE, N+1, caching, optimization, latency, throughput, p99, memory leak, CPU spike, bottleneck." license: MIT allowed-tools: "Read Edit Write Bash Glob Grep Agent TaskCreate TaskUpdate" metadata: author: claude-mods related-skills: debug-ops, monitoring-ops, testing-ops, code-stats, postgres-ops

Performance Operations

Orchestrator for cross-language performance profiling and optimization. Classifies symptoms inline, dispatches profiling to language expert agents (background), and manages optimization with confirmation.

Architecture

User describes performance issue or requests profiling
    |
    +---> T1: Diagnose (inline, fast)
    |       +---> Classify symptom (decision tree)
    |       +---> Detect language/runtime from project
    |       +---> Check installed profiling tools
    |       +---> Determine production vs development
    |       +---> Gather system baseline (CPU/mem/disk)
    |       +---> Present: diagnosis + recommended profiling approach
    |
    +---> T2: Profile (dispatch to language expert, background)
    |       +---> Select expert agent from routing table
    |       +---> Build perf-focused dispatch prompt
    |       +---> Expert runs profiler, collects data, interprets results
    |       |       +---> Fallback: general-purpose with tool commands inlined
    |       +---> Returns: findings + bottleneck identification + suggestions
    |       |
    |       +---> [Optional parallel dispatch]:
    |             +---> CPU profiling agent  ---+
    |             +---> Memory profiling agent --+--> Consolidate findings
    |             +---> Baseline benchmark ------+
    |
    +---> T3: Optimize (dispatch to expert, foreground + confirm)
            +---> Expert proposes specific code changes
            +---> Preflight: what changes, expected impact, risks
            +---> User confirms
            +---> Apply changes
            +---> Re-benchmark for before/after delta

Safety Tiers

T1: Diagnose - Run Inline

No agent needed. Execute directly via Bash for instant results.

| Operation | Command / Method | |-----------|-----------------| | Detect Python profilers | which py-spy && which memray && which scalene | | Detect Go profilers | which go && go tool pprof -h 2>/dev/null | | Detect Rust profilers | which cargo-flamegraph && which samply | | Detect Node profilers | which clinic && which 0x | | Detect benchmarking tools | which hyperfine && which k6 && which vegeta | | System CPU baseline | top -bn1 -o %CPU \| head -20 (Linux) or wmic cpu get loadpercentage (Win) | | System memory baseline | free -h (Linux) or wmic OS get FreePhysicalMemory (Win) | | Disk I/O check | iostat -x 1 3 (Linux) | | Identify language | Check for package.json, go.mod, Cargo.toml, pyproject.toml, requirements.txt | | Production vs dev | Ask user or detect from environment (NODE_ENV, FLASK_ENV, etc.) | | Read existing profiles | Parse .prof, .svg, .bin files in project |

Production safety rule: In production environments, only recommend sampling profilers (py-spy, pprof HTTP endpoint, perf). Never suggest attaching debuggers, tracing profilers, or tools that require process restart.

T2: Profile - Dispatch to Expert Agent

Gather context from T1 diagnosis, then dispatch to the appropriate language expert.

Language Expert Routing:

| Detected Language | Expert Agent | Key Profiling Tools | |-------------------|-------------|---------------------| | Python (.py, pyproject.toml, requirements.txt) | python-expert | py-spy, memray, scalene, tracemalloc | | Go (go.mod, .go files) | go-expert | pprof (CPU/heap/goroutine/mutex), benchstat | | Rust (Cargo.toml, .rs files) | rust-expert | cargo-flamegraph, samply, DHAT, criterion | | TypeScript/JavaScript (backend, package.json + server) | javascript-expert | clinic flame/doctor/bubbleprof, 0x | | TypeScript/JavaScript (frontend, bundle issues) | typescript-expert | webpack-bundle-analyzer, Lighthouse, source-map-explorer | | SQL / PostgreSQL | postgres-expert | EXPLAIN ANALYZE, pg_stat_statements, pgbench | | General / unknown / CLI benchmarking | general-purpose | hyperfine, perf, strace |

Dispatch template (T2):

You are handling a performance profiling task dispatched by the perf-ops orchestrator.

## Diagnosis (from T1)
- Symptom: {classified symptom from decision tree}
- Language/Runtime: {detected language}
- Environment: {production | development}
- Installed tools: {list from tool detection}
- System baseline: {CPU/memory/disk metrics}

## Profiling Task
{spec