appllama-usage
Skill0 starsChanged 3 months agoMITView on GitHub
Use the Appllama MCP (mcp.appllama.io) well — research real top-grossing mobile apps, their screens, flows, and UI elements, then build from what you learn. Load when the Appllama MCP is connected and the task involves building a mobile app or screen, researching app design patterns, studying onboarding/paywall/feature flows, improving an existing screen, or whenever an appllama_* / search_apps / list_app_screens tool is available. Covers the tool map, pagination, expiring media, and the full build-from-research playbooks.
4 other projects use a version of this, 4 of them edited.
Adopted by
Most recently taken up by
- davidanthonyn/claude-skillsedited, first seen Oct 20, 2026
- hsynozdamar-byte/claude-skills-editededited, first seen Oct 17, 2026
- jdodsoncollins/designing-with-aiedited, first seen Sep 14, 2026
- Appllama/appllama-skillsedited, first seen Aug 25, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 4
- Appllama/appllama-skills★ 1.9k97% same
- hsynozdamar-byte/claude-skills-edited★ 494% same
- davidanthonyn/claude-skills★ 097% same
- jdodsoncollins/designing-with-ai★ 097% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repositoryOne other file it gives its agents.
The file
We split this skill into the rules it gives an agent
4 rules. 3 are common, 0 are distinctive, and 1 is very specific to this project.
3
Common
Most of the 4 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 32
If links died mid-task, re-request that page for fresh ones — screen ids are durable, links are not.
- Common: line 34
Ignore the watermark: Every Appllama image and video carries a small Appllama watermark in the top-left corner.
- Very specific: line 38
Pagination is sequential: Every list response carries next_cursor.
- Common: line 86
When you pull screens for study, save them into a local working structure — links expire in about an hour, but your notes and downloads …
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Appllama Usage Skill
Appllama is a library of top-grossing mobile apps — their real screens, flows, and UI patterns, with revenue and download context. The MCP makes it an agent's research floor: not just a research tool, a builder's tool. You study what already wins, then you build something better.
Pair this skill with appllama-app-design-skill for every design/implementation step — this skill tells you what to study; that one tells you how to build.
Ground rules (read first)
- Start with
get_credits— it's free. It tells you the balance, limits, and reset date. Pro includes 1,500 credits a month (they reset in full on the 1st, UTC); every other tool call costs 1 credit. - Go deep. Design language lives in the whole journey, not a sample — walk every screen of the apps that matter for the task, images included. That is exactly what the library is for. The one thing that's against the terms is harvesting: sweeping the catalog to extract the dataset itself rather than to answer a real task. That isn't research, and it's detected server-side.
- Media URLs expire in ~1 hour. Download/view what you study promptly. If links died mid-task, re-request that page for fresh ones — screen ids are durable, links are not.
- Ignore the watermark. Every Appllama image and video carries a small Appllama watermark in the top-left corner. It is provenance, not part of the screen — don't let it skew your read of that corner (status bar, back button, title), and never reproduce it in anything you build.
- Pagination is sequential. Every list response carries
next_cursor; pass it back to continue. You cannot jump to page N — and a cursor only works for the same query that minted it. If a cursor errors, drop it and restart from page one. - If you hit a rate limit, wait it out. The per-minute and per-day limits sit far above real research; on the rare hit, wait the stated time — don't retry-hammer.
- Errors are instructions. Tool errors are written to be acted on (expired cursor → restart; out of credits → tell the user their credits reset on the 1st and they can request more in Settings → Usage).
Tool map
| Tool | What it gives you | Typical use |
get_credits | Balance, limits, reset date. Free. | Session start |
search_apps | 10 apps/page: name, revenue, downloads, rating, launch date, screens count, flow list with screen counts. Natural-language query + filters (revenue/downloads/rating/launch date/price/onboarding steps) + sort + board_id | Find the top apps for a category or need |
get_app | One app in full: ratings breakdown, category rank, IAP pricing, top countries, flows | Decide if an app deserves a deep study |
list_app_screens | 10 screens/page in journey order (welcome → onboarding → paywall → product), each with media URL, flow, UI elements, colors. Filter by flow or section | Walk an app screen by screen |
search_screens | Screens across the whole library. mode="keyword" matches screen names + filters (flow, screen_type, element, app_id); mode="semantic" searches by meaning/visual language | Gather design references for one screen type |
get_screen | One screen in full + up to 5 visually similar screens from other apps. Accepts screen_ref = app_id/screen_id (what appllama.io's "Copy Screen ID" produces) | The user pasted a screen ref; or drill into one reference |
list_flows | The flow taxonomy with screen/app counts | Discover what flows exist for a category |
get_flow_apps | Apps containing a flow, top revenue first | Find the best examples of one flow |
list_ui_elements | ~38 UI-element families with counts (one call) | Vocabulary for element-level research |
get_element_screens | Screens featuring an element family | Study how winners build one component |
list_my_boards | The member's own appllama.io boards (screens / apps / flows) | Find their curation first |
get_board | A board's full contents: screens with media, app profiles, or (app, flow) pairs | When the member curated a board for the task, START from it |
The screen_ref handshake: members can click "Copy Screen ID" on any
screen at appllama.io and paste it to you. It looks like
1393061654/spl_9i075 — feed it straight to
get_screen(screen_ref=...) and you're looking at exactly the screen they
mean, plus its closest siblings across the library.
The playbooks
| Scenario | Reference |
| Build an app from scratch (e.g. "build me a habit tracker") | references/build-from-scratch.md |
| Make an existing screen better | references/improve-a-screen.md |
| Flow & element research; general research method | references/research-methods.md |
Both build playbooks end the same way: the simulator loop from appllama-app-design-skill, repeated until you cannot find a flaw. Research without that loop is decoration.
Local reference boards
When you pull screens for study, save them into a local working structure — links expire in about an hour, but your notes and downloads don't:
research/
<category>/
apps.md # the shortlist: metrics, flows, verdicts
<app-name>/
screens.md # per-screen notes: id, name, flow, elements, colors
img/ # downloaded screens, in journey order
patterns.md # cross-app synthesis: the category's design languageDownload the screens as you study them — synthesis happens with the images side by side, not from metadata. Notes and screen IDs are durable; re-fetch a fresh link from the ID if you ever need the pixels again.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

