@growthub/cli 0.3.38 → 0.3.40
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +4 -2
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/.env.example +9 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/QUICKSTART.md +95 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/brands/NEW-CLIENT.md +46 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/brands/_template/brand-kit.md +89 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/brands/growthub/brand-kit.md +96 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/bundles/growthub-open-higgsfield-studio-v1.json +57 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/docs/open-higgsfield-fork-integration.md +63 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/docs/provider-adapter-layer.md +67 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/examples/platform-ready-handoff-sample.md +24 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/examples/prompt-matrix-sample.md +6 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/examples/shot-plan-sample.md +7 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/examples/visual-campaign-brief-sample.md +22 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/growthub-meta/README.md +67 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/growthub-meta/kit-standard.md +47 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/kit.json +108 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/output/README.md +34 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/output-standards.md +133 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/runtime-assumptions.md +145 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/setup/check-deps.sh +37 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/setup/clone-fork.sh +40 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/setup/patch-cors-proxy.sh +139 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/setup/verify-env.mjs +72 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/skills.md +257 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/asset-tracking.md +5 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/frame-analysis.md +24 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/generation-batch-plan.md +7 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/model-selection-recommendation.md +23 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/platform-ready-execution-handoff.md +17 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/prompt-matrix.md +7 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/prompt-templates/cinema-generation.md +16 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/prompt-templates/image-generation.md +11 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/prompt-templates/lip-sync-generation.md +14 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/prompt-templates/video-generation.md +11 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/review-qa-checklist.md +26 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/shot-plan.md +11 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/studio-selection-brief.md +18 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/templates/visual-campaign-brief.md +24 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/validation-checklist.md +49 -0
- package/assets/worker-kits/growthub-open-higgsfield-studio-v1/workers/open-higgsfield-studio-operator/CLAUDE.md +264 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -27,7 +27,9 @@ They should be understood as packaged execution environments. A kit can carry pr
|
|
|
27
27
|
```bash
|
|
28
28
|
growthub kit list
|
|
29
29
|
growthub kit inspect creative-strategist-v1
|
|
30
|
+
growthub kit inspect growthub-open-higgsfield-studio-v1
|
|
30
31
|
growthub kit download creative-strategist-v1
|
|
32
|
+
growthub kit download growthub-open-higgsfield-studio-v1
|
|
31
33
|
growthub kit path creative-strategist-v1
|
|
32
34
|
growthub kit validate /absolute/path/to/kit
|
|
33
35
|
```
|
|
@@ -35,9 +37,9 @@ growthub kit validate /absolute/path/to/kit
|
|
|
35
37
|
V1 is intentionally narrow:
|
|
36
38
|
|
|
37
39
|
- bundled catalog plus local export only
|
|
38
|
-
-
|
|
40
|
+
- downloadable worker kits for creative strategy, email strategy, and Open Higgsfield AI visual production
|
|
39
41
|
- deterministic zip plus expanded export folder
|
|
40
|
-
- public
|
|
42
|
+
- public example brand kits only
|
|
41
43
|
- no heartbeat wiring, app install flow, server registry, plugin lifecycle, or database kit records
|
|
42
44
|
|
|
43
45
|
### How local adapters use worker kits
|
|
@@ -0,0 +1,9 @@
|
|
|
1
|
+
# Growthub Open Higgsfield Studio — Environment Config
|
|
2
|
+
# Copy this file to .env and fill in your values.
|
|
3
|
+
# Never commit .env to version control.
|
|
4
|
+
|
|
5
|
+
# Your Muapi API key — get one at https://muapi.ai/dashboard
|
|
6
|
+
MUAPI_API_KEY=your_muapi_key_here
|
|
7
|
+
|
|
8
|
+
# Muapi base URL — do not change unless self-hosting
|
|
9
|
+
MUAPI_BASE_URL=https://api.muapi.io
|
|
@@ -0,0 +1,95 @@
|
|
|
1
|
+
# Quick Start — Open Higgsfield Studio Worker Kit
|
|
2
|
+
|
|
3
|
+
This folder is your self-contained agent working directory for Open Higgsfield AI visual production.
|
|
4
|
+
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## Step 1 — Point your Working Directory at this folder
|
|
8
|
+
|
|
9
|
+
**Growthub local (primary):** Open Growthub local and set the **Working Directory** to this folder in your project settings. Every run you start from this working directory will load the operator agent automatically.
|
|
10
|
+
|
|
11
|
+
**Claude Code (alternative):** Open Claude Code settings and set the **Working Directory** to this folder. The operator agent loads from `workers/open-higgsfield-studio-operator/CLAUDE.md` on session start.
|
|
12
|
+
|
|
13
|
+
---
|
|
14
|
+
|
|
15
|
+
## Step 2 — Add your MUAPI key
|
|
16
|
+
|
|
17
|
+
```bash
|
|
18
|
+
cp .env.example .env
|
|
19
|
+
```
|
|
20
|
+
|
|
21
|
+
Open `.env` and replace `your_muapi_key_here` with your key from [muapi.ai/dashboard](https://muapi.ai/dashboard).
|
|
22
|
+
|
|
23
|
+
The agent checks for this key at the start of every session (Step 0 of the workflow). It will not proceed without it.
|
|
24
|
+
|
|
25
|
+
---
|
|
26
|
+
|
|
27
|
+
## Step 3 — Verify your key works (optional but recommended)
|
|
28
|
+
|
|
29
|
+
```bash
|
|
30
|
+
node setup/verify-env.mjs
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
Runs a lightweight ping against the Muapi API with your key. Exits 0 on success. Prints a clear error if the key is invalid or unreachable.
|
|
34
|
+
|
|
35
|
+
---
|
|
36
|
+
|
|
37
|
+
## Step 4 — Check local dependencies (local-fork mode only)
|
|
38
|
+
|
|
39
|
+
```bash
|
|
40
|
+
bash setup/check-deps.sh
|
|
41
|
+
```
|
|
42
|
+
|
|
43
|
+
Checks for `node`, `npm`, `git`, and `ffmpeg`. All four are required for local-fork execution and frame-analysis workflows.
|
|
44
|
+
|
|
45
|
+
---
|
|
46
|
+
|
|
47
|
+
## Step 5 — Boot the local fork (local-fork mode only)
|
|
48
|
+
|
|
49
|
+
```bash
|
|
50
|
+
bash setup/clone-fork.sh
|
|
51
|
+
```
|
|
52
|
+
|
|
53
|
+
Clones the Open Higgsfield AI repo to `~/open-higgsfield-ai`, installs dependencies, **automatically applies the CORS proxy patch** (see `setup/patch-cors-proxy.sh`), and starts the dev server at `http://localhost:3001`.
|
|
54
|
+
|
|
55
|
+
The CORS patch is required — the upstream repo calls `api.muapi.ai` directly from the browser, which modern browsers block. The patch routes all API calls through the local Next.js server instead.
|
|
56
|
+
|
|
57
|
+
Skip this step if you are using browser-hosted or desktop-app mode.
|
|
58
|
+
|
|
59
|
+
**Already cloned but hitting CORS errors?** Run the patch standalone:
|
|
60
|
+
```bash
|
|
61
|
+
bash setup/patch-cors-proxy.sh
|
|
62
|
+
```
|
|
63
|
+
Then restart your dev server.
|
|
64
|
+
|
|
65
|
+
---
|
|
66
|
+
|
|
67
|
+
## Step 6 — Start a new session
|
|
68
|
+
|
|
69
|
+
**Growthub local:** Start a new run from this working directory. The agent loads automatically.
|
|
70
|
+
|
|
71
|
+
**Claude Code:** Open a new session with this folder as the Working Directory. The agent reads `skills.md` and the methodology automatically.
|
|
72
|
+
|
|
73
|
+
In both cases the agent will ask you 3 clarifying questions before generating anything.
|
|
74
|
+
|
|
75
|
+
---
|
|
76
|
+
|
|
77
|
+
## Execution modes
|
|
78
|
+
|
|
79
|
+
| Mode | When to use |
|
|
80
|
+
|---|---|
|
|
81
|
+
| `local-fork` | Local checkout running at localhost:3001 |
|
|
82
|
+
| `browser-hosted` | Hosted app at muapi.ai/open-higgsfield-ai |
|
|
83
|
+
| `desktop-app` | Electron app installed locally |
|
|
84
|
+
|
|
85
|
+
---
|
|
86
|
+
|
|
87
|
+
## First-run checklist
|
|
88
|
+
|
|
89
|
+
See `validation-checklist.md` for the full pre-session checklist before your first generation run.
|
|
90
|
+
|
|
91
|
+
---
|
|
92
|
+
|
|
93
|
+
## Creating a brand kit for a new client
|
|
94
|
+
|
|
95
|
+
See `brands/NEW-CLIENT.md`.
|
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
# Creating a New Client Brand Kit
|
|
2
|
+
|
|
3
|
+
Each client you run campaigns for should have their own brand kit. The agent uses this as its primary brand reference during Step 1 of every session.
|
|
4
|
+
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## Setup
|
|
8
|
+
|
|
9
|
+
```bash
|
|
10
|
+
cp brands/_template/brand-kit.md brands/<client-slug>/brand-kit.md
|
|
11
|
+
```
|
|
12
|
+
|
|
13
|
+
Replace `<client-slug>` with a lowercase hyphenated identifier (e.g. `acme-corp`, `solo-founder`, `ecom-brand-x`).
|
|
14
|
+
|
|
15
|
+
---
|
|
16
|
+
|
|
17
|
+
## Required fields to fill in
|
|
18
|
+
|
|
19
|
+
Open your new `brands/<client-slug>/brand-kit.md` and complete:
|
|
20
|
+
|
|
21
|
+
| Field | What to write |
|
|
22
|
+
|---|---|
|
|
23
|
+
| Brand name | Full brand name as it appears in content |
|
|
24
|
+
| Visual identity | Colors, typography, logo usage notes |
|
|
25
|
+
| Tone and voice | Adjectives that describe how the brand communicates |
|
|
26
|
+
| Target audience | Who the content is for |
|
|
27
|
+
| Content restrictions | What to avoid in visuals or copy |
|
|
28
|
+
| Reference assets | Paths to existing brand images, videos, or logo files |
|
|
29
|
+
|
|
30
|
+
Fill in every section. Incomplete brand kits result in generic outputs.
|
|
31
|
+
|
|
32
|
+
---
|
|
33
|
+
|
|
34
|
+
## Telling the agent to use your brand kit
|
|
35
|
+
|
|
36
|
+
At the start of your session, say:
|
|
37
|
+
|
|
38
|
+
> "Use `brands/<client-slug>/brand-kit.md` as the active brand kit."
|
|
39
|
+
|
|
40
|
+
The agent will load it in Step 1 instead of the Growthub default.
|
|
41
|
+
|
|
42
|
+
---
|
|
43
|
+
|
|
44
|
+
## Multiple clients
|
|
45
|
+
|
|
46
|
+
Keep one subdirectory per client under `brands/`. Each session uses exactly one active brand kit.
|
|
@@ -0,0 +1,89 @@
|
|
|
1
|
+
# Brand Kit — [CLIENT NAME]
|
|
2
|
+
|
|
3
|
+
Copy to `brands/<client-slug>/brand-kit.md` and fill before producing outputs.
|
|
4
|
+
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## IDENTITY
|
|
8
|
+
|
|
9
|
+
```yaml
|
|
10
|
+
client_name: "[CLIENT NAME]"
|
|
11
|
+
slug: "[client-slug]"
|
|
12
|
+
industry: "[industry]"
|
|
13
|
+
primary_offer: "[offer]"
|
|
14
|
+
campaign_owner: "[owner]"
|
|
15
|
+
date_onboarded: "YYYY-MM-DD"
|
|
16
|
+
```
|
|
17
|
+
|
|
18
|
+
## AUDIENCE
|
|
19
|
+
|
|
20
|
+
```yaml
|
|
21
|
+
primary_persona:
|
|
22
|
+
role: "[role]"
|
|
23
|
+
company_type: "[company type]"
|
|
24
|
+
pain_point: "[pain]"
|
|
25
|
+
desired_outcome: "[desired outcome]"
|
|
26
|
+
awareness_level: "[awareness]"
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
## POSITIONING
|
|
30
|
+
|
|
31
|
+
```yaml
|
|
32
|
+
core_positioning: "[one-sentence positioning]"
|
|
33
|
+
what_they_buy: "[outcome they actually want]"
|
|
34
|
+
unique_mechanism: "[why this works]"
|
|
35
|
+
proof_points:
|
|
36
|
+
- "[approved proof only]"
|
|
37
|
+
```
|
|
38
|
+
|
|
39
|
+
## VISUAL SYSTEM
|
|
40
|
+
|
|
41
|
+
```yaml
|
|
42
|
+
visual_identity:
|
|
43
|
+
palette:
|
|
44
|
+
primary: "#000000"
|
|
45
|
+
secondary: "#FFFFFF"
|
|
46
|
+
accent: "#CCCCCC"
|
|
47
|
+
visual_adjectives:
|
|
48
|
+
- "[cinematic]"
|
|
49
|
+
- "[premium]"
|
|
50
|
+
- "[clean]"
|
|
51
|
+
prohibited_visuals:
|
|
52
|
+
- "[visual no-go]"
|
|
53
|
+
- "[visual no-go]"
|
|
54
|
+
reference_styles:
|
|
55
|
+
- "[director / campaign / style]"
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
## MESSAGING
|
|
59
|
+
|
|
60
|
+
```yaml
|
|
61
|
+
voice_and_tone:
|
|
62
|
+
- "[direct]"
|
|
63
|
+
- "[clear]"
|
|
64
|
+
approved_phrases:
|
|
65
|
+
- "[approved phrase]"
|
|
66
|
+
messaging_guardrails:
|
|
67
|
+
- "[no-go claim]"
|
|
68
|
+
cta_language:
|
|
69
|
+
primary: "[primary CTA]"
|
|
70
|
+
secondary: "[secondary CTA]"
|
|
71
|
+
```
|
|
72
|
+
|
|
73
|
+
## ASSET LIBRARY
|
|
74
|
+
|
|
75
|
+
```yaml
|
|
76
|
+
available_assets:
|
|
77
|
+
product_stills: "[path or URL]"
|
|
78
|
+
brand_guidelines: "[path or URL]"
|
|
79
|
+
source_video: "[path or URL]"
|
|
80
|
+
portrait_assets: "[path or URL]"
|
|
81
|
+
audio_assets: "[path or URL]"
|
|
82
|
+
prior_generations: "[path or URL]"
|
|
83
|
+
```
|
|
84
|
+
|
|
85
|
+
## DELIVERABLES LOG
|
|
86
|
+
|
|
87
|
+
```text
|
|
88
|
+
- YYYY-MM-DD | Open Higgsfield Visual Package v<N> — <Project Name> | output/<client-slug>/<project-slug>/
|
|
89
|
+
```
|
|
@@ -0,0 +1,96 @@
|
|
|
1
|
+
# Brand Kit — Growthub
|
|
2
|
+
|
|
3
|
+
Reference example brand kit for visual-generation work.
|
|
4
|
+
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## IDENTITY
|
|
8
|
+
|
|
9
|
+
```yaml
|
|
10
|
+
client_name: "Growthub"
|
|
11
|
+
slug: "growthub"
|
|
12
|
+
industry: "AI-enabled growth infrastructure and creative operations"
|
|
13
|
+
primary_offer: "Creative velocity systems, visual strategy, and execution support for paid-media operators"
|
|
14
|
+
campaign_owner: "Growthub"
|
|
15
|
+
date_onboarded: "2026-04-10"
|
|
16
|
+
```
|
|
17
|
+
|
|
18
|
+
## AUDIENCE
|
|
19
|
+
|
|
20
|
+
```yaml
|
|
21
|
+
primary_persona:
|
|
22
|
+
role: "performance lead, agency owner, or growth operator"
|
|
23
|
+
company_type: "DTC brand, agency, or startup running paid acquisition"
|
|
24
|
+
pain_point: "creative throughput is too slow to sustain testing velocity"
|
|
25
|
+
desired_outcome: "more winning concepts without slower turnaround or more headcount"
|
|
26
|
+
awareness_level: "problem-aware"
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
## POSITIONING
|
|
30
|
+
|
|
31
|
+
```yaml
|
|
32
|
+
core_positioning: "Growthub is the operating layer that removes the bottleneck between creative ideas and campaign execution."
|
|
33
|
+
what_they_buy: "speed to winning creative with more control and less chaos"
|
|
34
|
+
unique_mechanism: "operator-grade planning plus AI-assisted visual production workflows"
|
|
35
|
+
proof_points:
|
|
36
|
+
- "Use only approved client-result examples already cleared by Growthub"
|
|
37
|
+
```
|
|
38
|
+
|
|
39
|
+
## VISUAL SYSTEM
|
|
40
|
+
|
|
41
|
+
```yaml
|
|
42
|
+
visual_identity:
|
|
43
|
+
palette:
|
|
44
|
+
primary: "#0E1726"
|
|
45
|
+
secondary: "#F4F1E8"
|
|
46
|
+
accent: "#D8613C"
|
|
47
|
+
visual_adjectives:
|
|
48
|
+
- "decisive"
|
|
49
|
+
- "cinematic"
|
|
50
|
+
- "premium"
|
|
51
|
+
- "high-signal"
|
|
52
|
+
prohibited_visuals:
|
|
53
|
+
- "generic SaaS gradient slop"
|
|
54
|
+
- "empty dashboard glamour shots with no human tension"
|
|
55
|
+
reference_styles:
|
|
56
|
+
- "high-contrast product-led motion"
|
|
57
|
+
- "operator POV"
|
|
58
|
+
- "documentary-meets-performance-marketing"
|
|
59
|
+
```
|
|
60
|
+
|
|
61
|
+
## MESSAGING
|
|
62
|
+
|
|
63
|
+
```yaml
|
|
64
|
+
voice_and_tone:
|
|
65
|
+
- "direct"
|
|
66
|
+
- "operator-level"
|
|
67
|
+
- "confident"
|
|
68
|
+
approved_phrases:
|
|
69
|
+
- "creative velocity"
|
|
70
|
+
- "remove the bottleneck between ideas and execution"
|
|
71
|
+
- "speed to winning ads"
|
|
72
|
+
messaging_guardrails:
|
|
73
|
+
- "Do not promise guaranteed revenue outcomes"
|
|
74
|
+
- "Do not reduce Growthub to just an AI tool"
|
|
75
|
+
cta_language:
|
|
76
|
+
primary: "Book your growth call"
|
|
77
|
+
secondary: "Review the plan and approve the batch"
|
|
78
|
+
```
|
|
79
|
+
|
|
80
|
+
## ASSET LIBRARY
|
|
81
|
+
|
|
82
|
+
```yaml
|
|
83
|
+
available_assets:
|
|
84
|
+
product_stills: "[fill per engagement]"
|
|
85
|
+
brand_guidelines: "[fill per engagement]"
|
|
86
|
+
source_video: "[fill per engagement]"
|
|
87
|
+
portrait_assets: "[fill per engagement]"
|
|
88
|
+
audio_assets: "[fill per engagement]"
|
|
89
|
+
prior_generations: "[fill per engagement]"
|
|
90
|
+
```
|
|
91
|
+
|
|
92
|
+
## DELIVERABLES LOG
|
|
93
|
+
|
|
94
|
+
```text
|
|
95
|
+
- 2026-04-10 | Open Higgsfield Visual Package v1 — Studio Launch Reference | output/growthub/studio-launch-reference/
|
|
96
|
+
```
|
|
@@ -0,0 +1,57 @@
|
|
|
1
|
+
{
|
|
2
|
+
"schemaVersion": 2,
|
|
3
|
+
"bundle": {
|
|
4
|
+
"id": "growthub-open-higgsfield-studio-v1",
|
|
5
|
+
"version": "1.0.0",
|
|
6
|
+
"kitId": "growthub-open-higgsfield-studio-v1",
|
|
7
|
+
"workerId": "open-higgsfield-studio-operator"
|
|
8
|
+
},
|
|
9
|
+
"briefType": "open-higgsfield-visual-production",
|
|
10
|
+
"publicExampleBrandPaths": [
|
|
11
|
+
"brands/growthub/brand-kit.md"
|
|
12
|
+
],
|
|
13
|
+
"requiredFrozenAssets": [
|
|
14
|
+
"QUICKSTART.md",
|
|
15
|
+
".env.example",
|
|
16
|
+
"skills.md",
|
|
17
|
+
"output-standards.md",
|
|
18
|
+
"runtime-assumptions.md",
|
|
19
|
+
"validation-checklist.md",
|
|
20
|
+
"workers/open-higgsfield-studio-operator/CLAUDE.md",
|
|
21
|
+
"brands/_template/brand-kit.md",
|
|
22
|
+
"brands/growthub/brand-kit.md",
|
|
23
|
+
"brands/NEW-CLIENT.md",
|
|
24
|
+
"setup/clone-fork.sh",
|
|
25
|
+
"setup/verify-env.mjs",
|
|
26
|
+
"setup/check-deps.sh",
|
|
27
|
+
"output/README.md",
|
|
28
|
+
"templates/visual-campaign-brief.md",
|
|
29
|
+
"templates/studio-selection-brief.md",
|
|
30
|
+
"templates/model-selection-recommendation.md",
|
|
31
|
+
"templates/shot-plan.md",
|
|
32
|
+
"templates/prompt-matrix.md",
|
|
33
|
+
"templates/generation-batch-plan.md",
|
|
34
|
+
"templates/asset-tracking.md",
|
|
35
|
+
"templates/review-qa-checklist.md",
|
|
36
|
+
"templates/platform-ready-execution-handoff.md",
|
|
37
|
+
"templates/frame-analysis.md",
|
|
38
|
+
"templates/prompt-templates/image-generation.md",
|
|
39
|
+
"templates/prompt-templates/video-generation.md",
|
|
40
|
+
"templates/prompt-templates/lip-sync-generation.md",
|
|
41
|
+
"templates/prompt-templates/cinema-generation.md",
|
|
42
|
+
"examples/visual-campaign-brief-sample.md",
|
|
43
|
+
"examples/shot-plan-sample.md",
|
|
44
|
+
"examples/prompt-matrix-sample.md",
|
|
45
|
+
"examples/platform-ready-handoff-sample.md",
|
|
46
|
+
"docs/open-higgsfield-fork-integration.md",
|
|
47
|
+
"docs/provider-adapter-layer.md",
|
|
48
|
+
"growthub-meta/README.md",
|
|
49
|
+
"growthub-meta/kit-standard.md"
|
|
50
|
+
],
|
|
51
|
+
"optionalPresets": [],
|
|
52
|
+
"export": {
|
|
53
|
+
"folderName": "growthub-agent-worker-kit-open-higgsfield-studio-v1",
|
|
54
|
+
"zipFileName": "growthub-agent-worker-kit-open-higgsfield-studio-v1.zip"
|
|
55
|
+
},
|
|
56
|
+
"activationModes": ["export"]
|
|
57
|
+
}
|
|
@@ -0,0 +1,63 @@
|
|
|
1
|
+
# Open Higgsfield Fork Integration Notes
|
|
2
|
+
|
|
3
|
+
This document tells the agent what to inspect in a maintained local fork before it commits to a plan.
|
|
4
|
+
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## EXPECTED REPO LAYOUT
|
|
8
|
+
|
|
9
|
+
Based on the upstream repository:
|
|
10
|
+
|
|
11
|
+
```text
|
|
12
|
+
app/
|
|
13
|
+
components/
|
|
14
|
+
electron/
|
|
15
|
+
packages/studio/src/
|
|
16
|
+
README.md
|
|
17
|
+
package.json
|
|
18
|
+
```
|
|
19
|
+
|
|
20
|
+
The agent should treat these as the runtime-critical zones:
|
|
21
|
+
- `packages/studio/src/models.js`
|
|
22
|
+
- `packages/studio/src/muapi.js`
|
|
23
|
+
- `packages/studio/src/components/*.jsx`
|
|
24
|
+
- `components/StandaloneShell.js`
|
|
25
|
+
- `components/ApiKeyModal.js`
|
|
26
|
+
- `electron/`
|
|
27
|
+
|
|
28
|
+
---
|
|
29
|
+
|
|
30
|
+
## WHAT TO INSPECT BEFORE GENERATING
|
|
31
|
+
|
|
32
|
+
1. Which studios are actually rendered in the current fork
|
|
33
|
+
2. Whether model ids or endpoint names differ from upstream
|
|
34
|
+
3. Which controls the UI exposes for the chosen model
|
|
35
|
+
4. Whether prompt is optional for the chosen mode
|
|
36
|
+
5. How many input images are supported
|
|
37
|
+
6. Whether upload history and generation history are available
|
|
38
|
+
7. Whether browser and desktop packaging diverge
|
|
39
|
+
|
|
40
|
+
---
|
|
41
|
+
|
|
42
|
+
## SOURCE OF TRUTH RULES
|
|
43
|
+
|
|
44
|
+
- `models.js` is the model source of truth
|
|
45
|
+
- `muapi.js` is the provider request-flow source of truth
|
|
46
|
+
- the relevant studio component is the UI behavior source of truth
|
|
47
|
+
- `README.md` is the environment and packaging overview
|
|
48
|
+
- `electron/` is the desktop-specific behavior source of truth
|
|
49
|
+
|
|
50
|
+
If these conflict, prefer:
|
|
51
|
+
1. studio component behavior
|
|
52
|
+
2. provider client behavior
|
|
53
|
+
3. model registry
|
|
54
|
+
4. README summary
|
|
55
|
+
|
|
56
|
+
---
|
|
57
|
+
|
|
58
|
+
## FORK-AWARE OUTPUT RULE
|
|
59
|
+
|
|
60
|
+
Every handoff should say whether it was:
|
|
61
|
+
- `fork-verified`
|
|
62
|
+
- `upstream-verified`
|
|
63
|
+
- `assumption-based`
|
|
@@ -0,0 +1,67 @@
|
|
|
1
|
+
# Provider Adapter Layer Notes
|
|
2
|
+
|
|
3
|
+
Muapi is the reference implementation for this kit because the upstream Open Higgsfield AI workflow is built around it. The adapter layer must remain pluggable.
|
|
4
|
+
|
|
5
|
+
---
|
|
6
|
+
|
|
7
|
+
## REFERENCE PROVIDER — MUAPI
|
|
8
|
+
|
|
9
|
+
| Field | Value |
|
|
10
|
+
|---|---|
|
|
11
|
+
| Provider name | Muapi |
|
|
12
|
+
| Auth pattern | `x-api-key` header |
|
|
13
|
+
| Upload flow | file upload first when image, video, or audio assets are required |
|
|
14
|
+
| Submit flow | `POST /api/v1/{model-endpoint}` |
|
|
15
|
+
| Poll flow | `GET /api/v1/predictions/{request_id}/result` |
|
|
16
|
+
| Result flow | completed payload yields output URL(s) and status |
|
|
17
|
+
|
|
18
|
+
---
|
|
19
|
+
|
|
20
|
+
## ADAPTER CONTRACT
|
|
21
|
+
|
|
22
|
+
Every provider adapter should support:
|
|
23
|
+
- `UPLOAD_ASSET`
|
|
24
|
+
- `SUBMIT_GENERATION`
|
|
25
|
+
- `POLL_RESULT`
|
|
26
|
+
- `NORMALIZE_RESULT`
|
|
27
|
+
- `LIST_MODEL_CAPABILITIES`
|
|
28
|
+
|
|
29
|
+
Optional:
|
|
30
|
+
- `CANCEL_JOB`
|
|
31
|
+
- `LIST_HISTORY`
|
|
32
|
+
- `HEALTHCHECK`
|
|
33
|
+
|
|
34
|
+
---
|
|
35
|
+
|
|
36
|
+
## MODEL ENDPOINT MAPPING ASSUMPTION
|
|
37
|
+
|
|
38
|
+
The agent should assume that a model entry maps to:
|
|
39
|
+
- a studio category
|
|
40
|
+
- an endpoint id
|
|
41
|
+
- accepted inputs
|
|
42
|
+
- exposed controls
|
|
43
|
+
- output class
|
|
44
|
+
|
|
45
|
+
Do not recommend a model without naming the endpoint or the endpoint assumption.
|
|
46
|
+
|
|
47
|
+
---
|
|
48
|
+
|
|
49
|
+
## FALLBACK MODES
|
|
50
|
+
|
|
51
|
+
When the reference provider path fails:
|
|
52
|
+
- fallback to a second model in the same studio if available
|
|
53
|
+
- fallback to a neighboring studio only if output intent can still be preserved
|
|
54
|
+
- mark the handoff with the exact fallback trigger
|
|
55
|
+
|
|
56
|
+
---
|
|
57
|
+
|
|
58
|
+
## FUTURE PROVIDER EXTENSION PATH
|
|
59
|
+
|
|
60
|
+
New providers should be added by implementing the same contract and documenting:
|
|
61
|
+
- auth
|
|
62
|
+
- endpoint mapping
|
|
63
|
+
- submit / poll rhythm
|
|
64
|
+
- file upload behavior
|
|
65
|
+
- result normalization
|
|
66
|
+
|
|
67
|
+
Do not rewrite this kit around one provider-specific prompt schema.
|
|
@@ -0,0 +1,24 @@
|
|
|
1
|
+
# Growthub Platform-Ready Execution Handoff v1
|
|
2
|
+
|
|
3
|
+
## Runtime Mode
|
|
4
|
+
|
|
5
|
+
local-fork
|
|
6
|
+
|
|
7
|
+
## Repo Inspection Summary
|
|
8
|
+
|
|
9
|
+
- `packages/studio/src/models.js` reviewed for available video and lip-sync models
|
|
10
|
+
- `packages/studio/src/muapi.js` reviewed for submit and poll behavior
|
|
11
|
+
- `packages/studio/src/components/VideoStudio.jsx` reviewed for i2v vs t2v switching
|
|
12
|
+
|
|
13
|
+
## Provider Adapter Assumptions
|
|
14
|
+
|
|
15
|
+
- provider: Muapi
|
|
16
|
+
- auth: `x-api-key`
|
|
17
|
+
- flow: submit -> poll -> result
|
|
18
|
+
|
|
19
|
+
## Execution Steps
|
|
20
|
+
|
|
21
|
+
1. open video studio and load prompt `P01`
|
|
22
|
+
2. submit batch `B01`
|
|
23
|
+
3. poll until complete and review for continuity
|
|
24
|
+
4. move to lip-sync batch after hook clip is approved
|
package/assets/worker-kits/growthub-open-higgsfield-studio-v1/examples/prompt-matrix-sample.md
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
1
|
+
# Growthub Prompt Matrix v1
|
|
2
|
+
|
|
3
|
+
| Prompt ID | Shot / Output | Studio | Model | Base Prompt | Variation Prompt | Negative / Exclusions | Controls | Assets |
|
|
4
|
+
|---|---|---|---|---|---|---|---|---|
|
|
5
|
+
| P01 | Hook reveal | video | Kling-class T2V | premium operator desk, kinetic startup energy, handheld push-in, warm key light, high-contrast branded palette | same beat with slower dolly and cleaner desk styling | warped hands, brand-off colors, text artifacts | 9:16, 5s | logo stills |
|
|
6
|
+
| P02 | Talking operator | lip-sync | Infinite Talk-class I2V | direct-to-camera founder, calm authority, subtle head motion, realistic office background | increase urgency in expression only | rubber mouth, eye drift, over-animated cheeks | 9:16, 720p | portrait + audio |
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
# Growthub Shot Plan v1
|
|
2
|
+
|
|
3
|
+
| Shot ID | Beat | Studio | Model | Assets | Camera Intent | Prompt Key | Ratio / Duration | Passes | Review Note |
|
|
4
|
+
|---|---|---|---|---|---|---|---|---|---|
|
|
5
|
+
| S01 | Hook reveal | video | Kling-class T2V | logo stills | handheld push-in | P01 | 9:16 / 5s | 3 | keep motion tight |
|
|
6
|
+
| S02 | Operator close-up | lip-sync | Infinite Talk-class I2V | portrait + VO | static medium close | P02 | 9:16 / 6s | 2 | check mouth sync |
|
|
7
|
+
| S03 | Hero payoff | cinema | cinema-native | product stills | 50mm dolly-in | P03 | 16:9 / keyframe | 4 | protect palette |
|
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
# Growthub Visual Campaign Brief v1
|
|
2
|
+
|
|
3
|
+
## Project Overview
|
|
4
|
+
|
|
5
|
+
| Field | Value |
|
|
6
|
+
|---|---|
|
|
7
|
+
| Client | Growthub |
|
|
8
|
+
| Project | AI UGC launch teaser |
|
|
9
|
+
| Objective | Produce 3 vertical concept clips and 1 cinematic hero still |
|
|
10
|
+
| Primary platform | Meta / TikTok |
|
|
11
|
+
| Runtime mode | local-fork |
|
|
12
|
+
|
|
13
|
+
## Studio Hypothesis
|
|
14
|
+
|
|
15
|
+
Primary studio: `video` for motion clips.
|
|
16
|
+
Fallback studio: `cinema` for hero still and controlled frame development.
|
|
17
|
+
|
|
18
|
+
## Output Package
|
|
19
|
+
|
|
20
|
+
- 3 motion concepts
|
|
21
|
+
- 1 hero keyframe
|
|
22
|
+
- 1 asset reuse plan
|
|
@@ -0,0 +1,67 @@
|
|
|
1
|
+
# Growthub Agent Worker Kit — Open Higgsfield Studio v1
|
|
2
|
+
|
|
3
|
+
**Kit ID:** `growthub-open-higgsfield-studio-v1`
|
|
4
|
+
**Version:** `1.0.0`
|
|
5
|
+
**Type:** `worker`
|
|
6
|
+
**Execution mode:** `export`
|
|
7
|
+
|
|
8
|
+
---
|
|
9
|
+
|
|
10
|
+
## What this kit does
|
|
11
|
+
|
|
12
|
+
This kit gives an agent a self-contained environment for visual-generation planning and execution support around Open Higgsfield AI.
|
|
13
|
+
|
|
14
|
+
It packages:
|
|
15
|
+
- agent operating instructions
|
|
16
|
+
- a locked methodology
|
|
17
|
+
- fork/runtime assumptions
|
|
18
|
+
- provider adapter notes
|
|
19
|
+
- visual production templates
|
|
20
|
+
- examples
|
|
21
|
+
- output standards
|
|
22
|
+
- contributor metadata
|
|
23
|
+
|
|
24
|
+
The intended operator is an AI visual content operator, cinematic prompt strategist, or browser-assisted creative producer working against a local fork, browser-hosted surface, or desktop app workflow.
|
|
25
|
+
|
|
26
|
+
---
|
|
27
|
+
|
|
28
|
+
## Folder structure
|
|
29
|
+
|
|
30
|
+
```text
|
|
31
|
+
growthub-open-higgsfield-studio-v1/
|
|
32
|
+
├── kit.json
|
|
33
|
+
├── bundles/
|
|
34
|
+
├── workers/
|
|
35
|
+
├── brands/
|
|
36
|
+
├── templates/
|
|
37
|
+
├── examples/
|
|
38
|
+
├── docs/
|
|
39
|
+
├── growthub-meta/
|
|
40
|
+
├── skills.md
|
|
41
|
+
├── output-standards.md
|
|
42
|
+
├── runtime-assumptions.md
|
|
43
|
+
└── validation-checklist.md
|
|
44
|
+
```
|
|
45
|
+
|
|
46
|
+
---
|
|
47
|
+
|
|
48
|
+
## Activation
|
|
49
|
+
|
|
50
|
+
1. Export the kit.
|
|
51
|
+
2. Point the agent working directory at the expanded folder.
|
|
52
|
+
3. The agent reads `workers/open-higgsfield-studio-operator/CLAUDE.md`.
|
|
53
|
+
4. `skills.md` provides the working method for every session.
|
|
54
|
+
|
|
55
|
+
---
|
|
56
|
+
|
|
57
|
+
## Supported output categories
|
|
58
|
+
|
|
59
|
+
- visual campaign brief
|
|
60
|
+
- studio selection brief
|
|
61
|
+
- shot plan
|
|
62
|
+
- prompt matrix
|
|
63
|
+
- generation batch plan
|
|
64
|
+
- model selection recommendation
|
|
65
|
+
- asset reuse/reference plan
|
|
66
|
+
- review notes
|
|
67
|
+
- platform-ready execution handoff
|