Skip to content
ai101.tools
navigateopenescclose
Claude+372Whisper+228LangChain+168Codex+223NotebookLM+276DALL-E 3+192DeepL+249n8n+208Topaz Video AI+153LlamaIndex+161
Application Performance logo
Skill

Application Performance

Runs profiling through to monitoring as one resumable pass with an explicit target.

0
SaveVisit website ↗

Install

Claude Code: /plugin marketplace add wshobson/agents → /plugin install application-performance@claude-code-workflows
Triggers on

Bir uygulama profillenirken, gecikme ya da işlem hacmi darboğazı aranırken veya optimizasyon sonrası izleme kurulurken.

Author
Seth Hobson
License
MIT

The command asks two questions up front that performance work usually skips: what is being optimised for, latency or throughput or cost, and how deep to go, from quick wins to an enterprise pass. Both are command flags, so the answer is fixed before profiling starts and the results cannot be reinterpreted afterwards to fit whatever improved. State lives in a performance-optimization directory with each phase writing its own output file, and phase checkpoints stop for approval instead of running the whole sequence unattended. The agent mix is what makes it end well: a frontend developer and a performance engineer do the work while an observability engineer ensures it closes with monitoring in place rather than a single profile nobody repeats.

Comments(0)

Sign in to comment

No comments yet — be the first.

Similar skills

Report this comment

Why are you reporting this?