agentleFS
Sign inStart free
daintreehqdaintreehq/daintree/.agents/skills/optimize/SKILL.md

optimize

Skill87 starsChanged 8 days agoLicence not identifiedView on GitHub

USE ONLY WHEN A HUMAN EXPLICITLY INVOKES IT — never auto-select or run this proactively: not after writing code that looks slow, not because a benchmark moved, not as a step inside another workflow. Once a human starts it with /optimize (Claude Code) or $optimize (Codex) it runs FULLY AUTONOMOUSLY to the end, never asking a question. It takes one freeform instruction and resolves it to ONE benchmark, or a small cluster of benchmarks that measure the same thing, sharing one subject and one likely fix — never a grab-bag of unrelated targets. It writes its decision down before measuring (metric, predicate, guards, threshold, protocol, apparatus hash), establishes a baseline, then hypothesises, changes code, re-measures against a champion arm re-measured in the same session, and keeps or reverts on the evidence. It re-measures every benchmark in the cluster against the branch point at the end, because one shared fix moves all of them. Local machine first to a claim, then the deterministic count/size/ratio legs on other operating systems via the perf-ab workflow; durations are never claimed off a shared CI runner. The full unit suite must pass before it opens a pull request. Ends with a before/after table per benchmark and machine and a pull request, or — when nothing moved the number, or the only things that moved it would have seriously degraded the system — an honest report that nothing could be optimised here and no pull request at all. Refuses a benchmark with no correctness predicate, because one that has none rewards breaking the feature.

  • Deletes or force-pushes
  • Commits and pushes

76 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use arrange, teach-impeccable and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • HK-hubSkill

    arrange

    Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.

    Also in 14 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 17 projects that use this

  • zwy123zwySkill

    normalize

    将用户随意输入的提示词规范化为结构清晰、便于大模型执行的标准化提示词。适用于需要整理、统一提示词格式时调用。

    Also in 19 projects that use this

  • open-coder-aiSkill

    policy-init

    Create conformant Chock policy from request. args(request, target_path,

    Also in 3 projects that use this

  • +8 more from HK-hub

The file

Show its rules and text

We split this skill into the rules it gives an agent

19 rules. 0 are common, 13 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 73 edited versions we read keep these.

  • 13

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.

“Common” is measured: kept by at least 6 in 10 of the 73 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free