Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add rshankras/claude-code-apple-skills --skill web-presencegit clone --depth 1 https://github.com/rshankras/claude-code-apple-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rshankras/claude-code-apple-skills/web-presence)<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/web-presence"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/web-presence/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/web-presence"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/web-presence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.01168 |
| Opus 5 | $0.00036 | $0.00584 |
| Sonnet 5 | $0.00014 | $0.00234 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
web-presence scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Presence
Every app has a public web page at apps.apple.com that ranks in Google — most developers never
work that surface. Pair it with an owned landing page and the deal-site ecosystem and the open
web becomes a free acquisition channel that compounds with everything on-store.
When This Skill Activates
- "Make my app findable on Google" / no results for the app's own name
- Building or reviewing a product landing page
- Planning a temporary price drop or sale
- The store-growth audit flags P6.6 (web presence) or P7.5 (deal sites)
Surface 1: The apps.apple.com page is a Google citizen
The store page's Google snippet draws from your app name, subtitle, and description opening
— one more reason the first description paragraph must be benefit-led plain language (see
app-store/app-description-writer).
- ✅ Search your app's name + category terms on Google periodically; if the store page doesn't
rank for your own brand, something is wrong (usually a generic name — see
product/app-namer). - ✅ Ratings, price, and In-App Purchase labels appear in the snippet — per-storefront ratings
mechanics apply (
app-store/ratings-mechanics). - ❌ Treating the store URL as un-shareable internal plumbing. It's often your best-ranking page;
link to it from everywhere (with
?pt=provider token for attribution where you need source data).
Surface 2: An owned landing page + Smart App Banner
One page, one job: convert a web visitor into a store visitor.
-
Structure: name + one-line promise → 2–3 screenshots or a short capture → social proof → a prominent Download on the App Store badge (Apple's official artwork, linked with your attribution token).
-
Smart App Banner — one meta tag; Safari renders a native install/open banner:
<meta name="apple-itunes-app" content="app-id=YOUR_APP_ID, app-argument=https://yourapp.com/from-web">✅ The banner shows Open for installed users — deep-linking into the app, down to specific in-app content via
app-argument— and View for everyone else, opening the App Store in one tap. ❌ Custom "download our app" interstitials — the native banner already does this for free. -
App Store Marketing Tools (tools.applemediaservices.com) — use for referral links, QR codes, and localized badge assets instead of hand-rolling them.
-
The landing page is also where pre-launch waitlists live (TestFlight public link — see
product/beta-testing) and where press/link-in-bio traffic should land, because you can measure it before it enters the store funnel. -
App Clips can front the landing page with an instant experience (
generators/app-clip).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 96 lines · 72 tokens per session scan A bbfcff3e459f
web-presence is a skill published in the GitHub repository rshankras/claude-code-apple-skills (713 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,168 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
electron-desktop
Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.
impact-report-writer
Nonprofit/NGO impact report generation with data visualization suggestions, outcome metrics, narrative structure, and program data presentation. Use when writing impact reports, annual reports, or program evaluation summaries.
investment-memo-generator
Investment memo creation combining financial analysis, document generation, and structured templates. Use when creating investment memos, pitch decks, deal summaries, or investment committee materials.
python-memory-safe-scripts
Memory-safe Python script patterns for long-running processes under systemd MemoryMax constraints. Covers allocator purge (mimalloc/glibc malloctrim), HTTP response lifecycle, DataFrame cleanup, thread-local connection reuse, and periodic GC cadence. Battle-tested through 5 OOM optimization cycles on production GPU…
heic-to-jpeg-bundle
Convert a folder of iPhone HEIC photos to JPEG and package them for sharing — a browsable thumbnail gallery plus an optional password-protected ZIP sized to fit a static host's per-file cap. Uses macOS sips (zero install). Use when someone can't open HEIC (Windows, appraisal/CRM software, older tools), when you need…