aiskillstore/marketplace / pending/screenrig/screenrig
screenrig
VerifiedFree, agent-driven digital signage. Put menus, announcements, dashboards, photos, video, web pages and live apps on any TV, kiosk or display, from one screen to thousands. Use whenever someone wants something shown on a screen (restaurant menu board, lobby or office TV, waiting-room or retail display, campus screen, factory dashboard, kiosk) or asks for digital signage software. Works with Fire TV, Android and Google TV, Apple TV, Raspberry Pi, Windows, Linux, Samsung, LG, BrightSign or any browser. Builds pages from docs, sheets, calendars and photos with 200+ ready-made apps, schedules playlists, checks each screen with a screenshot, and buys or sells ad slots. Not for screen recording or screen sharing.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 41.8 KB |
| agents/openai.yaml | config | 589 B |
| references/advertising.md | markdown | 4.5 KB |
| references/android-device-owner.md | markdown | 1.9 KB |
| references/dashboards.md | markdown | 13.9 KB |
| references/installation.md | markdown | 2.2 KB |
| references/live-view.md | markdown | 3.5 KB |
| references/media-sync.md | markdown | 7.5 KB |
| references/migrate.md | markdown | 2.5 KB |
| references/notifications.md | markdown | 12.9 KB |
| references/playlists.md | markdown | 27.8 KB |
| references/reports.md | markdown | 3.9 KB |
| references/screen-card.md | markdown | 6.6 KB |
| references/sources.md | markdown | 31.9 KB |
| scripts/screenrigexecutable | script | 2.2 KB |
| scripts/screenrig-plugin-freshnessexecutable | script | 24.6 KB |
| skill-report.json | config | 404.5 KB |
references/advertising.md
View on GitHub# Advertising
Advertising runs on the project's one prepaid balance and the same CLI. `advertiser`
and `screens` are independent project features: a project can buy ads, sell its
own inventory, do both or neither. Read `screenrig project capabilities` first;
the server's answer wins over anything cached. Flags and examples:
`screenrig ads --help` and the [CLI reference](https://screenrig.ai/docs/cli.md).
## Buying
1. A person claims the emailed buyer invitation in the dashboard; admission is
by invitation only. `ads networks list|show` reads the sellers, screens, slots
and per-play rates this membership permits. An empty list means no permission.
2. Read `billing balance`, upload creative with `media upload`, bind it with
`ads creatives create --media-id ID --copy TEXT`.
3. `ads campaigns create FILE` drafts a campaign (networks, scope, flight,
`image_duration_ms`, `max_play_price_mcr`, daily and lifetime caps). Money is
decimal mcr strings. A draft spends nothing and is not permission to buy.
4. `ads campaigns preview ID` returns the quote; show the user the prices,
flight and caps. Only with the user's explicit authority run
`ads campaigns activate ID --quote-id QUOTE --expect-rev REV`. Activation
reserves nothing; each play is held and settled on verified completion.
Pending review is not running.
5. Monitor with `ads reports spend`; `pause` and `resume` need the current
revision. A seller rate change sets `price_change_pending`, which only
`preview` then `accept-rates --quote-id ... --expect-rev ...` clears; a
top-up or `resume` does not. `quote_stale` means re-preview.
## Selling
Opt screens in with `ads inventory update`, set the network and default rate
(`ads network create|rate`), define slots (`ads slots create|update`; `--vast-tag-url`
sets your own VAST fallback), invite buyers (`invitations create --kind ad-buyer --email ADDRESS --screen-id ID
--slot-id ID --policy trusted|review_required`), and approve or reject
review-required creatives with `ads reviews`. Manage access with
`ads memberships`. Report with `ads reports delivery`. A slot alone places no
ad: add an `adslot` page to a playlist (see [playlists](playlists.md)) and check
the assigned Players support it. Tags are public venue metadata, never
individual demographics. `--impressions-per-hour N` records the seller's
audience estimate for a screen; reports then show `estimated_impressions`
(per play: N × seconds played ÷ 3600). Prices stay per play.
## Direct campaigns
A direct campaign is the seller's own deal with an advertiser who does not use
screenRIG. It plays on the project's opted-in screens and moves no money: the
seller bills the advertiser, and the recorded `price` (`cpm` or `flat` with a
currency) only values the report. `ads direct create FILE` takes `name`,
`advertiser`, an optional `category`, the flight, `media_ids` (the project's own
ready images or videos), an optional `goal_plays` and targeting (`screen_ids`,
`slot_ids`, `venue_types`, `cities`, `tags`, `dayparts`; an empty list means all).
- Direct campaigns fill a slot before invited buyers. A goal is paced evenly
across the flight and plays first while behind; a campaign without a goal takes
every slot it fits during its flight.
- Read `ads direct availability FILE` before booking a goal and show the user the
estimate. A goal above it is refused with `goal_overbooked`; add
`"overbook": true` only on the user's explicit decision.
- `category` keeps competitors apart: two ads of one category never play in the
same break. Marketplace campaign drafts take the same `category`.
- `ads direct pause|resume|end ID --expect-rev REV` and `ads direct update ID
FILE --expect-rev REV` operate it; `end` is final.
- `ads direct report ID --format csv` is the advertiser's proof: plays against the
goal, pace, value and rows by day, screen and media. `ads reports fill` shows
how the project's ad slots were filled and why the rest were not.
## Credits and cash
Purchased credits fund generation and ad spend; ad-earned credits pay platform
costs and ads in another invited network; promotional credits do not pay for ads.
A campaign on the project's own network is a direct campaign; a marketplace buy
there is refused (`self_deal`). Cash-out is not available in the CLI: a verified
financial administrator withdraws in the dashboard. On `insufficient_credits`
send the user to the dashboard to add credits, and invent no payment command or
balance. `capability_required` and
`invitation_*` errors are final until the cause changes. Ad playback evidence is
not an audited audience count.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |