Facebook Page Hook Extractor
Reverse-engineer the hook from a high-share Facebook Page post, from its URL or pasted text.
How to use it
- Hit Copy the whole skill.
- Claude: ⋯ → Download .md, then Customize → Skills → Add → Upload skill.
ChatGPT: make a Project and paste it into Instructions.
Neither? Paste it at the top of a new chat — it works for that chat. - Describe your job in plain words. The AI follows the skill from there.
npx degit sergebulaev/facebook-skills/.codex-marketplace/facebook-skills/skills/fb-hook-extractor#main ~/.claude/skills/fb-hook-extractorFor one project only, change the path to .claude/skills/fb-hook-extractor.
Not working?
- Check which app you pasted it into — the steps above name the right one.
- Some skills need the paid tier of Claude or ChatGPT.
Paste into Claude, ChatGPT or Cursor.
Show the full text89 lines
Facebook Page Hook Extractor
Paste a high-share Page post URL (or the text). Get back: which hook formula it uses, the exact structure, why it worked, and a blank template you can fill with your own voice.
When to use
- User finds a high-share Page post they want to study
- User wants to replicate a specific Page's pattern
- Before
fb-post-writer, to seed a draft with a proven shape
Input
A Facebook Page post URL (any of the many shapes: /posts/, permalink.php,
/watch/, share/p/). For a share/p/ link the page and post ids are hidden
behind an opaque token, so paste the post text. The bundle has no built-in Page
reader, so the user pastes the post text either way.
Output
- Formula identified (FB1-FB10 from
../../references/hook-formulas.md) with a confidence score - Container: short post vs story post, and why that container fit the idea
- Structural breakdown:
- The hook line (and for a story post, how the first line earns the "See more" tap)
- Body architecture (the beats, for a longer post)
- The close (what earns the share or the comment)
- Interaction-triggering devices (numbers, named entities, the question, the turn)
- Primary goal the original chased (shares / comments / reactions)
- Why it worked psychologically and algorithmically (meaningful interactions)
- Blank template with
{slot}markers matched to the original, ready for the user's topic - Cautions: anything in the original that would fail a 2026 audit (em dashes over the cap, an AI-vocab cluster, "We are thrilled to announce", engagement bait, 5+ hashtags)
Steps
- Parse the URL.
lib.url_parser.parse_facebook_url(url)returnspage,post_id,share_token,url_type. Ifurl_typeis "share", tell the user the ids are hidden and ask for the post text. - Get the text. This bundle has no built-in Page reader, so ask the user to paste the post (and any first comments, if relevant). If they later wire an Apify Page actor, read it automatically.
- Detect the container. A short post (one line / under ~80 chars) or a longer story post.
- Classify against the 10 formulas using features:
- Short post: a flat opinion (FB1)? one hard number (FB2)? an easy question (FB3)? a binary this-or-that (FB4)? a relatable shared moment (FB5)? a behind-the-scenes glimpse (FB6)? a usable tip (FB7)?
- Story post: a narrative with a turn (FB8)? a launch led human (FB9)? a named customer/team spotlight (FB10)?
- Score confidence. If two formulas fit, return the top 2 with fit scores.
- Extract structure. Label each part by its role. For a story post, map the first line (the "See more" tap), the beats, and the closer.
- Name the primary goal the original optimized for (shares / comments / reactions).
- Generate a blank template with
{slot}markers matched to the original shape and the user's topic. - Audit the source. Flag any AI tells in the original so the user does not copy them.
Example
See references/examples.md for worked teardowns.
Formulas reference
See ../../references/hook-formulas.md for the 10 canonical Facebook formulas
with full skeletons and goal tags.
Files
SKILL.md- this filereferences/classification-rules.md- feature extraction + scoring heuristicsreferences/examples.md- worked teardowns (short post and story post)
Related skills
fb-post-writer- use the extracted template to draft your ownfb-humanizer- audit your draft before shippingfb-content-planner- study competitors' Pages while planning
| 1 | |
| 2 | name fb-hook-extractor |
| 3 | description "Reverse-engineer the hook from a high-share Facebook Page post, from its URL or pasted text. Identifies which of the 10 canonical 2026 Facebook formulas it uses (one-line opinion, tiny number, ask-the-page question, this-or-that, behind-the-scenes, story post, announcement, spotlight), explains why it earned shares or comments, and returns a blank template mapped to your topic. Use to learn from a Page post you admire. Not for writing your own (use fb-post-writer)." |
| 4 | |
| 5 | |
| 6 | # Facebook Page Hook Extractor |
| 7 | |
| 8 | Paste a high-share Page post URL (or the text). Get back: which hook formula it |
| 9 | uses, the exact structure, why it worked, and a blank template you can fill with |
| 10 | your own voice. |
| 11 | |
| 12 | ## When to use |
| 13 | |
| 14 | User finds a high-share Page post they want to study |
| 15 | User wants to replicate a specific Page's pattern |
| 16 | Before `fb-post-writer`, to seed a draft with a proven shape |
| 17 | |
| 18 | ## Input |
| 19 | |
| 20 | A Facebook Page post URL (any of the many shapes: `/posts/`, `permalink.php`, |
| 21 | `/watch/`, `share/p/`). For a `share/p/` link the page and post ids are hidden |
| 22 | behind an opaque token, so paste the post text. The bundle has no built-in Page |
| 23 | reader, so the user pastes the post text either way. |
| 24 | |
| 25 | ## Output |
| 26 | |
| 27 | **Formula identified** (FB1-FB10 from `../../references/hook-formulas.md`) with |
| 28 | a confidence score |
| 29 | **Container:** short post vs story post, and why that container fit the idea |
| 30 | **Structural breakdown:** |
| 31 | The hook line (and for a story post, how the first line earns the "See more" tap) |
| 32 | Body architecture (the beats, for a longer post) |
| 33 | The close (what earns the share or the comment) |
| 34 | Interaction-triggering devices (numbers, named entities, the question, the turn) |
| 35 | **Primary goal** the original chased (shares / comments / reactions) |
| 36 | **Why it worked** psychologically and algorithmically (meaningful interactions) |
| 37 | **Blank template** with `{slot}` markers matched to the original, ready for the |
| 38 | user's topic |
| 39 | **Cautions:** anything in the original that would fail a 2026 audit (em |
| 40 | dashes over the cap, an AI-vocab cluster, "We are thrilled to announce", |
| 41 | engagement bait, 5+ hashtags) |
| 42 | |
| 43 | ## Steps |
| 44 | |
| 45 | **Parse the URL.** `lib.url_parser.parse_facebook_url(url)` returns `page`, |
| 46 | `post_id`, `share_token`, `url_type`. If `url_type` is "share", tell the user |
| 47 | the ids are hidden and ask for the post text. |
| 48 | **Get the text.** This bundle has no built-in Page reader, so ask the user to |
| 49 | paste the post (and any first comments, if relevant). If they later wire an |
| 50 | Apify Page actor, read it automatically. |
| 51 | **Detect the container.** A short post (one line / under ~80 chars) or a |
| 52 | longer story post. |
| 53 | **Classify against the 10 formulas** using features: |
| 54 | Short post: a flat opinion (FB1)? one hard number (FB2)? an easy question |
| 55 | (FB3)? a binary this-or-that (FB4)? a relatable shared moment (FB5)? a |
| 56 | behind-the-scenes glimpse (FB6)? a usable tip (FB7)? |
| 57 | Story post: a narrative with a turn (FB8)? a launch led human (FB9)? a named |
| 58 | customer/team spotlight (FB10)? |
| 59 | **Score confidence.** If two formulas fit, return the top 2 with fit scores. |
| 60 | **Extract structure.** Label each part by its role. For a story post, map the |
| 61 | first line (the "See more" tap), the beats, and the closer. |
| 62 | **Name the primary goal** the original optimized for (shares / comments / |
| 63 | reactions). |
| 64 | **Generate a blank template** with `{slot}` markers matched to the original |
| 65 | shape and the user's topic. |
| 66 | **Audit the source.** Flag any AI tells in the original so the user does not |
| 67 | copy them. |
| 68 | |
| 69 | ## Example |
| 70 | |
| 71 | See `references/examples.md` for worked teardowns. |
| 72 | |
| 73 | ## Formulas reference |
| 74 | |
| 75 | See `../../references/hook-formulas.md` for the 10 canonical Facebook formulas |
| 76 | with full skeletons and goal tags. |
| 77 | |
| 78 | ## Files |
| 79 | |
| 80 | `SKILL.md` - this file |
| 81 | `references/classification-rules.md` - feature extraction + scoring heuristics |
| 82 | `references/examples.md` - worked teardowns (short post and story post) |
| 83 | |
| 84 | ## Related skills |
| 85 | |
| 86 | `fb-post-writer` - use the extracted template to draft your own |
| 87 | `fb-humanizer` - audit your draft before shipping |
| 88 | `fb-content-planner` - study competitors' Pages while planning |
| 89 |