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 obeone/claude-skills --skill apple-shortcutsgit clone --depth 1 https://github.com/obeone/claude-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/obeone/claude-skills/apple-shortcuts)<a href="https://agentmods.dev/skills/obeone/claude-skills/apple-shortcuts"><img src="https://agentmods.dev/badge/skills/obeone/claude-skills/apple-shortcuts/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/obeone/claude-skills/apple-shortcuts"><img src="https://agentmods.dev/badge/skills/obeone/claude-skills/apple-shortcuts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00133 | $0.03080 |
| Opus 5 | $0.00067 | $0.01540 |
| Sonnet 5 | $0.00027 | $0.00616 |
| Haiku 4.5 | $0.00013 | $0.00308 |
Grade A, and why
apple-shortcuts 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 12d 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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Shortcuts
Generate plist XML that the Shortcuts app imports. Targets macOS 12+ and iOS 15+. Use this skill for creation, modification, reverse engineering, and reference lookups.
Critical upfront fact: signing
Since iOS 15 / macOS 12, Shortcuts refuses unsigned files. This skill produces plist XML. Delivery to the user requires one of:
- macOS 12+: run
shortcuts sign -i in.plist -o out.shortcut -m anyoneto produce a distributable.shortcut. The user double-clicks or runsopen -a Shortcuts out.shortcut. - macOS, manual route: open the plist in Shortcuts.app (rename to
.shortcutfirst), re-save — Shortcuts re-signs it. - iOS, no signing toolchain: the user must receive a signed
.shortcutvia iCloud share link (https://www.icloud.com/ shortcuts/...), AirDrop, or Messages. Unsigned plist XML cannot be imported on iOS.
State this cost to the user before generating. If they lack macOS, the deliverable is XML plus instructions; full binary signing without macOS is a rabbit hole this skill does not enter.
See gotchas/signing-and-sharing.md for the full story.
Quickstart (three steps)
1. Identify the action set
If you know the action by name but not its identifier:
./tools/find-action-identifier.py "send message"
If you need to discover an unknown third-party action on macOS:
./tools/list-app-intents.py --bundle com.example.app
If you need the full native action catalog:
./tools/list-native-actions.py
2. Generate the plist
Consult references in this order:
references/plist-format.mdfor the envelope and top-level keys.references/variables-and-types.mdfor magic variable wiring.references/actions-native-*.mdfor concrete action schemas.patterns/*.mdif the task matches a known pattern.templates/*.plistas starting points.
Write the plist as XML. Every action dict must carry at minimum
WFWorkflowActionIdentifier and WFWorkflowActionParameters.
What ships with it
38 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- gotchas/common-pitfalls.md 5.6 KB
- gotchas/performance.md 4.6 KB
- gotchas/platform-differences.md 5.2 KB
- gotchas/signing-and-sharing.md 4.6 KB
- patterns/automation-triggers.md 5.1 KB
- patterns/error-handling.md 6.5 KB
- patterns/http-api-calls.md 7.7 KB
- patterns/json-parsing.md 5.2 KB
- patterns/shortcuts-chaining.md 5.0 KB
- patterns/user-input.md 4.5 KB
- references/actions-native-automation.md 8.2 KB
- references/actions-native-communication.md 7.5 KB
- references/actions-native-core.md 17 KB
- references/actions-native-files.md 8.0 KB
- references/actions-native-full-index.md 18 KB
- references/actions-native-web.md 9.6 KB
- references/control-flow.md 11 KB
- references/plist-format.md 15 KB
- references/variables-and-types.md 12 KB
- templates/automation-shortcut.plist 4.8 KB
- templates/http-api-shortcut.plist 6.8 KB
- templates/menu-driven-shortcut.plist 4.8 KB
- templates/minimal-shortcut.plist 2.7 KB
- third-party/a-shell.md 2.2 KB
- third-party/actions-app.md 9.5 KB
- third-party/data-jar.md 3.3 KB
- third-party/discovery-pattern.md 3.7 KB
- third-party/jayson.md 2.1 KB
- third-party/pushcut.md 3.6 KB
- third-party/scriptable.md 2.7 KB
- third-party/toolbox-pro.md 3.3 KB
- tools/diff-actions.py 7.5 KB runs code
- tools/find-action-identifier.py 15 KB runs code
- tools/inspect-shortcut.py 9.3 KB runs code
- tools/list-app-intents.py 8.6 KB runs code
- tools/list-native-actions.py 15 KB runs code
- tools/README.md 7.8 KB
- tools/validate-shortcut.py 16 KB runs code
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.
- 12d ago First seen · 332 lines · 133 tokens per session scan A 7fb9cd3ce670
apple-shortcuts is a skill published in the GitHub repository obeone/claude-skills (3 stars, last pushed 7d ago), licensed MIT. It adds 133 tokens to every session and 3,080 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
offensive-mobile
Mobile (Android + iOS) application penetration testing methodology. Covers static analysis (apktool/jadx for Android, class-dump/Hopper/IDA for iOS), dynamic instrumentation with Frida and Objection, SSL pinning bypass strategies, root/jailbreak detection bypass, deep-link / URL-scheme abuse, exported component…
update-turbo
Update installed Turbo skills from the local repo with a dynamic changelog, conflict resolution for customized skills, and guided user experience. Use when the user asks to "update turbo", "update turbo skills", "reinstall turbo", or "upgrade turbo".
obsidian-bases
An Obsidian skill for creating database-view files. Obsidian is a note-taking app, and a database view shows notes as tables or cards using filters and formulas.
companion-skill
An AI companion skill for developers and office workers during long-running or repetitive tasks. It provides conversation, feedback, generated lifestyle images, and messages sent through Feishu, a workplace collaboration app.
app-store-listing-optimizer
Optimize iOS App Store and Google Play Store listings for maximum discoverability and conversion. Perform competitive keyword research, craft keyword-optimized titles/subtitles/descriptions, design screenshot sequences, and generate A/B test variants. Use when the user has a built app and needs to write or improve…
paywall-pricing-optimizer
Design effective paywalls, structure subscription tiers, and optimize pricing for mobile apps. Covers monetization model selection, paywall screen design, pricing psychology, A/B testing strategy, and RevenueCat/StoreKit/Google Billing integration. Use when the user wants to monetize an app, design a paywall, choose…