Reverse-engineer the hook from a viral Threads post

Threads hook extractor

by sergebulaev · MIT license · ★ 49 on GitHub

Reverse-engineer the hook from a viral Threads post or thread URL. Identifies which of the 10 canonical 2026 Threads formulas it uses (warm contrarian, data-point, build-in-public, quote-post, mini-list, relatable, listicle, story,…

---
name: threads-hook-extractor
description: "Reverse-engineer the hook from a viral Threads post or thread URL. Identifies which of the 10 canonical 2026 Threads formulas it uses (warm contrarian, data-point, build-in-public, quote-post, mini-list, relatable, listicle, story, curiosity-gap, how-I teardown), explains why it worked, and returns a blank template mapped to your topic with its primary goal (replies, reposts, likes, quotes). Use to learn from a post you admire. Not for writing your own (use threads-post-writer)."
---

# Threads Hook Extractor

Paste a viral Threads post or thread URL. 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 viral post or thread they want to study
- User wants to replicate a specific creator's pattern
- Before `threads-post-writer`, to seed a draft with a proven shape

## Input

Overview

Paste a viral Threads post or thread URL. Get back: which hook formula it uses, the exact structure, why it worked, and a blank template you can fill with your own voice.

What you get

Formula identified(T1-T10 from ../../references/hook-formulas.md) with a
Containersingle post vs thread, and why that container fit the idea
Structural breakdown
The hook line (and for a thread, how post 1 opens the loop)
Body architecture (per-post roles for a thread)
The close (what earns the repost or the reply)

Manual install (npx, ZIP)

Claude Codenpx skills add sergebulaev/threads-skills --skill threads-hook-extractor -g -a claude-code

Claude Code (degit)npx degit sergebulaev/threads-skills/skills/threads-hook-extractor#main ~/.claude/skills/threads-hook-extractor

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md3.8 KB

Read SKILL.md here

sergebulaev/main1 file shown

SKILL.md3.8 KB

Browse every file on GitHub↗

SKILL.md

Show the full text85 lines

threads-hook-extractor/SKILL.md85 lines · 3.8 KB

PreviewCode

Outline

RawView on GitHub

Threads Hook Extractor

Paste a viral Threads post or thread URL. 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 viral post or thread they want to study
User wants to replicate a specific creator's pattern
Before threads-post-writer, to seed a draft with a proven shape

Input

A Threads post or thread URL (threads.net or threads.com, /@handle/post/). For a thread, the URL of the first post is best.

Output

Formula identified (T1-T10 from ../../references/hook-formulas.md) with a confidence score
Container: single post vs thread, and why that container fit the idea
Structural breakdown:
- The hook line (and for a thread, how post 1 opens the loop)
- Body architecture (per-post roles for a thread)
- The close (what earns the repost or the reply)
- Reaction-triggering devices (numbers, named entities, the open loop, the warm invite)
Primary goal the original chased (replies / reposts / likes / quotes)
Why it worked psychologically and algorithmically
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 (more than one em dash in a post, an AI-vocab cluster, 2+ hashtags, link in post 1, a cold X tone)

Steps

Parse the URL. lib.url_parser.parse_threads_url(url) returns handle, post_id, url_type.
Get the text. This bundle has no built-in post reader, so ask the user to paste the post or the full thread text. (If they later wire an Apify post-read actor, read it automatically.)
Detect the container. One self-contained post, or a multi-post thread.
Classify against the 13 formulas using features:
- Single post: a warm contrarian claim (T1)? one hard number (T2)? a personal metric/confession (T3)? a quote post adding a layer (T4)? a one-line-per-item list (T5)? a relatable shared moment (T6)?
- Thread: a numbered teaching promise (T7)? a story starting at the tension (T8)? a surprising result with the mechanism withheld (T9)? a first-person "how I" teardown (T10)?
Score confidence. If two formulas fit, return the top 2 with fit scores.
Extract structure. Label each part by its role. For a thread, map post 1 (the loop), the front-loaded payoff, the body beats, and the closer.
Name the primary goal the original optimized for.
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 13 canonical Threads formulas with full skeletons and goal tags.

Files

SKILL.md - this file
references/classification-rules.md - feature extraction + scoring heuristics
references/examples.md - worked teardowns (single post and thread)

threads-post-writer - use the extracted template to draft your own post or thread
threads-humanizer --mode audit - audit your draft before shipping

1	---
2	name: threads-hook-extractor
3	description: "Reverse-engineer the hook from a viral Threads post or thread URL. Identifies which of the 10 canonical 2026 Threads formulas it uses (warm contrarian, data-point, build-in-public, quote-post, mini-list, relatable, listicle, story, curiosity-gap, how-I teardown), explains why it worked, and returns a blank template mapped to your topic with its primary goal (replies, reposts, likes, quotes). Use to learn from a post you admire. Not for writing your own (use threads-post-writer)."
4	---
5
6	# Threads Hook Extractor
7
8	Paste a viral Threads post or thread URL. Get back: which hook formula it uses,
9	the exact structure, why it worked, and a blank template you can fill with your
10	own voice.
11
12	## When to use
13
14	- User finds a viral post or thread they want to study
15	- User wants to replicate a specific creator's pattern
16	- Before `threads-post-writer`, to seed a draft with a proven shape
17
18	## Input
19
20	A Threads post or thread URL (`threads.net` or `threads.com`, `/@handle/post/`).
21	For a thread, the URL of the first post is best.
22
23	## Output
24
25	- Formula identified (T1-T10 from `../../references/hook-formulas.md`) with a
26	confidence score
27	- Container: single post vs thread, and why that container fit the idea
28	- Structural breakdown:
29	- The hook line (and for a thread, how post 1 opens the loop)
30	- Body architecture (per-post roles for a thread)
31	- The close (what earns the repost or the reply)
32	- Reaction-triggering devices (numbers, named entities, the open loop, the warm
33	invite)
34	- Primary goal the original chased (replies / reposts / likes / quotes)
35	- Why it worked psychologically and algorithmically
36	- Blank template with `{slot}` markers matched to the original, ready for the
37	user's topic
38	- Cautions: anything in the original that would fail a 2026 audit (more
39	than one em dash in a post, an AI-vocab cluster, 2+ hashtags, link in post 1,
40	a cold X tone)
41
42	## Steps
43
44	1. Parse the URL. `lib.url_parser.parse_threads_url(url)` returns `handle`,
45	`post_id`, `url_type`.
46	2. Get the text. This bundle has no built-in post reader, so ask the user to
47	paste the post or the full thread text. (If they later wire an Apify
48	post-read actor, read it automatically.)
49	3. Detect the container. One self-contained post, or a multi-post thread.
50	4. Classify against the 13 formulas using features:
51	- Single post: a warm contrarian claim (T1)? one hard number (T2)? a personal
52	metric/confession (T3)? a quote post adding a layer (T4)? a one-line-per-item
53	list (T5)? a relatable shared moment (T6)?
54	- Thread: a numbered teaching promise (T7)? a story starting at the tension
55	(T8)? a surprising result with the mechanism withheld (T9)? a first-person
56	"how I" teardown (T10)?
57	5. Score confidence. If two formulas fit, return the top 2 with fit scores.
58	6. Extract structure. Label each part by its role. For a thread, map post 1
59	(the loop), the front-loaded payoff, the body beats, and the closer.
60	7. Name the primary goal the original optimized for.
61	8. Generate a blank template with `{slot}` markers matched to the original
62	shape and the user's topic.
63	9. Audit the source. Flag any AI tells in the original so the user does not
64	copy them.
65
66	## Example
67
68	See `references/examples.md` for worked teardowns.
69
70	## Formulas reference
71
72	See `../../references/hook-formulas.md` for the 13 canonical Threads formulas
73	with full skeletons and goal tags.
74
75	## Files
76
77	- `SKILL.md` - this file
78	- `references/classification-rules.md` - feature extraction + scoring heuristics
79	- `references/examples.md` - worked teardowns (single post and thread)
80
81	## Related skills
82
83	- `threads-post-writer` - use the extracted template to draft your own post or thread
84	- `threads-humanizer --mode audit` - audit your draft before shipping
85