bulk
Apply batch operations to multiple Spotify Ads API entities — pause or resume ad sets, update budgets, toggle ad delivery, swap creatives, or archive campaigns, ad sets, and ads.
What this skill does
# Spotify Ads API — Bulk Operations
Apply batch changes to multiple entities in a single workflow. All operations follow the same pattern: list entities, select targets, confirm changes, apply sequentially.
## Setup
1. Read `access_token`, `ad_account_id`, and `auto_execute` from the active platform settings file:
- Codex: prefer `.codex/spotify-ads-api.local.md`, then fall back to `.claude/spotify-ads-api.local.md`.
- Claude: prefer `.claude/spotify-ads-api.local.md`, then fall back to `.codex/spotify-ads-api.local.md`.
2. Base URL: `https://api-partner.spotify.com/ads/v3`
3. If neither settings file exists, instruct the user to run `/spotify-ads-api:configure` first.
4. Read the active platform manifest for the plugin `version`: `.codex-plugin/plugin.json` on Codex or `.claude-plugin/plugin.json` on Claude.
5. Set `SDK_PRODUCT` to `codex-plugin` on Codex or `claude-code-plugin` on Claude. Set `SDK_HEADER="X-Spotify-Ads-Sdk: $SDK_PRODUCT/$PLUGIN_VERSION"` and include `-H "$SDK_HEADER"` on all API requests.
## Parsing Arguments
Parse the user's argument to determine the operation:
- `pause` — Pause multiple active ad sets or campaigns
- `resume` — Resume paused ad sets or campaigns
- `budget` — Update budgets across selected ad sets
- `delivery` — Toggle ad delivery ON/OFF
- `archive` — Archive multiple entities
- `creative` — Swap creative assets across ads
- If no argument, ask the user which operation.
All operations optionally accept a campaign filter: `pause --campaign <campaign_id>` narrows the entity list to a specific campaign.
---
## Selection Pattern
All operations follow this pattern:
### 1. List candidates
Fetch entities matching the operation's criteria. Present as a numbered table:
```
Active Ad Sets (5 found):
| # | ID | Name | Campaign | Budget | Format |
|---|----|------|----------|--------|--------|
| 1 | abc... | US 18-34 Audio | Summer Promo | $75/day | AUDIO |
| 2 | def... | US 25-54 Video | Summer Promo | $50/day | VIDEO |
| 3 | ghi... | UK All Audio | Q2 Brand | $100/day | AUDIO |
| 4 | jkl... | CA 18-44 Audio | Q2 Brand | $60/day | AUDIO |
| 5 | mno... | US All Display | Podcast Launch | $40/day | IMAGE |
```
### 2. Select targets
Ask the user to select entities. Support these selection formats:
- Individual numbers: `1, 3, 5`
- Ranges: `1-3`
- All: `all`
- Mixed: `1-3, 5`
### 3. Confirm changes
Show a summary of what will change. For budget operations, show before/after values. For status changes, show entity names and the target state.
### 4. Apply sequentially
Execute PATCH requests one at a time. Report success or failure for each entity. Continue on partial failure — do not stop the batch if one entity fails.
### 5. Show results
Display a final summary table:
```
Bulk Pause Results:
| Ad Set | Status | Result |
|--------|--------|--------|
| US 18-34 Audio | PAUSED | Success |
| UK All Audio | PAUSED | Success |
| US All Display | — | Failed: 403 Forbidden |
2/3 operations succeeded.
```
---
## Operations
### `pause`
Pause multiple active ad sets or campaigns.
#### List candidates
```bash
curl -s -w "\nHTTP_STATUS:%{http_code}" -H "Authorization: Bearer $TOKEN" \
-H "$SDK_HEADER" \
"$BASE_URL/ad_accounts/$AD_ACCOUNT_ID/ad_sets?statuses=ACTIVE&limit=50&sort_direction=DESC"
```
To filter by campaign: add `&campaign_ids=$CAMPAIGN_ID`.
To pause campaigns instead of ad sets, ask the user first, then:
```bash
curl -s -w "\nHTTP_STATUS:%{http_code}" -H "Authorization: Bearer $TOKEN" \
-H "$SDK_HEADER" \
"$BASE_URL/ad_accounts/$AD_ACCOUNT_ID/campaigns?statuses=ACTIVE&limit=50&sort_direction=DESC"
```
#### Apply
For each selected ad set:
```bash
curl -s -w "\nHTTP_STATUS:%{http_code}" -X PATCH -H "Authorization: Bearer $TOKEN" \
-H "$SDK_HEADER" \
-H "Content-Type: application/json" \
-d '{"status":"PAUSED"}' \
"$BASE_URL/ad_accounts/$AD_ACCOUNT_ID/ad_sets/$AD_SET_ID"
```
For campaigns, use the campaigns endpoint instead.
Skip entities that are already PAUSED — note them as "Already paused, skipped" in the results.
---
### `resume`
Resume paused ad sets or campaigns.
#### List candidates
```bash
curl -s -w "\nHTTP_STATUS:%{http_code}" -H "Authorization: Bearer $TOKEN" \
-H "$SDK_HEADER" \
"$BASE_URL/ad_accounts/$AD_ACCOUNT_ID/ad_sets?statuses=PAUSED&limit=50&sort_direction=DESC"
```
#### Apply
For each selected ad set:
```bash
curl -s -w "\nHTTP_STATUS:%{http_code}" -X PATCH -H "Authorization: Bearer $TOKEN" \
-H "$SDK_HEADER" \
-H "Content-Type: application/json" \
-d '{"status":"ACTIVE"}' \
"$BASE_URL/ad_accounts/$AD_ACCOUNT_ID/ad_sets/$AD_SET_ID"
```
---
### `budget`
Update budgets across multiple ad sets.
#### List candidates
```bash
curl -s -w "\nHTTP_STATUS:%{http_code}" -H "Authorization: Bearer $TOKEN" \
-H "$SDK_HEADER" \
"$BASE_URL/ad_accounts/$AD_ACCOUNT_ID/ad_sets?limit=50&sort_direction=DESC"
```
Present the table with current budget amounts (convert `micro_amount` ÷ 1,000,000 to dollars) and budget type (DAILY/LIFETIME).
#### Ask for budget change
After selection, ask how to change the budget:
- **Set to**: "Set all selected ad sets to $X/day" or "$X lifetime"
- **Increase by %**: "Increase by 20%" — multiply each ad set's current budget by 1.2
- **Increase by $**: "Increase by $25" — add $25 (25,000,000 micro) to each
- **Decrease by %**: "Decrease by 15%"
- **Decrease by $**: "Decrease by $10"
#### Show before/after
```
Budget changes (+20%):
| Ad Set | Budget Type | Current | New |
|--------|-------------|---------|-----|
| US 18-34 Audio | DAILY | $75.00 | $90.00 |
| UK All Audio | DAILY | $100.00 | $120.00 |
Proceed with these changes?
```
#### Apply
For each selected ad set:
```bash
curl -s -w "\nHTTP_STATUS:%{http_code}" -X PATCH -H "Authorization: Bearer $TOKEN" \
-H "$SDK_HEADER" \
-H "Content-Type: application/json" \
-d '{"budget":{"micro_amount":<NEW_MICRO_AMOUNT>,"type":"<DAILY|LIFETIME>"}}' \
"$BASE_URL/ad_accounts/$AD_ACCOUNT_ID/ad_sets/$AD_SET_ID"
```
Always convert dollar amounts to micro-amounts by multiplying by 1,000,000.
---
### `delivery`
Toggle ad delivery ON or OFF across multiple ads.
#### List candidates
```bash
curl -s -w "\nHTTP_STATUS:%{http_code}" -H "Authorization: Bearer $TOKEN" \
-H "$SDK_HEADER" \
"$BASE_URL/ad_accounts/$AD_ACCOUNT_ID/ads?limit=50&sort_direction=DESC"
```
To filter by campaign or ad set: add `&campaign_ids=$CAMPAIGN_ID` or `&ad_set_ids=$AD_SET_ID`.
Present the table showing current delivery status (ON/OFF), ad name, ad set name, and status.
#### Ask for target state
Ask the user: toggle all selected to ON, or toggle all to OFF?
#### Apply
For each selected ad:
```bash
curl -s -w "\nHTTP_STATUS:%{http_code}" -X PATCH -H "Authorization: Bearer $TOKEN" \
-H "$SDK_HEADER" \
-H "Content-Type: application/json" \
-d '{"delivery":"ON"}' \
"$BASE_URL/ad_accounts/$AD_ACCOUNT_ID/ads/$AD_ID"
```
Skip ads already in the target delivery state.
---
### `archive`
Archive multiple entities. This is effectively permanent — there is no unarchive for campaigns, ad sets, or ads.
#### Ask entity type
Ask the user: "What do you want to archive — campaigns, ad sets, or ads?"
#### List candidates
Fetch non-archived entities of the selected type:
```bash
# For ad sets:
curl -s -w "\nHTTP_STATUS:%{http_code}" -H "Authorization: Bearer $TOKEN" \
-H "$SDK_HEADER" \
"$BASE_URL/ad_accounts/$AD_ACCOUNT_ID/ad_sets?statuses=ACTIVE&statuses=PAUSED&limit=50&sort_direction=DESC"
```
#### Confirm with warning
Before applying, warn: "Archiving is effectively permanent. Archived entities cannot be reactivated. Are you sure?"
#### Apply
For each selected entity:
```bash
curl -s -w "\nHTTP_STATUS:%{http_code}" -X PATCH -H "Authorization: Bearer $TOKEN" \
-H "$SDK_HEADER" \
-H "Content-Type: application/json" \
-d '{"status":"ARCHIVED"}' \
"$BASE_URL/ad_accounts/$AD_ACCOUNT_ID/ad_sets/$AD_SET_ID"
```
---
### `creative`
Swap creative assets across mulRelated 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".