content-generator
Generate valid JSON import files for the FSAI applicant portal, custom forms, and email sequences. Use when asked to "generate content", "content generator", "portal json", "sequences json", "forms json", "fsai content", "brand onboarding content", or when working with FSAI brand onboarding.
What this skill does
# FSAI Content Generator
This skill generates valid JSON import files for the FSAI applicant portal, custom forms, and email sequences. The output is consumed by the FSAI backend's content import endpoints.
---
## Guided Workflow
Content generation follows a **three-phase process**. Each phase builds on the previous one because later phases reference content created in earlier phases.
### Phase 1: Custom Forms (`output/forms.json`)
**Why first:** Custom forms must be imported into the platform before the portal can reference them. The portal's `formName` fields must match forms that actually exist.
1. **Setup** — If `metadata/` and `output/` directories don't exist in the current workspace, create them.
2. **Metadata check** — Look for a `metadata/*.json` file. If none found, tell the user:
> "No metadata file found. Export one from the FSAI admin panel and place it in `metadata/`. The file contains brand info, available forms, and uploaded assets needed to generate valid content."
3. **Read metadata** — Examine `metadata.availableForms` to understand what default forms already exist (fields with `dataLocation` are defaults, those without are custom). Identify gaps — what additional questions does this brand need that aren't covered by defaults?
4. **Generate `output/forms.json`** — Create custom forms following the Forms JSON Schema below. Use `useExistingFields` to pull default fields into custom form pages where it makes sense. Never set `dataLocation` on new fields. Skip this phase if the brand only needs the default forms.
5. **Validate** — Copy the validator and run it:
```bash
cp "${CLAUDE_PLUGIN_ROOT}/skills/content-generator/references/validate.ts" ./validate.ts
npx tsx validate.ts
```
6. **Hand off to user** — Present the forms.json and tell them:
> "Import this forms.json via the super admin panel, then **re-export the metadata** so the next phase can reference the newly created forms by name."
**Wait for the user to provide updated metadata before proceeding to Phase 2.**
### Phase 2: Portal (`output/portal.json`)
**Why second:** The portal references forms by name. With the updated metadata (which now includes custom forms from Phase 1), all `formName` references will validate correctly.
1. **Read updated metadata** — The user should have placed a fresh metadata export in `metadata/`. Read it to see all available forms (defaults + newly imported custom forms), assets, and brand context.
2. **Generate `output/portal.json`** — Build the portal sections and steps following the Portal JSON Schema below. Reference both default and custom form names. Use real asset IDs from metadata for video/slide steps.
3. **Validate** — Run `npx tsx validate.ts` and fix any errors.
4. **Present to user** — Show the portal structure. They can import it via the super admin panel.
### Phase 3: Email Sequences (`output/sequences.json`)
**Why last:** Sequences are independent of forms/portal but are typically generated in the same session.
1. **Generate `output/sequences.json`** — Create email sequences following the Sequences JSON Schema below. Use tracking link placeholders and merge tags.
2. **Validate** — Run `npx tsx validate.ts` and fix any errors.
3. **Present to user** — Show the sequences. They can import them via the super admin panel.
### Shortcut: Single-phase generation
If the user only needs one file type (e.g., "just generate the portal"), skip the other phases. If they ask for everything at once and custom forms aren't needed, generate portal and sequences together. The phased workflow only matters when custom forms are involved, because forms must exist in the platform before the portal can reference them.
---
## Portal JSON Schema (`output/portal.json`)
```typescript
interface ImportPortalJson {
/** Main title displayed at the top of the applicant portal */
title: string;
/** Subtitle displayed below the title */
subtitle: string;
/** Ordered list of portal sections */
sections: ImportPortalSectionJson[];
}
interface ImportPortalSectionJson {
/** Section heading */
title: string;
/** Optional section description */
subtitle?: string;
/** Optional emoji shown next to the section title */
emoji?: string;
/** Ordered list of steps within this section */
steps: ImportPortalStepJson[];
}
interface ImportPortalStepJson {
/** Step heading shown to the applicant */
title: string;
/** Step description / instructions */
subtitle: string;
/** The type of interaction this step presents */
action:
| 'video' // Embedded video player (requires assetId referencing a video asset)
| 'form' // Dynamic form (requires formName matching an available form)
| 'slides' // PDF/image slides viewer
| 'studio_slides' // Interactive slide deck from the studio (requires assetId referencing a slide asset)
| 'call' // Schedule a call (Calendly or similar)
| 'sign' // E-signature document
| 'document' // Downloadable document
| 'visit_link' // External link (requires url)
| 'upload' // File upload prompt
| 'invite_team'; // Invite team members step
/** Form name to bind to (required for action: 'form'). Must match a name from metadata availableForms. */
formName?: string | null;
/** Asset UUID to bind to (required for action: 'video' and 'studio_slides'). Must match an assetId from metadata assets. */
assetId?: string;
/** Whether completing this step creates a deal in the pipeline */
createsDeal?: boolean;
/** Whether this step is the FDD (Franchise Disclosure Document) step */
isFdd?: boolean;
/** Whether this step is hidden from the applicant by default */
hidden?: boolean;
/** URL for visit_link steps or fallback video URL */
url?: string | null;
/** Arbitrary JSON data attached to the step (rarely used) */
json?: unknown | null;
}
```
---
## Forms JSON Schema (`output/forms.json`)
```typescript
interface ImportFormsJson {
/** List of custom forms to create */
forms: ImportFormJson[];
}
interface ImportFormJson {
/** Display name of the form */
name: string;
/** Optional description */
description?: string;
/** Which entity type this form collects data for */
appliesTo: 'user' | 'franchisee-org' | 'location';
/** Optional group name — creates or matches an existing form group */
groupName?: string;
/** Ordered list of pages in this form */
pages: ImportFormPageJson[];
}
interface ImportFormPageJson {
/** Page heading */
title: string;
/** Optional page description */
subtitle?: string;
/** New custom fields to create on this page */
fields: ImportFormFieldJson[];
/** Field names from default forms to move into this page */
useExistingFields?: string[];
}
interface ImportFormFieldJson {
/** Internal field name */
name: string;
/** Display text shown to the user */
question: string;
/** Additional help text */
description?: string;
/** Input placeholder text */
placeholder?: string;
/** Field input type */
type: 'short-text' | 'long-text' | 'currency' | 'number' | 'date' | 'url'
| 'email' | 'phone' | 'multiselect' | 'singleselect' | 'boolean' | 'dropdown';
/** Whether the field is required (default false) */
required?: boolean;
/** Options for multiselect, singleselect, and dropdown types */
options?: string[];
}
```
### Form Generation Rules
1. **Never set `dataLocation`** — imported fields are always custom. Only default fields have dataLocation.
2. **Use `useExistingFields`** to reference default fields from metadata by name rather than recreating them. This moves the field from its default form into your custom form.
3. **Check metadata first** — read `metadata.availableForms[].pages[].fields[]` to see what questions are already collected. Don't duplicate them.
4. **Fields with `dataLocation`** in metadata are default fields that map to database columns. ReferencRelated in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".