CF SEO & GEO (Generative Engine Optimization) Playbook
Rank on Google AND get cited by ChatGPT, Perplexity, and Claude. A dual SEO + GEO strategy built from 30+ Product Hunt #1 launches and 10k+ GitHub stars campaigns — so your product shows up whether users search or ask AI. This playbook covers: GEO fundamentals including IndexNow instant push and Schema markup (FAQPage, Article, Organization), the E-E-A-T writing voice system with founder authenticity signals, SEO article templates using the QAE pattern (Question → Answer → Evidence), keyword funnel strategy (TOFU/MOFU/BOFU), content marketing for startups and developers, AI SEO tactics for Perplexity and ChatGPT search, perplexity SEO optimization, seo article template creation, seo writing best practices, seo checklist and seo audit workflows, seo tools for developers, seo for startups, and multi-platform distribution via Dev.to and Hashnode with canonical URLs. Unique content: The "founder voice" writing system that injects authenticity signals into AI-generated content — the key to being cited by AI engines like Perplexity and ChatGPT. Includes actionable seo checklist, seo article template prompts, seo writing prompts, schema markup generators, GEO audit checklist, and real case studies from GitHub stars growth and Product Hunt launches. Keywords: seo, geo, generative engine optimization, ai seo, perplexity seo, chatgpt seo, perplexity seo guide, e-e-a-t, indexnow, schema markup, seo article template, seo writing, content marketing, content marketing for startups, search engine optimization, seo strategy, seo checklist, seo audit, seo tools, seo tools for developers, seo for startups, seo for developers, perplexity optimization, bing copilot seo, chatgpt search optimization, seo playbook, seo guide, seo tutorial
As a process F 28/100 · Will not run — References files that are not bundled: link
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1749 chars, limit 1024 - warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: link - note
description-budgetdescription takes 1749 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 28/100
- 0Tools and files. 1 referenced file(s) missing: link
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 12 mutating operations with no state check
- 40Consistency. Frontmatter name (SEO & GEO (Generative Engine Optimization) Playbook) differs from the folder (seo-geo-playbook)
- 100Steps. 54 steps
- 100Execution cost. Instruction body is 2834 tokens
- low 11 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1748: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 34 headings
- +3Step-by-step instructions: 54 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 30.