agentleFS
Sign inStart free
cihantopaccihantopac/searvex/skills/optimize/SKILL.md

optimize

Skill4 starsChanged 13 days agoApache-2.0View on GitHub

Single step 6 of the /searvex workflow - Apply safe, framework-aware SEO fixes to the current repository with Searvex - dry-run diff, explicit user approval, automatic verification and rollback. Drafts judgement-based changes (titles, descriptions, alt text) for review.

  • Reads credentials

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

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

  • 0

    Common

    Most of the 73 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    If the user pasted a Searvex repair prompt (generated from the HTML report), follow its steps: re-inspect the source, reject false …

    line 10
  2. Very specific:

    If the output says the site URL or language is unknown, ask the user for them and re-run with --site-url / --lang.

    line 17
  3. Distinctive:

    Read the referenced files and the page's real content.

    line 23
  4. Distinctive:

    Use only facts that exist in the codebase or that the user confirms.

    line 25
  5. Very specific:

    Never modify .env/secret files, never commit or push unless the user asks, and keep changes minimal.

    line 32

“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

Workflow — never skip the approval step. Keep messages short: show what will change and ask; put long diffs in a summary (files and one line each), not in the chat.

If the user pasted a Searvex repair prompt (generated from the HTML report), follow its steps: re-inspect the source, reject false positives, fix root causes once, use the listed optimize --only … command for the automatic part, and report per reference. Record verdicts with node "${CLAUDE_PLUGIN_ROOT}/dist/searvex.mjs" review <runId> <ref> confirmed|rejected|fixed --note "…" so the report shows them next to the original evidence.

  1. Dry run. node "${CLAUDE_PLUGIN_ROOT}/dist/searvex.mjs" optimize ${ARGUMENTS:-.} If the output says the site URL or language is unknown, ask the user for them and re-run with --site-url / --lang. Show the user the automatic fixes and the plan.patch diff (summarise long diffs).
  2. Ask for approval of the automatic fixes. Only after a clear yes, run the same command with --apply --yes. Searvex verifies the result and rolls back automatically if verification fails. Report the change id and the undo command (rollback <changeId> <path>).
  3. Judgement tasks (titles, descriptions, alt text, headings, content, Organization schema):
    • Read the referenced files and the page's real content. Draft concrete changes that follow the project's conventions (framework metadata API, components, i18n files).
    • Use only facts that exist in the codebase or that the user confirms. No keyword stuffing, no invented claims, no misleading structured data.
    • Show the drafts as a diff and apply them with Edit only after the user approves.
  4. Verify. Re-run audit <path> and report before/after for the affected rules in a few lines: fixed, remaining, rejected as false positive, needs manual action. Link the new report.html (its "Changes" tab shows the difference to the previous run).

Never modify .env/secret files, never commit or push unless the user asks, and keep changes minimal.

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