agentleFS
Sign inStart free
dracocephalumdracocephalum/dc-agentics/.claude/skills/optimize/SKILL.md

optimize

Skill0 starsChanged 35 days agoApache-2.0View on GitHub

Measure what this repository's documents cost an agent to read and, only on request, reduce it - compaction with no rule lost, or removal of what a named model does unprompted, logged so it can be restored. Measures by default; changes nothing unless asked.

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

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 73 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the first that exists and follow it as written.

    line 18

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

A cost pass over the documents agents read. Not a consistency check - that is /scrub, which asks whether the documents are true; this asks what they cost. The two never run as one.

Find the standard

  1. agentics/rules/optimize.md - an initialized repository
  2. repo/optimize.md - the dc-agentics toolkit, which adds its own adjustments on top of repo/payload/agentics/rules/optimize.md

Read the first that exists and follow it as written.

Operation

$ARGUMENTS names it. With none, or with anything that does not name one exactly, the operation is measure.

  • measure - report weights and when each is paid, then say which of the other two the numbers justify. Changes nothing.
  • compact - remove verifiable redundancy only, with the before-and-after rule lists the document requires. One reviewable change.
  • defaults <model> - only with the model named, and only under every guard in the document. "Optimize" or "compact" never means this.

Report

Measure: the table by load group, with totals and the arithmetic of what a pass would cost and save. Compact and defaults: what was removed, where each rule now lives, and for defaults that the removals are asserted, not verified.

Download now (ZIP)

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