Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create and audit Printify products with manifest-driven image uploads, personalization checks, and local proofing. Trigger phrases: `create Printify products`, `upload Printify artwork`, `audit Printify personalization`, `check Printify product drift`, `run Printify`, `use Printify`.
.claude/skills/mvanhorn-pp-printify/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 4% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 119% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 160% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 251% | 0% |
This skill drives the printify-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
$HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:bash npx -y @mvanhorn/printing-press-library install printify --cli-only
printify-pp-cli --version$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 1.26.6 or newer):
bashgo install github.com/mvanhorn/printing-press-library/library/commerce/printify/cmd/printify-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.
Use this CLI for Printify product automation that needs more than raw endpoint calls: image uploads, manifest-driven drafts, personalization field checks, placement proofing, and operational audits. It is especially useful for agents building or verifying POD product batches from local artwork and CSV inputs.
These capabilities aren't available in any other tool for this API.
personalization-audit — Audit a product for documented personalization placeholder fields, missing text/image setup, and unsupported browser-only gaps._Use this before publishing a personalized product or before handing a manifest to another agent._
bash printify-pp-cli personalization-audit --product-file ./examples/sample-product.json --agent
placement-matrix — Show variant, print-area, placeholder, uploaded image, x/y/scale/angle, and missing-placement rows for a product._Use this when an agent must prove artwork placement is consistent across variants._
bash printify-pp-cli placement-matrix --product-file ./examples/sample-product.json --uploads-file ./examples/sample-uploads.json --agent
product-drift — Compare an intended product manifest against the current Printify product payload after create or update._Use this after automation creates a product and before trusting the resulting listing._
bash printify-pp-cli product-drift --product-file ./examples/current-product.json --manifest ./examples/sample-product.json --agent
catalog-margin-matrix — Join catalog variants and shipping data to estimate per-variant cost and margin at a target retail price._Use this before creating a batch when product economics matter more than raw catalog browsing._
bash printify-pp-cli catalog-margin-matrix --variants-file ./examples/sample-variants.json --shipping-file ./examples/sample-shipping.json --target-price 24.99 --agent
personalization-batch — Expand a reusable product manifest and CSV rows into per-product manifests using documented image and text placeholder fields._Use this when an agent needs repeatable personalized product drafts before making API writes._
bash printify-pp-cli personalization-batch --template ./examples/template-product.json --csv ./examples/personalization.csv --out ./examples/generated-manifests --agent
asset-reuse — List uploaded images, where each is used, unused uploads, and products sharing the same artwork._Use this to clean upload libraries or verify that a product batch reuses the expected artwork._
bash printify-pp-cli asset-reuse --products-file ./examples/sample-products.json --uploads-file ./examples/sample-uploads.json --agent
fulfillment-risk — Flag open orders tied to risky product, variant, publish, or shipment states._Use this when an agent needs to find fulfillment problems before customer-service work starts._
bash printify-pp-cli fulfillment-risk --orders-file ./examples/sample-orders.json --products-file ./examples/sample-products.json --agent
catalog — Browse the Printify catalog including blueprints, print providers, product variants, and shipping information. Explore available products and their customization options.
printify-pp-cli catalog retrieve-alist-of-all-print-providers-that-fulfill-orders-for-aspecific-blueprint — Retrieve a list of all print providers that fulfill orders for a specific blueprintprintify-pp-cli catalog retrieve-alist-of-available-print-providers — Retrieves the list of blueprints in the catalog to explore fromprintify-pp-cli catalog retrieve-alist-of-variants-of-ablueprint-from-aspecific-print-provider — Retrieves the list of of variants options for the Print Provider and Blueprint.printify-pp-cli catalog retrieve-aspecific-blueprint — Retrieves the list of blueprints in the catalog to explore fromprintify-pp-cli catalog retrieve-aspecific-print-provider — Retrieves the list of blueprints in the catalog to explore fromprintify-pp-cli catalog retrieve-available-shipping-list-information — Retrieves the list of print providers avilable for the Blueprintprintify-pp-cli catalog retrieve-economy-shipping-method-information — Retrieves the list of print providers available for the Blueprintprintify-pp-cli catalog retrieve-express-shipping-method-information — Retrieves the list of print providers available for the Blueprintprintify-pp-cli catalog retrieve-priority-shipping-method-information — Retrieves the list of print providers available for the Blueprintprintify-pp-cli catalog retrieve-shipping-information — Retrieves the list of print providers avilable for the Blueprintprintify-pp-cli catalog retrieve-specific-shipping-method-information — Retrieves the list of print providers avilable for the Blueprintprintify-pp-cli catalog retrieves-list-of-blueprints-in-the — Retrieves the list of blueprints in the catalog to explore fromshops — Manage Printify shops and shop connections. Retrieve shop information and disconnect shops from your account.
shops-json — Manage shops json
printify-pp-cli shops-json — This will return the list of available merchant shops (IDs and titles)uploads — Upload and manage images and assets. Upload images from URLs or base64-encoded content, retrieve upload information, and archive uploaded images.
printify-pp-cli uploads an-image — Upload an imageprintify-pp-cli uploads retrieve-an-uploaded-image-by-id — Retrieve an uploaded image by iduploads-json — Manage uploads json
printify-pp-cli uploads-json — Retrieve a list of uploaded imagesWhen you know what you want to do but not which command does it, ask the CLI directly:
bashprintify-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.
bashprintify-pp-cli shops-json --agent --select id,title
Use this first so follow-up product and order commands target the right shop without dumping the full shop payload.
bashprintify-pp-cli personalization-batch --template ./examples/template-product.json --csv ./examples/personalization.csv --out ./examples/generated-manifests --agent
Turn a reusable template and row data into deterministic product manifests before any API writes.
bashprintify-pp-cli placement-matrix --product-file ./examples/sample-product.json --uploads-file ./examples/sample-uploads.json --agent --select variant_id,print_area,image_id,x,y,scale,angle
Inspect only the placement columns an agent needs before publishing.
bashprintify-pp-cli product-drift --product-file ./examples/current-product.json --manifest ./examples/sample-product.json --agent
Confirm the remote product still matches the manifest the automation intended.
bashprintify-pp-cli fulfillment-risk --orders-file ./examples/sample-orders.json --products-file ./examples/sample-products.json --agent
Join orders, variants, product state, and shipment state into a single operational risk view.
Printify uses a personal access token as a bearer token. Set PRINTIFY_API_TOKEN in your environment or .env; do not pass the token as a command argument.
Run printify-pp-cli doctor to verify setup.
Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.
--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 printify-pp-cli catalog retrieve-alist-of-all-print-providers-that-fulfill-orders-for-aspecific-blueprint mock-value --agent --select id,name,status
--dry-run shows the request without sending--idempotent only when an already-existing create should count as success, and --ignore-missing only when a missing delete target should count as successCommands that read from the local store or the API wrap output in a provenance envelope:
json{ "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."}, "results": <data> }
Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout.
When you (or the agent) notice something off about this CLI, record it:
printify-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
printify-pp-cli feedback --stdin < notes.txt
printify-pp-cli feedback list --json --limit 10Entries are stored locally at ~/.local/share/printify-pp-cli/feedback.jsonl. They are never POSTed unless PRINTIFY_FEEDBACK_ENDPOINT is set AND either --send is passed or PRINTIFY_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.
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.
A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration - HeyGen's "Beacon" pattern.
printify-pp-cli profile save briefing --json
printify-pp-cli --profile briefing catalog retrieve-alist-of-all-print-providers-that-fulfill-orders-for-aspecific-blueprint mock-value
printify-pp-cli profile list --json
printify-pp-cli profile show briefing
printify-pp-cli profile delete briefing --yesExplicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.
| Code | Meaning | |------|---------| | 0 | Success | | 2 | Usage error (wrong arguments) | | 3 | Resource not found | | 4 | Authentication required | | 5 | API error (upstream issue) | | 7 | Rate limited (wait and retry) | | 10 | Config error |
Parse $ARGUMENTS:
help, or --help → show printify-pp-cli --help outputinstall → ends with mcp → MCP installation; otherwise → see Prerequisites above--agent)bash go install github.com/mvanhorn/printing-press-library/library/other/printify/cmd/printify-pp-mcp@latest
bash claude mcp add printify-pp-mcp -- printify-pp-mcp
claude mcp listwhich printify-pp-cliIf not found, offer to install (see Prerequisites at the top of this skill).
--agent flag:bash printify-pp-cli <command> [subcommand] [args] --agent
printify-pp-cli <command> --help.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 8,915 | 36,773 | +312% | 1 | 1 | 0% | 286 | 3,814 | +1234% | 0 | 0 | — |
case-02 | fail→fail | 5,072 | 6,760 | +33% | 1 | 1 | 0% | 276 | 3,896 | +1312% | 0 | 0 | — |
case-03 | fail→fail | 7,086 | 5,885 | -17% | 1 | 1 | 0% | 676 | 3,778 | +459% | 0 | 0 | — |
case-04 | fail→pass | 19,246 | 2,681 | -86% | 1 | 1 | 0% | 3,567 | 3,727 | +4% | 0 | 0 | — |
case-05 | fail→fail | 9,152 | 5,597 | -39% | 1 | 1 | 0% | 788 | 3,716 | +372% | 0 | 0 | — |
case-06 | fail→pass | 10,386 | 2,849 | -73% | 1 | 1 | 0% | 1,803 | 3,957 | +119% | 0 | 0 | — |
case-07 | fail→pass | 16,754 | 5,704 | -66% | 1 | 1 | 0% | 3,202 | 4,452 | +39% | 0 | 0 | — |
case-08 | fail→pass | 9,205 | 2,821 | -69% | 1 | 1 | 0% | 1,518 | 3,941 | +160% | 0 | 0 | — |
case-09 | fail→pass | 6,358 | 4,324 | -32% | 1 | 1 | 0% | 1,160 | 4,068 | +251% | 0 | 0 | — |
case-10 | fail→fail | 4,178 | 5,596 | +34% | 1 | 1 | 0% | 199 | 3,775 | +1797% | 0 | 0 | — |
case-11 | fail→fail | 13,255 | 5,507 | -58% | 1 | 1 | 0% | 1,865 | 3,803 | +104% | 0 | 0 | — |
case-12 | fail→pass | 10,820 | 4,831 | -55% | 1 | 1 | 0% | 1,801 | 4,070 | +126% | 0 | 0 | — |
case-13 | fail→fail | 4,648 | 6,617 | +42% | 1 | 1 | 0% | 730 | 3,830 | +425% | 0 | 0 | — |
case-14 | fail→fail | 12,370 | 2,829 | -77% | 1 | 1 | 0% | 1,964 | 3,914 | +99% | 0 | 0 | — |
case-15 | fail→fail | 7,746 | 2,986 | -61% | 1 | 1 | 0% | 1,278 | 3,830 | +200% | 0 | 0 | — |
case-16 | fail→fail | 14,415 | 5,180 | -64% | 1 | 1 | 0% | 1,179 | 3,708 | +215% | 0 | 0 | — |
case-17 | fail→fail | 12,093 | 4,953 | -59% | 1 | 1 | 0% | 2,409 | 3,621 | +50% | 0 | 0 | — |
case-18 | fail→pass | 9,889 | 2,797 | -72% | 1 | 1 | 0% | 1,723 | 3,891 | +126% | 0 | 0 | — |
case-19 | fail→pass | 9,791 | 2,337 | -76% | 1 | 1 | 0% | 1,563 | 3,837 | +145% | 0 | 0 | — |
case-20 | fail→fail | 10,363 | 5,102 | -51% | 1 | 1 | 0% | 1,758 | 3,689 | +110% | 0 | 0 | — |
case-21 | pass→pass | 7,065 | 7,055 | -0% | 1 | 1 | 0% | 1,287 | 4,657 | +262% | 0 | 0 | — |
case-22 | pass→pass | 11,163 | 7,879 | -29% | 1 | 1 | 0% | 2,206 | 4,756 | +116% | 0 | 0 | — |
case-23 | pass→pass | 23,525 | 14,792 | -37% | 1 | 1 | 0% | 4,278 | 6,304 | +47% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 13 counted toward the lift figure. The other 10 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +35 percentage points is the difference between those two pass rates over the 13 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.