AGENT SKILL

benchmark-optimization-loop

Use when the user asks to make something faster, try many variants, run recursive optimization, benchmark latency/throughput/cost, or choose the best implementation by repeated measured tests.

License 许可
MIT
最近更新
2026-11-14
Stars
★ 0
Forks
1

01 前言 Front Matter

name
benchmark-optimization-loop
tools
Read, Write, Edit, Bash, Grep, Glob
license
MIT
metadata
{ "origin": "ECC" }
description
Use when the user asks to make something faster, try many variants, run recursive optimization, benchmark latency/throughput/cost, or choose the best implementation by repeated measured tests.

03 SKILL.md 正文

Benchmark Optimization Loop

Use this skill to convert "make it 20x faster" or "try 50 recursive optimizations" into a bounded measured loop that can actually improve a system.

Required Baseline

Do not optimize until these exist:

  • the operation being optimized;
  • the correctness gate that must stay green;
  • the metric: wall time, p95 latency, rows/sec, cost/run, memory, error rate;
  • the current baseline;
  • the search budget: max variants, max time, max spend, max data impact.

If the user asks for an unrealistic target, keep the ambition but make the loop bounded and measurable.

Loop

  1. Measure the baseline.
  2. Identify bottlenecks from evidence.
  3. Generate variants that test one hypothesis each.
  4. Run variants with the same input shape.
  5. Reject variants that fail correctness, safety, or reproducibility.
  6. Promote the fastest safe variant.
  7. Codify the winning path in a script, command, test, config, or doc.
  8. Rerun the baseline and winner to confirm the delta.

Variant Table

Track variants like this:

Variant | Hypothesis | Command | Time | Correct? | Notes
baseline | current path | npm run job | 120s | yes | stable
batch-500 | fewer round trips | npm run job -- --batch 500 | 42s | yes | winner
parallel-8 | more workers | npm run job -- --workers 8 | 31s | no | rate limited

Recursive Search

For recursive or hyperparameter work:

  • persist every run to a ledger;
  • compare against the prior accepted winner, not only the previous run;
  • keep a holdout or replay check;
  • stop when improvement is within noise, correctness fails, cost exceeds the budget, or the search starts changing more variables than it can explain.

Use phrases like "best measured safe variant" instead of "global optimum" unless the search space was actually exhaustive.

Promotion Gate

A variant cannot become the new default until:

  • correctness tests pass;
  • the performance delta is repeated or explained;
  • rollback is obvious;
  • the change is encoded in source control or a durable runbook;
  • the final summary includes exact commands and measurements.

04 同仓库更多 Skills

sanjeevafk
sanjeevafk/agent-skills

zarr-python

Chunked N-D arrays for cloud storage (Zarr-Python 3). Compressed arrays, parallel I/O, S3/GCS via fsspec, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.

★ 0
sanjeevafk
sanjeevafk/agent-skills

whiteboard-diagrams

Create accurate, simple, hand-drawn whiteboard diagrams from a user's process, system, architecture, learning workflow, comparison, or causal explanation. Use when the user asks for a scribbly whiteboard visual, educational workflow graphic, hand-drawn explainer, or diagram like the bundled reference; ask one focused clarification question when the subject or relationships are missing, then generate and visually verify the final image.

★ 0
sanjeevafk
sanjeevafk/agent-skills

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

★ 0
sanjeevafk
sanjeevafk/agent-skills

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

★ 0
sanjeevafk
sanjeevafk/agent-skills

verification-loop

A comprehensive verification system for Claude Code sessions.

★ 0
sanjeevafk
sanjeevafk/agent-skills

vercel-deploy

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

★ 0