agentleFS
Sign inStart free
powerczukpowerczuk/seo-machine/skills/optimize/SKILL.md

optimize

Skill0 starsChanged 2 months agoMITView on GitHub

Rewrite existing content to raise its A–G score across six lenses and deliver the optimized version with a before/after scorecard and change log.

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

3 rules. 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/text_metrics.py ...

    line 19
  2. Very specific:

    Run text_metrics.py again and re-score A–G.

    line 44
  3. Distinctive:

    If still below 70/100, say which criteria block it and what the author must supply.

    line 46

“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

/optimize — Content optimization

Target: $ARGUMENTS

Rules and numbers: ${CLAUDE_PLUGIN_ROOT}/skills/seo-fundamentals/SKILL.md (ground-truth rules) and ${CLAUDE_PLUGIN_ROOT}/skills/seo-fundamentals/references/scoring-spec.md. There is one score in this plugin — the A–G score from /score. This skill uses it twice (before/after) and organizes the work between them.

Phase 1 — Baseline

  1. Get the content: read the file, or fetch the URL with python3 ${CLAUDE_PLUGIN_ROOT}/scripts/fetch_page.py "<url>" --json.
  2. Confirm the primary keyword and primary entity (infer and state, or ask once).
  3. Run python3 ${CLAUDE_PLUGIN_ROOT}/scripts/text_metrics.py ... --keyword "<kw>" for the hard numbers.
  4. SERP pre-audit: WebSearch the keyword; note top-10 content types, depth, and the entities they converge on. When the user wants rigor, run /entity-coverage first and reuse its MUST-COVER / OPPORTUNITY / INFORMATION GAIN lists.
  5. Score A–G exactly as /score does (load ${CLAUDE_PLUGIN_ROOT}/skills/score/SKILL.md and its anchors). Present the baseline scorecard and dual verdict.

Phase 2 — Fix plan (six lenses)

Group every issue under one lens, with severity from scoring-spec.md §4 and the criterion it moves:

LensFeedsTypical fixes
Entity & topical signalsG1, G2, A6, B8Primary entity into title/H1/first 50 words as sentence subject; add missing MUST-COVER entities; remove topic drift; one dominant entity per URL; sameAs
Information gainG3, B3, D5Add attributes absent from top 10 — only from real user material (own data, experience, quotes); otherwise [NEEDS REAL DATA: …]
Passage extractabilityG6, A8Answer each H2/H3 in its first 40–60 words; definition-style openings; split rambling paragraphs into claim + fact; tables/lists where the sub-query wants them
Engagement & human signalsB4, B5Hook, APP intro, real anecdotes and first-person stake from the author, contextual CTAs (first within 500 words), visual notes
Structure & coherenceC4, B4, B8One H1; 4–7 H2s; no skipped levels; heading every 300–400 words; consistent terminology; 40–70% prose
Technical hygieneC1–C8, D1–D3, G4Title as click copy, meta description with CTA, slug, internal/external links, alt text, schema matching the body, density ≤3%

Order: Critical → High → Medium → Low. Fix G-lens items first when AI Overviews readiness is below PARTIAL.

Phase 3 — Apply

Rewrite in place, keeping the author's voice and every real fact. Never add statistics, names, quotes, or sources the input did not contain — mark gaps instead. If the text shows AI-writing patterns (uniform paragraphs, filler, em-dash overuse, no first-hand specifics), run the humanizer skill (${CLAUDE_PLUGIN_ROOT}/skills/humanizer/SKILL.md) as a pass rather than scrubbing ad hoc.

Phase 4 — Re-score and deliver

  1. Run text_metrics.py again and re-score A–G.
  2. Deliver: the optimized content; before/after scorecard (A–G + both verdicts); change log (every modification, one line each); updated meta title/description/slug (3 options each); internal/external link suggestions; schema recommendation (or /schema-gen); list of [NEEDS REAL DATA] gaps for the author.
  3. If still below 70/100, say which criteria block it and what the author must supply.

Offer next: /citable-passage for a passage-level pass, /meta-tags for final click copy, /alignment-audit before deploying schema.

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