Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

substack-aeo-geo-optimizer

Étoiles83

Forks20

Mis à jour1 mai 2026 à 16:00

Optimizes any Substack content for AEO (Answer Engine Optimization) and GEO (Generative Engine Optimization) — making it citable by ChatGPT, Perplexity, Claude, Gemini, and Google AI Overviews. Use this skill whenever the user provides a Substack URL or pastes Substack post content and wants to increase AI visibility, get cited by AI search engines, optimize for generative search, or asks things like "optimize this for AI search", "make this citable by ChatGPT or Perplexity", "GEO optimize this post", "AEO this article", "how do I get AI to cite my newsletter", "optimize for AI overviews", "make this show up in AI answers". Always trigger this skill when the goal is to make a Substack post more visible inside AI-generated answers, not just Google rankings. This is separate from SEO metadata optimization.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

aiskilloftheweek

aiskilloftheweek/claude-ai-skill-of-the-week

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Analystes en études de marché et spécialistes en marketingProfessions des affaires et des opérations financières·SOC 13-1161

SKILL.md

readonly

Plus depuis ce dépôt

même dépôt

mock-interview-simulator

aiskilloftheweek/claude-ai-skill-of-the-week

Activates a rigorous, role-specific mock interview simulation that adapts to your target job, company, and experience level. Use this skill every time the user wants to practice for a job interview, simulate a hiring conversation, stress-test their answers, or get feedback on how they present themselves. Trigger on phrases like "prepare me for an interview", "run a mock interview", "let's practice for my interview", "simulate a hiring manager", "ask me interview questions", "help me prep for [company/role]", "I have an interview coming up", or any mention of interview anxiety, preparation, or a specific role the user is applying for. Also trigger when the user pastes a job description and asks what to expect. Do NOT use for general career advice or resume reviews — use a dedicated skill for those.

2026-06-0583

humanaizer

aiskilloftheweek/claude-ai-skill-of-the-week

Rewrites AI-generated text to sound like it was written by a real human being. Use this skill every time the user provides a text and asks to humanize it, remove AI tells, make it sound more natural, less robotic, or more authentic. Trigger on phrases like "humanize this", "make this sound human", "remove AI writing patterns", "this sounds too AI", "rewrite this in my voice", "de-AI this", "make this less robotic", or whenever the user pastes text and asks for it to sound more like a real person wrote it. If the user also provides a sample of their own writing, use it for voice calibration before rewriting.

2026-05-1683

cold-outreach-personalizer

aiskilloftheweek/claude-ai-skill-of-the-week

Generates hyper-personalized cold outreach messages (email, LinkedIn DM, connection request) from raw prospect research. Use this skill every time the user wants to write a personalized cold email, LinkedIn message, or outbound sequence for a specific prospect. Trigger on phrases like "write a cold email to", "outreach for this prospect", "LinkedIn message for", "cold email for", "personalize this outreach", "write a sequence for", or whenever the user pastes prospect information and asks for a message. Always trigger this skill when the goal is to write outreach that references specific, real signals about the prospect — not a generic template.

2026-05-1683

ai-standup

aiskilloftheweek/claude-ai-skill-of-the-week

Facilitates a structured daily standup with a solopreneur or founder, conducting a voice-first step-by-step conversation to align goals, identify blockers, and maximize daily productivity. Use this skill whenever the user mentions "standup", "daily standup", "today's standup", "let's start the standup", "let's do the standup", or uploads a Trello screenshot, a task list, or any document representing the day's activities. Also trigger this skill if the user simply says "let's start" or "I'm ready" after uploading an image with tasks.

2026-05-1583

honest-thinking-partner

aiskilloftheweek/claude-ai-skill-of-the-week

Activates a brutally honest thinking partner mode that sharpens reasoning, surfaces blind spots, dismantles flawed logic, and forces concrete action planning. Use this skill every time the user wants honest feedback on a plan, decision, or idea — especially when they seem to be rationalizing, avoiding something, or stuck. Also trigger when the user says things like "be honest with me", "tell me what you really think", "am I thinking about this wrong", "what am I missing", "stress-test this", "play devil's advocate", "challenge my thinking", "I need brutal feedback", or pastes a plan, decision, or idea asking for feedback. Trigger even when the request is casual — if the user shares a plan and seems to want validation, this skill is what they actually need. Do NOT use for pure information requests with no decision or reasoning component.

2026-05-0883

sop-writer

aiskilloftheweek/claude-ai-skill-of-the-week

Transforms any process description — however rough, incomplete, or disorganized — into a clear, delegatable Standard Operating Procedure (SOP). Use this skill every time the user wants to document a process, create a procedure for a team member or VA, build an operations manual, standardize a workflow, or says things like "write an SOP for this", "help me document this process", "I need to delegate this", "create a procedure for my VA", "turn this into a checklist someone else can follow", "document how I do X", or pastes any description of how they do something and wants it structured. Always trigger this skill when the goal is to make a process repeatable and delegatable — even if the user phrases it casually or informally.

2026-04-2383

name

substack-aeo-geo-optimizer

description

Substack AEO/GEO Optimizer

Transforms a Substack post (URL or pasted text) into content that AI engines (ChatGPT, Perplexity, Claude, Gemini, Google AI Overviews) are structurally likely to cite in their answers.

Built on the CITED framework from Passionfruit's AEO methodology and Princeton KDD 2024 GEO research showing 30-40% citation lift from structured optimization.

Core insight: why most Substack content never gets cited by AI

AI engines don't cite content at random. They cite content that:

Answers a specific question directly and immediately (in the first 40-60 words)
Contains verifiable facts with named sources (not vague claims)
Uses structured, extractable formats (FAQ, lists, definition blocks)
Signals authority through author credentials and entity clarity
Covers the topic comprehensively enough to be the best available answer

Most Substack posts are written for human readers who tolerate narrative buildup. AI engines are pattern-matching for extraction — they need the answer upfront, the evidence inline, and the structure explicit.

Step 1 — Read and classify the content

If a URL is provided, fetch and read the full post content. If text is pasted, read it directly.

Classify the post into one of these query types (this determines optimization priority):

Query type	Signal	Primary AI citation format
Definitional	"What is X", "X explained"	Definition block (40-60 words), then depth
How-to / Process	"How to X", numbered steps	Numbered list with clear step verbs
Comparison	"X vs Y", "best X for Y"	Comparison table, named criteria
Opinion / Contrarian	"Why X is wrong", "The truth about X"	Named expert quotes, cited data
List / Roundup	"Best X", "Top Y tools"	Structured list with consistent criteria
Case study / Story	"How I did X", "My results with Y"	Result-first opening, metrics inline

Step 2 — Run the CITED audit

Score the existing post on each of the 5 CITED dimensions. Mark each as ✅ Present / ⚠️ Weak / ❌ Missing.

C — Context clarity

Does the post make clear who it's for and what specific question it answers?

✅ Present: clear audience, specific question answered in title/intro
⚠️ Weak: topic is clear but audience or query angle is vague
❌ Missing: post reads as general exploration with no specific answerable question

I — Intent match

Does the content structure match the intent of someone asking this question to an AI?

✅ Present: informational → direct answer; comparison → table; how-to → steps
⚠️ Weak: intent is right but format doesn't match (e.g., steps buried in paragraphs)
❌ Missing: content doesn't answer the query an AI user would actually ask

T — Truth signals

Does the post contain verifiable, citable evidence? Count: named statistics with source, expert quotes with attribution, specific data points.

✅ Present: at least 1 cited stat or data point every 150-200 words
⚠️ Weak: some stats present but no sources named, or fewer than 1 per 300 words
❌ Missing: all claims are opinion-based, no named sources

E — Extraction format

Is the content structurally easy for an AI to lift and cite?

✅ Present: direct-answer intro in 40-60 words, FAQ section, or structured list
⚠️ Weak: good content but buried in narrative without extractable structure
❌ Missing: wall of text, no headers, no extractable blocks

D — Differentiation

Does the post contain at least one thing no other source says in this way? Original framework, proprietary data, personal result, counter-intuitive claim.

✅ Present: clear unique angle, named framework, or original data
⚠️ Weak: good writing but no unique insight AI couldn't find elsewhere
❌ Missing: standard take on a standard topic

Step 3 — Produce the AEO/GEO optimization report

Output a structured report with these sections:

Section 1: CITED Audit Score

C — Context clarity:    [✅/⚠️/❌] [1-line explanation]
I — Intent match:       [✅/⚠️/❌] [1-line explanation]
T — Truth signals:      [✅/⚠️/❌] [1-line explanation]
E — Extraction format:  [✅/⚠️/❌] [1-line explanation]
D — Differentiation:    [✅/⚠️/❌] [1-line explanation]

AI Citation Readiness: [LOW / MEDIUM / HIGH]

Section 2: Top 3 AI queries this post could answer

List the 3 most likely questions a user would ask ChatGPT or Perplexity that this post should show up in — but probably doesn't yet.

Format:

1. "[Exact query a user would type]"
   → Currently blocked by: [what's missing]

2. "[Exact query a user would type]"
   → Currently blocked by: [what's missing]

3. "[Exact query a user would type]"
   → Currently blocked by: [what's missing]

Section 3: Rewritten opening (the AEO intro block)

The single highest-impact fix. Rewrite the post's opening paragraph as an AEO-optimized direct-answer intro of 40-60 words.

Rules for this block:

Answers the primary query directly in sentence 1
Includes the most searchable term naturally
Contains at least 1 verifiable claim (or flags [ADD STAT: topic] if none available)
Does NOT start with a question, anecdote, or emotional hook
Reads as the answer an AI would lift verbatim

Format:

ORIGINAL OPENING:
[first 50-80 words of original post]

AEO-OPTIMIZED OPENING (40-60 words):
[rewritten version]

Why this works: [1-line explanation of the structural change]

Section 4: FAQ block for AI citation

Generate 3-5 FAQ entries the post should include to capture question-based queries. These are the questions people ask AI engines that this post answers (or should answer).

Format:

**Q: [Natural language question — how a user would actually ask an AI]**
A: [Direct answer in 2-4 sentences. Specific, not vague. Citable.]

**Q: [Question]**
A: [Answer]

Rules:

Questions must be in natural spoken language, not keyword strings
Answers must be self-contained (readable without the full post context)
Each answer should be 40-100 words — long enough to be useful, short enough to extract

Section 5: Truth signal gaps

List the specific claims in the post that currently lack a named source, and suggest what type of source would make them citable.

Format:

CLAIM: "[quote the unsourced claim]"
→ Source needed: [e.g., "Substack 2024 growth data", "email open rate benchmark study", "your own newsletter analytics"]
→ Why it matters: [why an AI would hesitate to cite this without evidence]

If the post has no unsourced claims, say so explicitly — that's a strength.

Section 6: Structural fixes checklist

Quick wins the creator can implement in 15 minutes:

□ Add direct-answer intro (see Section 3 above)
□ Add FAQ block (see Section 4 above)
□ [List any missing headers that would help AI parse sections]
□ [Flag any specific stat that needs a source added]
□ [Note if post needs a comparison table]
□ [Note if URL slug should include primary keyword]
□ [Note if post's first 150 words bury the main point]

Only include fixes that apply to this specific post. Skip items that are already done.

Section 7: Platform-specific citation notes

Brief note on which AI engine this post is most likely to get cited by, and why:

Most likely platform: [ChatGPT / Perplexity / Google AI Overviews / Claude]
Reason: [1-2 sentences on why this content fits that platform's citation pattern]

Hardest platform to crack: [platform]
What's missing: [specific gap for that platform]

Platform citation patterns (reference only — don't show this to user):

Perplexity: favors recent, structured, evidence-rich content with clear citations. Crawls continuously. Most responsive to fixes.
ChatGPT: favors encyclopedic, comprehensive content. Cites Wikipedia 47.9% of the time for factual queries. Prefers well-established sources.
Google AI Overviews: pulls from pages already ranking in top 20 organic results. SEO foundation matters here.
Claude: favors factual accuracy, clear structure, and content that addresses trade-offs honestly.

Step 4 — Optional: Full rewrite mode

If the user explicitly asks for a full rewrite (not just the report), apply all Section 3-5 fixes to produce a complete AEO-optimized version of the post.

Rules for full rewrite:

Preserve the author's voice and unique insights — do not genericize
Keep all original ideas, frameworks, and examples
Only change structure and evidence density, not the substance
Flag every added element: [AEO: direct answer], [AEO: stat added], [AEO: FAQ]
Do not invent statistics or sources — use [ADD STAT: topic] as placeholders

Calibration notes

What this skill does NOT do:

Generate llms.txt files (requires full site inventory, not just one post)
Audit technical crawler access (requires server access)
Track actual citation performance (requires external monitoring tools)
Replace keyword research for Google SEO (use substack-seo-metadata-generator for that)

What makes a post uncitable by design (flag these):

Pure personal diary / emotional essay with no searchable question
Content that requires knowing the author's personal context to make sense
Posts that are deliberately vague or paywall-teased without a complete free version
Content in a category where no AI platform cites external sources (e.g., fiction)

If the post falls into one of these categories, say so directly and explain why AEO optimization won't help, rather than forcing a framework that doesn't fit.

Output language

Always match the language of the input content. If the Substack post is in Italian, the entire optimization report is in Italian. If in English, in English. Do not mix languages in the output.