Crafts viral social media hook video prompts for TikTok

Higgsfield Social Hook Skill

by pixelab-ch · MIT license · ★ 6 on GitHub

Crafts viral social media hook video prompts for TikTok, Instagram Reels, and YouTube Shorts via Higgsfield. Routes to kling3_0 (primary) or grok_video (fallback).

---
name: higgsfield-social-hook
description: >-
  Crafts viral social media hook video prompts for TikTok, Instagram Reels,
  and YouTube Shorts via Higgsfield. Routes to kling3_0 (primary) or
  grok_video (fallback). Use when the user wants scroll-stopping hooks,
  viral short-form video, attention-grabbing openers, TikTok content,
  Reels content, Shorts content, or any social-media-optimized video.
when_to_use: >-
  Use for social media video, TikTok, Instagram Reels, YouTube Shorts, viral
  video, hook, scroll-stopper, short-form, trending, engagement, views, or
  any request for social media video content. Use even for "make something
  that gets views" or "viral content."
allowed-tools: >-
  mcp__higgsfield__generate_video
  mcp__higgsfield__generate_image
  mcp__higgsfield__models_explore
  mcp__higgsfield__job_status

Overview

Crafts scroll-stopping hook video prompts for TikTok, Instagram Reels, and YouTube Shorts and routes them to the best Higgsfield model. On request, it assembles the full parameter set, surfaces the credit cost, and — after explicit user confirmation — generates the asset via the opt-in generation flow.

Manual install (npx, ZIP)

Claude Codenpx skills add pixelab-ch/higgsfield-skills --skill higgsfield-social-hook -g -a claude-code

Claude Code (degit)npx degit pixelab-ch/higgsfield-skills/skills/11-social-hook#main ~/.claude/skills/higgsfield-social-hook

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.md5.8 KB

Read SKILL.md here

pixelab-ch/main1 file shown

SKILL.md5.8 KB

Browse every file on GitHub↗

SKILL.md

Show the full text121 lines

higgsfield-social-hook/SKILL.md121 lines · 5.8 KB

PreviewCode

Outline

RawView on GitHub

What this skill does

Model routing

Primary and fallback video models

	kling3_0 (primary)	grok_video (fallback)
Rationale	Wide duration range, mode tuning, supports start + end image	Fallback when primary unavailable; native audio
Mode	`std`, `pro`, `4k`*	No tunable params
Sound	`on`, `off`	Native audio (always on)
Aspect ratios	`16:9`, `9:16`, `1:1`	`16:9`, `9:16`, `1:1`
Duration	`3`–`15` s (continuous range)	`1`–`15` s (continuous range)
Media roles	`start_image`, `end_image`	`start_image` only (max 1)

*kling3_0 4k mode is a generation-mode enum, NOT a 4K output-resolution claim. Do not describe it as 4K video or high-resolution output.

Routing rule: Use kling3_0 by default. Only fall back to grok_video when (1) the primary model is unavailable, or (2) the user wants native audio generation and, after being informed of the trade-offs (no tunable params, no end_image, start_image max 1), explicitly accepts those constraints. Never switch silently.

MODEL-06 directive: If a parameter is rejected at generation time, call higgsfield:models_explore with the target model name to re-verify the live schema. Full parameter tables: references/model-specs.md.

Per-platform aspect ratio quick rule

Vertical 9:16 for TikTok / Reels / Shorts; 16:9 for standard YouTube and LinkedIn; 1:1 for Instagram feed square posts (kling3_0 and grok_video both support 1:1). Full per-platform recommendation table: references/model-specs.md.

Prompt-building workflow

Gather intent — Confirm with the user: content category (comedy, transformation, product, story, etc.), platform (TikTok/Reels/Shorts), target aspect ratio, desired duration, and whether native audio is needed.
Select model — Apply the routing table above. Use kling3_0 by default; select grok_video only when a routing trigger applies.
Build the hook prompt — Use the craft principles and the 25+ hook patterns from references/hook-craft.md:
- Identify the hook type (visual shock, curiosity gap, emotional trigger, pattern interrupt, or direct address) and the 2-second master template structure.
- Apply per-platform optimization from references/platforms.md.
- Reference worked prompts by category from references/examples.md.
Present for review — Show the assembled prompt, hook structure, model, aspect ratio, and duration to the user for review and refinement before any generation call.

Opt-in generation

Generation costs Higgsfield credits and requires explicit user confirmation before any generate call is made. This skill never auto-generates.

Full step-by-step flow (confirmation gate, balance/cost surface, generate → poll → display): ../../shared/generation-flow.md

This skill's primary model: kling3_0

Media upload: Conditional — only when the user supplies a start_image or end_image reference for image-to-video. This skill is NOT a mandatory-I2V skill; T2V is the default path. When the user provides a reference image, run the higgsfield:media_upload → higgsfield:media_confirm atomic pair before generating.

Tool signatures: ../../shared/mcp-tools.md

Reference materials

File	Contents
references/model-specs.md	Verified parameter tables for kling3_0 and grok_video, per-platform aspect ratio and duration recommendations, routing rationale, and re-verify directive
references/hook-craft.md	Hook psychology (5 attention triggers), the full 25+ proven hook pattern encyclopedia, the 2-second master template, retention techniques, sound strategy, text overlay strategy, and common mistakes
references/platforms.md	Per-platform optimization (TikTok/Reels/Shorts), content-category playbooks (comedy, educational, satisfying, transformation, BTS, reaction, storytime, product, lifestyle), trending format templates, and analytics-driven iteration guidance
references/examples.md	5 production-ready worked hook prompts (satisfying transformation, comedy skit, product reveal, emotional story, impossible visual) with full timing breakdowns and parameter settings

1	---
2	name: higgsfield-social-hook
3	description: >-
4	Crafts viral social media hook video prompts for TikTok, Instagram Reels,
5	and YouTube Shorts via Higgsfield. Routes to kling3_0 (primary) or
6	grok_video (fallback). Use when the user wants scroll-stopping hooks,
7	viral short-form video, attention-grabbing openers, TikTok content,
8	Reels content, Shorts content, or any social-media-optimized video.
9	when_to_use: >-
10	Use for social media video, TikTok, Instagram Reels, YouTube Shorts, viral
11	video, hook, scroll-stopper, short-form, trending, engagement, views, or
12	any request for social media video content. Use even for "make something
13	that gets views" or "viral content."
14	allowed-tools: >-
15	mcp__higgsfield__generate_video
16	mcp__higgsfield__generate_image
17	mcp__higgsfield__models_explore
18	mcp__higgsfield__job_status
19	mcp__higgsfield__job_display
20	mcp__higgsfield__media_upload
21	mcp__higgsfield__media_confirm
22	mcp__higgsfield__balance
23	mcp__higgsfield__show_plans_and_credits
24	---
25
26	# Higgsfield Social Hook Skill
27
28	## What this skill does
29
30	Crafts scroll-stopping hook video prompts for TikTok, Instagram Reels, and YouTube
31	Shorts and routes them to the best Higgsfield model. On request, it assembles the full
32	parameter set, surfaces the credit cost, and — after explicit user confirmation —
33	generates the asset via the opt-in generation flow.
34
35	---
36
37	## Model routing
38
39	### Primary and fallback video models
40
41	\| \| kling3_0 (primary) \| grok_video (fallback) \|
42	\|---\|---\|---\|
43	\| Rationale \| Wide duration range, mode tuning, supports start + end image \| Fallback when primary unavailable; native audio \|
44	\| Mode \| `std`, `pro`, `4k`* \| No tunable params \|
45	\| Sound \| `on`, `off` \| Native audio (always on) \|
46	\| Aspect ratios \| `16:9`, `9:16`, `1:1` \| `16:9`, `9:16`, `1:1` \|
47	\| Duration \| `3`–`15` s (continuous range) \| `1`–`15` s (continuous range) \|
48	\| Media roles \| `start_image`, `end_image` \| `start_image` only (max 1) \|
49
50	`kling3_0` `4k` mode is a generation-mode enum*, NOT a 4K output-resolution claim.
51	Do not describe it as 4K video or high-resolution output.
52
53	Routing rule: Use `kling3_0` by default. Only fall back to `grok_video` when
54	(1) the primary model is unavailable, or (2) the user wants native audio generation
55	and, after being informed of the trade-offs (no tunable params, no `end_image`,
56	`start_image` max 1), explicitly accepts those constraints. Never switch silently.
57
58	MODEL-06 directive: If a parameter is rejected at generation time, call
59	`higgsfield:models_explore` with the target model name to re-verify the live schema.
60	Full parameter tables: [references/model-specs.md](references/model-specs.md).
61
62	### Per-platform aspect ratio quick rule
63
64	Vertical `9:16` for TikTok / Reels / Shorts; `16:9` for standard YouTube and LinkedIn;
65	`1:1` for Instagram feed square posts (`kling3_0` and `grok_video` both support `1:1`).
66	Full per-platform recommendation table: [references/model-specs.md](references/model-specs.md).
67
68	---
69
70	## Prompt-building workflow
71
72	1. Gather intent — Confirm with the user: content category (comedy, transformation,
73	product, story, etc.), platform (TikTok/Reels/Shorts), target aspect ratio, desired
74	duration, and whether native audio is needed.
75
76	2. Select model — Apply the routing table above. Use `kling3_0` by default; select
77	`grok_video` only when a routing trigger applies.
78
79	3. Build the hook prompt — Use the craft principles and the 25+ hook patterns from
80	[references/hook-craft.md](references/hook-craft.md):
81	- Identify the hook type (visual shock, curiosity gap, emotional trigger, pattern
82	interrupt, or direct address) and the 2-second master template structure.
83	- Apply per-platform optimization from
84	[references/platforms.md](references/platforms.md).
85	- Reference worked prompts by category from
86	[references/examples.md](references/examples.md).
87
88	4. Present for review — Show the assembled prompt, hook structure, model, aspect
89	ratio, and duration to the user for review and refinement before any generation call.
90
91	---
92
93	## Opt-in generation
94
95	Generation costs Higgsfield credits and requires explicit user confirmation before any
96	generate call is made. This skill never auto-generates.
97
98	Full step-by-step flow (confirmation gate, balance/cost surface,
99	generate → poll → display):
100	[`../../shared/generation-flow.md`](../../shared/generation-flow.md)
101
102	This skill's primary model: `kling3_0`
103
104	Media upload: Conditional — only when the user supplies a `start_image` or
105	`end_image` reference for image-to-video. This skill is NOT a mandatory-I2V skill;
106	T2V is the default path. When the user provides a reference image, run the
107	`higgsfield:media_upload` → `higgsfield:media_confirm` atomic pair before generating.
108
109	Tool signatures: [`../../shared/mcp-tools.md`](../../shared/mcp-tools.md)
110
111	---
112
113	## Reference materials
114
115	\| File \| Contents \|
116	\|---\|---\|
117	\| [references/model-specs.md](references/model-specs.md) \| Verified parameter tables for kling3_0 and grok_video, per-platform aspect ratio and duration recommendations, routing rationale, and re-verify directive \|
118	\| [references/hook-craft.md](references/hook-craft.md) \| Hook psychology (5 attention triggers), the full 25+ proven hook pattern encyclopedia, the 2-second master template, retention techniques, sound strategy, text overlay strategy, and common mistakes \|
119	\| [references/platforms.md](references/platforms.md) \| Per-platform optimization (TikTok/Reels/Shorts), content-category playbooks (comedy, educational, satisfying, transformation, BTS, reaction, storytime, product, lifestyle), trending format templates, and analytics-driven iteration guidance \|
120	\| [references/examples.md](references/examples.md) \| 5 production-ready worked hook prompts (satisfying transformation, comedy skit, product reveal, emotional story, impossible visual) with full timing breakdowns and parameter settings \|
121