AGENT SKILL

benchmark-optimization-loop

Convert 'make it faster' requests into a bounded measured optimization loop — baseline first, generate one-hypothesis variants, benchmark each against a correctness gate, and promote the fastest safe variant with reproducible commands. Use when asked to speed something up, try many variants, run recursive optimization, benchmark latency/throughput/cost, or pick the best implementation by repeated measured tests.

License 许可
MIT
最近更新
2026-11-11
Stars
★ 3
Forks
0

01 前言 Front Matter

name
benchmark-optimization-loop
tools
Read, Write, Edit, Bash, Grep, Glob
license
MIT
metadata
{ "origin": "ECC" }
description
Convert 'make it faster' requests into a bounded measured optimization loop — baseline first, generate one-hypothesis variants, benchmark each against a correctness gate, and promote the fastest safe variant with reproducible commands. Use when asked to speed something up, try many variants, run recursive optimization, benchmark latency/throughput/cost, or pick 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

mdnaimul22
mdnaimul22/human-skills

higgsfield-websites

Build, edit, and deploy full-stack websites, apps and games via the Higgsfield CLI (`higgsfield website …`). Each is a React 19 + TanStack Start SSR app in one Cloudflare Worker (D1/R2/KV/DO/Containers). THREE product types, picked via `--type` on create: `website` (standalone, no Higgsfield integration — references/website-flow.md), `app` (Sign in with Higgsfield + fnf SDK, Quanta — references/app-flow.md), `game` (realtime multiplayer rooms — references/game-flow.md). Routes to the right flow; each carries its own rules and deploy/publish gates. Use when: "build me a website", "make a landing page", "create a web app", "build a SaaS dashboard / portfolio", "make me a game", "deploy this site", "publish". Also owns GAME ART: "make a spritesheet", "tileable texture", "animate a 3D character", game music/SFX — see the game-* references. NOT for: single image/video/audio generation (higgsfield-generate), product photos (higgsfield-product-photoshoot), marketplace cards (higgsfield-marketplace-cards).

★ 3
mdnaimul22
mdnaimul22/human-skills

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

内容创作者写作与文案Skill与智能体开发
★ 3
mdnaimul22
mdnaimul22/human-skills

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

内容创作者开发工程师写作与文案
★ 3
mdnaimul22
mdnaimul22/human-skills

verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

★ 3
mdnaimul22
mdnaimul22/human-skills

using-superpowers

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Skill与智能体开发
★ 3
mdnaimul22
mdnaimul22/human-skills

using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

★ 3