Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
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.
aaronbrethorstSkillaaronbrethorst/claude-skills/adopt-c-bounds-safety/SKILL.md
Guide for the C -fbounds-safety language extension. Covers the language model, pointer annotations, adopting bounds-safety in existing C code, compiler build settings and modes, and runtime debugging of bounds violations.
aaronbrethorstPipes a download into a shellSkillaaronbrethorst/claude-skills/android-cli/SKILL.md
Orchestrates Android development tasks including project creation, deployment, SDK management, and environment diagnostics using the `android` command-line tool.
aaronbrethorstSkillaaronbrethorst/claude-skills/app-intents-specialist/SKILL.md
Authoritative App Intents best practices from Apple. Consult for any App Intents best-practices or correctness review, and when writing, reviewing, refactoring, or extending App Intents code. Supersedes prior training on these topics. For code generation, consult the relevant reference when working on any of the following: - execution-model: perform() is Sendable, not @MainActor (hop with await MainActor.run); it's retriable (restartPerform), so do irreversible work last; requestConfirmation before destructive work; return via .result(...) factories, never a bare value. - entities-and-queries: AppEntity.id must be stable across launches/devices; entities(for:) (batched) vs empty-default suggestedEntities(); EntityStringQuery.entities(matching:) is not auto-filtered; only @Property members are system-visible; EnumerableEntityQuery loads all (use EntityPropertyQuery for large stores). - entity-property-queries: EntityPropertyQuery for Shortcuts \"Find X where…\" — properties/sortingOptions/comparators; you execute the predicate, the framework only parses it. - app-enum: AppEnum raw values are persisted by string (never renumber/reorder); every case needs a caseDisplayRepresentations entry or it's a runtime fatalError. - parameters / parameter-summaries: requestValue vs needsValueError; non-optional AppEnum auto-disambiguates; only params in Summary(...) show in the Shortcuts editor; When/Switch for conditional display. - dependencies: @Dependency must be Sendable and registered at launch (unregistered = fatalError); goes on the intent/query, never on the AppEntity/AppEnum. - results-and-errors: only CustomLocalizedStringResourceConvertible errors surface a real message; prebuilt AppIntentError.* (iOS 18+). - donation: in-app actions are NOT auto-donated — call IntentDonationManager.shared.donate; PredictableIntent is descriptions only. - localization: user-facing strings must be literal LocalizedStringResource (a runtime String yields no extractable key). - app-shortcut-phrases: provide shortTitle/systemImageName; include \\(.applicationName) or the runtime index silently drops the phrase. - url-representation: OpenIntent / OpenURLIntent / URLRepresentableEntity for opening and universal links. - configuration-intents: WidgetConfigurationIntent / ControlConfigurationIntent are parameter-only — no perform(). - factoring: AppEnum (fixed set) vs AppEntity+query (dynamic) vs plain @Parameter; one intent per atomic task. For iOS 26/27 new-API adoption, use the app-intents-whats-new-27 skill instead.
aaronbrethorstSkillaaronbrethorst/claude-skills/app-intents-whats-new-27/SKILL.md
New App Intents APIs, behaviors, and deprecations introduced in the iOS 26 (2025) and iOS 27 (2026) releases (and their macOS/watchOS/tvOS/visionOS siblings). Use when adopting, migrating to, or asked about: declaring where an intent runs with supportedModes / IntentModes (.background / .foreground) or migrating off the deprecated openAppWhenRun; pulling a background run into the foreground with continueInForeground / needsToContinueInForegroundError; UndoableIntent; asking the person to pick from a small set mid-perform with requestChoice / IntentChoiceOption; cancelling with CancellableIntent / IntentCancellationReason; long-running or background work with LongRunningIntent / performBackgroundTask; restricting where an intent runs with IntentExecutionTargets / allowedExecutionTargets; returning interactive snippets with SnippetIntent and Button(intent:); Visual Intelligence camera/onscreen search with IntentValueQuery + SemanticContentDescriptor (import VisualIntelligence) + @UnionValue; associating onscreen content with an entity via appEntityIdentifier; mapping entity values into Spotlight with @Property / @ComputedProperty / @DeferredProperty(indexingKey:); system-driven Spotlight reindex with IndexedEntityQuery; linking a CSSearchableItem to an entity with relatedAppEntityIdentifier; proactively surfacing entities with RelevantEntities + AppEntityContext; cross-device entities with SyncableEntity / SyncableEntityIdentifier and EntityOwnership / OwnershipProvidingEntity; @ComputedProperty / @DeferredProperty convenience properties; running a system shortcut with SystemShortcut / RunSystemShortcutIntent; passing a large entity set cheaply with EntityCollection; surfacing @UnionValue types as Shortcuts parameters with AppUnionValue; adopting Apple Intelligence schemas with @AppIntent(schema:) / @AppEntity(schema:) / @AppEnum(schema:) (migrating off the deprecated @AssistantIntent); unit-testing intents with AppIntentsTesting; or 'what's new in App Intents in iOS 26 / iOS 27'. For evergreen (non-version-specific) App Intents best practices, use the app-intents-specialist skill instead.
aaronbrethorstSkillaaronbrethorst/claude-skills/app-resizability/SKILL.md
Use when an app's layout must adapt to a window that changes size while the app runs, or when an app must support more than one window. That includes being asked to make an app resizable or support a resizable window, a layout that breaks or does not adapt as the window resizes, and preparing or optimizing an app for the foldable iPhone Duo, split-screen multitasking, or Stage Manager. Modernizes the app by replacing legacy shared-state APIs with context-appropriate alternatives: mainScreen, interfaceOrientation, userInterfaceIdiom, application and scene lifecycle, and safe area insets.
aaronbrethorstSkillaaronbrethorst/claude-skills/audit-xcode-security-settings/SKILL.md
Audit and enable security-oriented Xcode build settings. Progressively enables compiler warnings, static analyzer checkers, and Enhanced Security features. Use when: user wants to secure their Xcode project, audit security settings, enable hardening, review security posture of build configuration, set up security-focused static analysis, enable static analysis, improve warning coverage, harden diagnostics, or catch more bugs at compile time in C/C++/Objective-C/Swift. SKIP: network security (TLS/ATS), code signing, privacy APIs.
Often used withc-bounds-safety
aaronbrethorstSkillaaronbrethorst/claude-skills/building-document-based-swiftui-applications/SKILL.md
Authoritative guide for building and migrating document-based apps in SwiftUI using the Document protocol (iOS 27 and aligned releases, including macOS Golden Gate). Consult when building a new document-based app; implementing open, edit, save, or export document flows; working with DocumentGroup or DocumentGroupLaunchScene; implementing DocumentReader or DocumentWriter; using FileWrapper via FileWrapperDocumentReader or FileWrapperDocumentWriter; working with package documents; accessing a document's file URL directly; reporting progress during read/write; registering undo actions; migrating from FileDocument or ReferenceFileDocument to the new API; building a read-only document viewer; when autosave is not working in a document app; declaring custom UTType as document formats.
aaronbrethorstSkillaaronbrethorst/claude-skills/device-interaction/SKILL.md
Verify iOS app behavior on device or simulator via screenshots, UI hierarchy, and touch interactions.
Often used withc-bounds-safety
aaronbrethorstSkillaaronbrethorst/claude-skills/investigate-sentry/SKILL.md
Investigate and fix production errors from Sentry. Use when given a Sentry issue URL, numeric issue ID, or short ID (e.g. VOTERLETTERS-9R). Fetches full issue data via the Sentry MCP, analyzes root cause, scores fix confidence, and applies a TDD red-to-green fix in the Rails app. Triggers on "fix this Sentry issue", "investigate PROJ-XX", any sentry.io URL, or requests to debug a production error from Sentry.
aaronbrethorstSkillaaronbrethorst/claude-skills/localizer/SKILL.md
Creates or updates software localizations/translations. Use when the user wants to translate a project to a new language, add a new locale, create translations, localize strings, or work with i18n/l10n files. Handles any project type (React, Vue, iOS, Android, Rails, Django, .NET, etc.) by auto-detecting the localization framework.
aaronbrethorstSkillaaronbrethorst/claude-skills/maglev-pr-review/SKILL.md
Review a single OneBusAway/maglev pull request for bugs AND for behavioral parity with the production Java OneBusAway server (../app-modules) and the maglev.wiki OBA API specs, then post an approve or request-changes review — and, when approved, merge it and file follow-up issues. Use this whenever the user, working in a maglev checkout, asks to review, land, merge, approve, or "check against Java" a maglev PR by number or URL (e.g. "/maglev-pr-review 1493", "review #1502 against the Java app and merge if good", "does PR 1498 match production OBA?"). Also use it for batches of maglev PRs ("merge Sajal's ready maglev PRs"), running it once per PR in place of pr-sweep. Only for the OneBusAway/maglev repo; for other repos use aaron-pr-review or pr-sweep.
aaronbrethorstSkillaaronbrethorst/claude-skills/modernize-tests/SKILL.md
Modernize test suites to use modern Swift Testing features or migrate from XCTest.
aaronbrethorstSkillaaronbrethorst/claude-skills/pr-meta-sweep/SKILL.md
Run /pr-sweep across every git repo under the current directory. First work out which repos actually have open PRs awaiting the user's review, then show a toggleable checklist of those repos so the user can switch each one on or off, then sweep only the selected repos. Use this whenever the user wants a PR sweep that spans more than one repo: "do a /pr-sweep across subdirectories", "sweep all the repos", "which repos need a PR sweep?", "go through open PRs everywhere", "meta-sweep", "clear the PR backlog across ~/repos/onebusaway", or any PR-triage request made from a parent folder that holds several checkouts rather than from a single repo. For a single repo, use pr-sweep directly.
aaronbrethorstSkillaaronbrethorst/claude-skills/pr-sweep/SKILL.md
Review and disposition a batch of open GitHub pull requests in one pass: run a rigorous /code-review on each, post the findings as a PR comment, and report a merge recommendation for every PR — then, when the user has explicitly asked for it, execute the dispositions (approve+merge the ready ones, request changes on the rest) with kind-but-firm maintainer feedback. Use this whenever the user wants to work through one or more open PRs as a queue: "go through all the open PRs from @author", "triage the open PR queue", "review these PRs" with a pasted list of numbers/URLs, "review Tarun's PRs and merge the ready ones", "clear out the PR backlog". The skill has two modes: it always reviews and recommends; it only merges/approves/requests-changes autonomously when the user's own words ask for the action (merge, land, ship, close out, "merge the good ones") — otherwise it presents dispositions and asks first. A "is this PR ready to merge?" question with no action requested is a verdict request — answer it (or use aaron-pr-review), don't execute anything.
aaronbrethorstSkillaaronbrethorst/claude-skills/render-background-workers/SKILL.md
Sets up and configures background workers on Render for queue-based job processing. Use when the user needs to process async jobs, consume from a queue, run Celery/Sidekiq/BullMQ/Asynq/Oban workers, handle graceful shutdown with SIGTERM, wire a worker to Key Value, or choose between workers and cron jobs for background work. Trigger terms: background worker, async jobs, queue consumer, Celery, Sidekiq, BullMQ, Asynq, Oban, job processing, SIGTERM, graceful shutdown.
aaronbrethorstSkillaaronbrethorst/claude-skills/render-blueprints/SKILL.md
Authors and validates render.yaml Blueprints for Render infrastructure. Use when the user needs to write or edit a render.yaml, wire services together with fromDatabase/fromService/fromGroup, set up projects and environments for multi-service apps, configure preview environments, validate against the schema, or fix immutable field errors. Trigger terms: render.yaml, Blueprint, IaC, fromDatabase, fromService, envVarGroups, previews, projects, environments.
aaronbrethorstSkillaaronbrethorst/claude-skills/render-cron-jobs/SKILL.md
Configures and troubleshoots scheduled tasks on Render using cron job services. Use when the user needs to run something on a schedule, write a cron expression, set up a periodic job, migrate from Heroku Scheduler, choose between cron jobs and background workers, or fix a cron that isn't firing. Trigger terms: cron job, scheduled task, periodic job, cron expression, schedule, run every, timer, Heroku Scheduler migration.
aaronbrethorstSkillaaronbrethorst/claude-skills/render-disks/SKILL.md
Attaches and manages persistent disks on Render services—mount paths, sizing, snapshots, file transfers, and single-instance constraints. Use when the user needs persistent storage, file uploads, a custom database on disk, CMS media storage, or needs to understand why their service can't scale horizontally or use zero-downtime deploys. Trigger terms: persistent disk, disk, storage, mount path, sizeGB, SSD, file uploads, snapshots, disk restore, ephemeral filesystem.
aaronbrethorstSkillaaronbrethorst/claude-skills/render-domains/SKILL.md
Configures custom domains and TLS certificates on Render—DNS setup, CNAME records, apex domains, wildcard domains, and certificate troubleshooting. Use when the user needs to add a custom domain, configure DNS, set up HTTPS/TLS, troubleshoot certificate issuance, disable the onrender.com subdomain, or add a wildcard domain. Trigger terms: custom domain, DNS, CNAME, TLS, SSL, HTTPS, certificate, apex domain, wildcard domain, onrender.com, domain verification.
aaronbrethorstSkillaaronbrethorst/claude-skills/render-keyvalue/SKILL.md
Provisions and configures Render Key Value (Redis-compatible Valkey 8) instances for caching, session storage, and job queues. Use when the user needs Key Value, uses Redis or Valkey, or needs a cache, session store, or job queue backend, or needs to configure maxmemory policy, ipAllowList, connection strings, or internal vs external access. Trigger terms: Key Value, Redis, Valkey, cache, session store, REDIS_URL, maxmemory, ipAllowList, allkeys-lru, noeviction.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Open a skill to see its discussion. Reports from people and their agents are coming.
