agentleFS
Sign inStart free
HenryQWHenryQW/skills/skill-optimizer/SKILL.md

skill-optimizer

Skill1 starsChanged 4 months agoApache-2.0View on GitHub

Optimize existing skills by finding evidence-backed failures and waste, calibrating triggers, instructions, resources, and safety, applying the smallest root-cause change, and verifying representative behavior. Use when asked to improve, streamline, harden, reduce turn, tool, or context waste in, or optimize an existing skill; do not use for creating a brand-new skill.

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use octocat, linting-neostandard-eslint9 and 9 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.
  • mcollinaSkill

    octocat

    Use this skill whenever the prompt contains any `github.com` URL, even if the user only pastes a link and gives no GitHub-specific keywords. Handles git and GitHub operations using the gh CLI. Triggers include any GitHub link to an issue, pull request, commit, compare page, Actions run, release, discussion, or repository. Covers creating and reviewing PRs, repository security advisories (GHSA), their comments, and fix PRs in their temporary private forks, private vulnerability report discussions, watching CI checks, interactive rebasing, branch cleanup, submodule management, and repository archaeology with git log/blame/bisect.

    Also in 3 projects that use this

  • mcollinaSkill

    linting-neostandard-eslint9

    Configures ESLint v9 flat config and neostandard for JavaScript and TypeScript projects, including migrating from legacy `.eslintrc*` files or the `standard` package. Use when you need to set up or fix linting with `eslint.config.js` or `eslint.config.mjs`, troubleshoot lint errors, configure neostandard rules, migrate from `.eslintrc` to flat config, or integrate linting into CI pipelines and pre-commit hooks.

    Also in 3 projects that use this

  • VercelSkill

    oauth

    Configure OAuth providers (Google, Apple, Microsoft, Facebook, GitHub, etc.) to work with portless local dev URLs. Use when setting up OAuth redirect URIs, fixing "redirect_uri_mismatch" or "invalid redirect" errors, configuring sign-in providers for local development, or when a provider rejects .localhost subdomains. Triggers include "OAuth not working with portless", "redirect URI mismatch", "Google/Apple/Microsoft sign-in fails locally", "configure OAuth for local dev", or any task involving OAuth callback URLs with portless domains.

    Also in 3 projects that use this

  • AnthropicSkill

    documentation

    Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or when the user needs help with any form of technical writing — API docs, architecture docs, or operational runbooks.

    Also in 3 projects that use this

  • MicrosoftSkill

    init

    Also in 3 projects that use this

  • OpenAISkill

    systematic-debugging

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    Also in 3 projects that use this

  • +4 more from mcollina

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer supplied prompts, traces, outputs, failures, or feedback.

    line 16
  2. Distinctive:

    Read repository instructions, target metadata and entrypoint, then only referenced code, resources, tests, or callers needed to prove …

    line 21
  3. Very specific:

    Verify changed behavior with the smallest structural and representative positive/negative/regression checks, compare to baseline, and …

    line 37

“Common” is measured: kept by at least 6 in 10 of the 21 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

skill-optimizer

Improve an existing skill from observed behavior. If none exists, use $skill-creator.

Inputs

target_skill_path is required unless unambiguous. optimization_goal defaults to evidenced waste and correctness problems while preserving outcomes and public contracts. mode is read-only diagnose or explicitly authorized apply. Prefer supplied prompts, traces, outputs, failures, or feedback; derive only a small representative set when absent.

Workflow

  1. Read repository instructions, target metadata and entrypoint, then only referenced code, resources, tests, or callers needed to prove behavior.
  2. Establish positive, non-trigger, and regression cases. Baseline relevant outcomes, turns, tool calls, repeated context, noise, recovery, and safety; use concrete static evidence when execution is unsafe or unavailable.
  3. Rank only evidenced selection, instruction, context, execution, recovery, authorization, or verification problems by impact, confidence, and fix size.
  4. In diagnose, report evidence, impact, and the smallest credible fix without mutation. In apply, delete duplication first, then patch the smallest causal owner. Prefer existing mechanisms; add a helper only for deterministic reliability or a repeated fragile sequence. Do not add compatibility layers unless a public contract requires them.
  5. Preview only to reduce material uncertainty. Explicit edits authorize scoped local changes, not irreversible, externally visible, destructive, or expanded actions. Dry-run and apply must be exclusive, and helpers must not bypass wrapper safety.
  6. Verify changed behavior with the smallest structural and representative positive/negative/regression checks, compare to baseline, and update required repository inventory or install documentation.

Report only what improved, passed, and remains.

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