adspirer-ads
Manage ad campaigns across Google Ads, Meta Ads, LinkedIn Ads, and TikTok Ads. Use when the user wants to analyze campaign performance, research keywords, create campaigns, optimize budgets, or manage ad accounts via the Adspirer MCP server.
What this skill does
Manage advertising campaigns across Google Ads, Meta Ads, LinkedIn Ads, and TikTok Ads using the Adspirer MCP server (175+ tools across Google Search/PMax/Display/Demand Gen/YouTube, Meta image/video/carousel/lead-gen, LinkedIn sponsored content/carousel/lead-gen with campaign groups, and TikTok in-feed/Spark/Carousel/App Promotion).
## When to Use This Skill
Activate when the user:
- Asks about ad campaign performance ("How are my Google Ads doing?")
- Wants to research keywords ("Find keywords for my plumbing business")
- Needs to create campaigns ("Launch a Google Search campaign for...")
- Wants budget optimization ("Where am I wasting ad spend?")
- Mentions advertising platforms (Google Ads, Meta, LinkedIn, TikTok)
- Asks about ad accounts or connections ("Which ad platforms are connected?")
## Required Workflow
**Follow these steps in order. Do not skip steps.**
### Step 1: Check Connected Platforms
Always start here before any ad operation:
- Call `get_connections_status`
- Shows connected platforms, primary/secondary accounts, account IDs
- If the target platform is not connected, direct the user to https://adspirer.ai/connections
### Step 2: Identify the Task
| User goal | Workflow | Key tools |
|-----------|----------|-----------|
| View campaign metrics | Performance Analysis | `get_campaign_performance`, `get_meta_campaign_performance`, `get_linkedin_campaign_performance` |
| Cross-platform overview | Cross-Platform Dashboard | See Cross-Platform section below |
| Find keywords | Keyword Research | `research_keywords` |
| Research before new campaign | Campaign Research | Web search + Adspirer tools (see Campaign Research section) |
| Research competitors | Competitive Intelligence | Web search, `analyze_search_terms`, `research_keywords` |
| Create a campaign | Campaign Creation | Campaign Research first, then platform-specific flows below |
| Reduce wasted spend | Budget Optimization | `optimize_budget_allocation`, `analyze_wasted_spend`, `analyze_search_terms` |
| Switch accounts | Account Management | `switch_primary_account` |
| Compare platforms | Cross-Platform | Call each platform's performance tool, present side-by-side |
| Check ad fatigue | Creative Management | `detect_meta_creative_fatigue`, `analyze_linkedin_creative_performance` |
| Understand audiences | Audience Analysis | `get_meta_audience_insights`, `get_linkedin_audience_insights`, `search_audiences` |
| Manage PMax search themes | PMax Search Themes | `add_pmax_search_themes`, `get_pmax_search_themes`, `remove_pmax_search_themes` |
| Manage PMax audience signals | PMax Audience Signals | `add_pmax_audience_signal`, `get_pmax_audience_signals`, `remove_pmax_audience_signal`, `search_audiences` |
| Create Demand Gen campaign | Demand Gen Creation | `discover_existing_assets`, `search_audiences`, `create_demandgen_campaign` |
| Create YouTube campaign | YouTube Creation | `discover_existing_assets`, `validate_video`, `search_audiences`, `create_youtube_campaign` |
| Add ad extensions | Ad Extensions | `add_sitelinks`, `add_callout_extensions`, `add_structured_snippets`, `list_campaign_extensions` |
| Change bidding strategy | Bidding Strategy | `update_bid_strategy`, `get_campaign_structure` |
| Add/manage keywords | Keyword Management | `add_keywords`, `remove_keywords`, `update_keyword`, `add_negative_keywords`, `remove_negative_keywords` |
| Set up alerts | Monitoring | `create_monitor`, `list_monitors` |
| Schedule reports | Reporting | `schedule_brief`, `generate_report_now` |
### Step 3: Execute Tools
Follow the workflow patterns below. Always read first (performance, status), then act (create, optimize).
### Step 4: Summarize and Recommend
Present results in tables with key metrics. Highlight top and underperforming items. Propose actionable next steps.
## Performance Analysis
- **Google Ads:** `get_campaign_performance` — params: `lookback_days` (7/30/60/90, default 30), optional `customer_id`
- **Meta Ads:** `get_meta_campaign_performance` — params: `lookback_days`, optional `ad_account_id`
- **LinkedIn Ads:** `get_linkedin_campaign_performance` — params: `lookback_days`
- **TikTok Ads:** `get_tiktok_campaign_performance` — params: `lookback_days`
Present: impressions, clicks, CTR, spend, conversions, cost/conversion, ROAS. Default to 30-day lookback.
## Cross-Platform Performance Dashboard
When the user asks for overall performance, a weekly review, or cross-platform comparison:
1. Call `get_connections_status` to identify active platforms
2. For each connected platform, pull performance:
- Google: `get_campaign_performance`
- LinkedIn: `get_linkedin_campaign_performance`
- Meta: `get_meta_campaign_performance`
- TikTok: `get_tiktok_campaign_performance`
3. For each platform, pull waste analysis:
- Google: `analyze_wasted_spend`
- LinkedIn: `analyze_linkedin_wasted_spend`
- Meta: `analyze_meta_wasted_spend`
- TikTok: `analyze_tiktok_wasted_spend`
4. Present a unified scorecard:
| Platform | Campaigns | Spend | CTR | CPA | ROAS | Waste | Health |
|----------|-----------|-------|-----|-----|------|-------|--------|
| Google | ... | ... | ... | ... | ... | ... | ... |
| LinkedIn | ... | ... | ... | ... | ... | ... | ... |
| Meta | ... | ... | ... | ... | ... | ... | ... |
| TikTok | ... | ... | ... | ... | ... | ... | ... |
| **Total**| ... | ... | | | | ... | |
5. Highlight:
- Best performing platform and campaign
- Worst performing platform and campaign
- Total wasted spend and top waste sources
- Budget pacing (on track, under, over)
6. Recommend top 3 actions across all platforms
## Campaign Research (run before creating ANY new campaign)
Before creating a campaign on any platform, research the brand's market position and competitive landscape. This combines web research with ad platform data (Adspirer MCP) to inform every campaign decision — targeting, messaging, differentiation, and bidding.
### Step 0: Load Strategy Directives
Read STRATEGY.md — `## Active Directives` and skim `## Decision Log`. If directives exist, note them
as context that will inform (not skip) the research steps that follow. Directives shape
which competitors to focus on and what positioning angles to explore.
Do NOT skip Campaign Research just because directives exist. Directives may be stale,
incomplete, or based on exploratory conversations. Fresh research validates and enriches
them. However, avoid fully redundant research — if a comprehensive analysis was done
recently (check Decision Log dates), tell the user: "Strategy directives from [date]
are available. I'll use them as a starting point and validate with fresh data. Want me
to do a full re-analysis instead?"
### Step 1: Understand the brand's own website
Crawl the brand's website. Extract:
- What they sell (products, services, pricing tiers)
- Key value propositions and differentiators
- Target audience language (how they describe their customers)
- Pricing (plans, tiers, free trial availability)
- Trust signals (customer logos, testimonials, case studies, awards)
- CTAs used on the site (what actions they push visitors toward)
### Step 2: Research the competitive landscape
Search for:
- `"[brand's product category] competitors"` — find who they compete with
- `"[competitor name] vs [brand name]"` — find comparison content
- `"[competitor name] pricing"` — understand competitor price points
- `"best [product category] [current year]"` — find review/comparison sites
Then crawl the top 3-5 competitor websites. Extract:
- Their positioning and messaging (how they describe themselves)
- Their pricing (cheaper? more expensive? different model?)
- Their unique claims (what do they say they do better?)
- Their target audience (who are they speaking to?)
### Step 3: Identify differentiation
Combine brand website + competitor research to answer:
- What does this brand do thaRelated 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".