pp-stackadapt
The first agent-native StackAdapt CLI: pacing, delivery drift Trigger phrases: `check my stackadapt campaigns`, `which campaigns are underpacing`, `are my stackadapt campaigns on budget`, `where is my ad budget being wasted`, `stackadapt campaign performance`, `use stackadapt`, `run stackadapt`.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/marketing/stackadapt/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
# StackAdapt — Printing Press CLI
## Prerequisites: Install the CLI
This skill drives the `stackadapt-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first:
1. Install via the Printing Press installer. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows:
```bash
npx -y @mvanhorn/printing-press-library install stackadapt --cli-only
```
2. Verify: `stackadapt-pp-cli --version`
3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill.
If the `npx` install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.3 or newer):
```bash
go install github.com/mvanhorn/printing-press-library/library/marketing/stackadapt/cmd/stackadapt-pp-cli@latest
```
If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds.
## When to Use This CLI
Use this CLI to analyze StackAdapt campaigns you already run: check pacing against budget, find under-performing or non-delivering campaigns, spot CTR/spend drift, and pull delivery reports. It is the right tool for read-only reporting and analysis, especially for agents and scripts that want JSON output.
## Anti-triggers
Do not use this CLI for:
- Creating, editing, pausing, or deleting campaigns, ads, or segments — this CLI is read-only; use the StackAdapt UI or the official SDK.
- Uploading audiences or creatives — out of scope.
- Real-time bidding or pixel firing — not what this CLI does.
## Unique Capabilities
These capabilities aren't available in any other tool for this API.
### Pacing & delivery observatory
- **`pacing`** — See which campaigns are under- or over-pacing against their budget, not just current spend.
_Reach for this to catch campaigns that will overspend or underdeliver before the budget cycle ends._
```bash
stackadapt-pp-cli pacing --advertiser adv_123 --agent
```
- **`delivery-drift`** — Track CTR, CPM, and spend drift week-over-week for a campaign and flag when performance degrades.
_Reach for this to catch a slowly degrading campaign before it wastes budget._
```bash
stackadapt-pp-cli delivery-drift --advertiser adv_123 --days 7 --agent
```
### Audience & efficiency
- **`bottleneck`** — Rank the highest-spend campaigns by worst ROAS or CPA, with a reason column.
_Reach for this to find where ad budget is being wasted._
```bash
stackadapt-pp-cli bottleneck --advertiser adv_123 --agent
```
- **`stale-campaigns`** — Find active campaigns with zero delivery in the last N days.
_Reach for this to find live-but-not-delivering campaigns._
```bash
stackadapt-pp-cli stale-campaigns --days 14 --agent
```
## Command Reference
**graphql** — Raw GraphQL query passthrough (advanced; prefer the typed commands)
- `stackadapt-pp-cli graphql` — Execute a raw GraphQL query against the StackAdapt API
**Offline store** — mirror objects locally, then search and query without API calls
- `stackadapt-pp-cli sync` — Pull advertisers, campaigns, campaign-groups, ads, and segments into a local SQLite store (`--resources a,b` to scope, `--limit N` per resource).
- `stackadapt-pp-cli search "<term>"` — Substring-search synced objects by name or any field offline (`--type <resource>` to scope).
- `stackadapt-pp-cli sql "<SELECT ...>"` — Run a read-only SQL query against the store's `resources` table (resource_type, id, name, data JSON, synced_at). Mutating statements are rejected.
- Any list command accepts `--data-source local` (store only) or `--data-source auto` (live, store fallback when the API is unreachable).
### Finding the right command
When you know what you want to do but not which command does it, ask the CLI directly:
```bash
stackadapt-pp-cli which "<capability in your own words>"
```
`which` resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code `0` means at least one match; exit code `2` means no confident match — fall back to `--help` or use a narrower query.
## Recipes
### Find under-pacing campaigns
```bash
stackadapt-pp-cli pacing --advertiser adv_123 --agent
```
Returns each campaign's pace (actual vs expected spend) so you can fix budget delivery before the cycle ends.
### Catch a degrading campaign
```bash
stackadapt-pp-cli delivery-drift --advertiser adv_123 --days 7 --agent
```
Shows CTR/CPM/spend drift week-over-week and flags when performance slips.
### Trim a verbose report for an agent
```bash
stackadapt-pp-cli report campaign-delivery --days 30 --agent --select records.campaign_name,records.metrics.cost,records.metrics.ctr
```
Delivery reports are large; --select with dotted paths returns only the fields an agent needs, saving context.
### Find where budget is wasted
```bash
stackadapt-pp-cli bottleneck --advertiser adv_123 --agent
```
Ranks high-spend campaigns by worst ROAS/CPA with a reason column.
## Auth Setup
This CLI uses the StackAdapt GraphQL API, which needs a GraphQL API token (the legacy REST key will not work). To get set up:
1. Ask your StackAdapt account manager for a GraphQL API token if you do not have one.
2. Export it so the CLI can read it:
`export STACKADAPT_API_TOKEN=your-token`
3. Run `stackadapt-pp-cli doctor` to confirm it connects.
The token is sent as `Authorization: Bearer <token>`. The CLI is read-only and never modifies your campaigns.
## Agent Mode
Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color --yes`.
- **Pipeable** — JSON on stdout, errors on stderr
- **Filterable** — `--select` keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:
```bash
stackadapt-pp-cli graphql --query example-value --agent --select id,name,status
```
- **Previewable** — `--dry-run` shows the request without sending
- **Non-interactive** — never prompts, every input is a flag
- **Read-only** — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests
## Agent Feedback
When you (or the agent) notice something off about this CLI, record it:
```
stackadapt-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
stackadapt-pp-cli feedback --stdin < notes.txt
stackadapt-pp-cli feedback list --json --limit 10
```
Entries are stored locally at `~/.local/share/stackadapt-pp-cli/feedback.jsonl`. They are never POSTed unless `STACKADAPT_FEEDBACK_ENDPOINT` is set AND either `--send` is passed or `STACKADAPT_FEEDBACK_AUTO_SEND=true`. Default behavior is local-only.
Write what *surprised* you, not a bug report. Short, specific, one line: that is the part that compounds.
## Output Delivery
Every command accepts `--deliver <sink>`. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:
| Sink | Effect |
|------|--------|
| `stdout` | Default; write to stdout only |
| `file:<path>` | Atomically write output to `<path>` (tmp + rename) |
| `webhook:<url>` | POST the output body to the URL (`application/json` or `application/x-ndjson` when `--compact`) |
Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.
## Named Profiles
A profile is a Related 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".