Latest Agent Skills

Exports a timeline.json as a Premiere Pro editor packet, including FCP7 XML, captions, and media, with verification steps.

Designs an edit blueprint and uncertainty register for video projects, following a narrative loop and schema constraints.

Analyzes source footage to generate structured analysis artifacts including assets, segments, transcripts, and gap reports for video editing workflows.

Selects and curates still photos from ZIPs, folders, or event material, producing album and highlight selections with quality checks and delivery packages.

Orchestrates an end-to-end video production pipeline from source footage to a rough cut or final packaged video, with staged gates, resume support, and progress tracking.

Runs regression evaluations comparing agent edits against human-approved golden projects, and registers new goldens after human approval.

Interviews users to capture creative intent for video projects, producing a structured creative brief and unresolved blockers list before editing begins.

Selects candidate clips from analysis artifacts, applies brief-based must-have and must-avoid rules, and writes a selects_candidates.yaml plan.

Packages an approved video project into a final deliverable, running preflight checks, rendering, and audio finishing.

Crops and reframes event photos to improve composition while preserving the original aspect ratio, with QA contact sheets and delivery folders.

Modifies an existing rough cut by generating a review_patch and re-compiling the timeline, supporting clip shortening, removal, reordering, and audio adjustments.

Build, review, or improve SwiftUI features using the iOS 26+ Liquid Glass API, with guidance on availability, composition, and performance.

Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.

Defines the design tokens, component catalog, and layout patterns for the OpenFoodJournal SwiftUI app, ensuring new views stay visually consistent.

Evaluates iOS, macOS, tvOS, watchOS, and visionOS app code against Apple's App Store Review Guidelines to identify potential rejection issues before submission.

Provides living project knowledge for the OpenFoodJournal iOS app, including architecture, data models, service contracts, and conventions, to be consulted before any work on the project.

Guides the creation of effective agent skills, covering structure, progressive disclosure, and best practices for SKILL.md files and bundled resources.

Creates a technical journey retrospective document from a coding session, capturing decisions, tradeoffs, and debugging moments in a developer blog post style.

Bulk-create or update display names and descriptions for subscriptions, subscription groups, and in-app purchases across all App Store Connect locales using the asc CLI, eliminating manual per-language entry.

Manage TestFlight testers, groups, and build distribution using the asc CLI, including exporting configuration, adding testers, and creating What to Test notes.

Validates App Store submission readiness, submits prepared versions, and monitors review status using current asc commands.

Resize and validate App Store screenshots using current asc size data and macOS sips, preparing them for App Store Connect submission.

Automates translating and syncing App Store metadata (description, keywords, what's new, subtitle) to multiple locales using LLM translation and the asc CLI.

Track build processing, find latest builds, and clean up old builds with asc. Use when managing build retention or waiting on processing.

Automates iOS screenshot capture and upload: builds and launches the app on a simulator with xcodebuild/simctl, drives UI with AXe, frames screenshots with Koubou, and uploads them via the asc CLI.

Creates and renews iOS/macOS signing assets—bundle IDs, capabilities, certificates, and provisioning profiles—via the App Store Connect CLI, including encrypted git-backed team sync.

Syncs App Store metadata with App Store Connect using the canonical asc metadata workflow, including pull, validate, preview, and apply steps for app-info and version localization fields.

Creates a new App Store Connect app record by driving the web UI with browser automation, filling the New App form and verifying via API.

Determines whether an app is ready to submit to the App Store, then drives the release flow with asc: validation, staging, review submission, first-time availability, subscriptions, IAP, Game Center, and App Privacy checks.

Archives, exports, and notarizes macOS apps for distribution outside the App Store using xcodebuild and the asc CLI, including Developer ID signing, notarization submission, and stapling.

Fetches and summarizes TestFlight crash reports, beta feedback, and performance diagnostics using the asc CLI.

Build, archive, export, upload, and manage Xcode version/build numbers with the current asc xcode helpers before App Store Connect upload or submission. Use when creating an IPA or PKG for upload.

Submits or updates a Wall of Apps entry in the App-Store-Connect-CLI repository using the `asc apps wall submit` command, with dry-run preview and confirmation.

Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.

Maps human-friendly names to App Store Connect IDs for apps, builds, versions, groups, and testers using the asc CLI.

Guides the use of the asc CLI for App Store Connect, covering command discovery, canonical verbs, flags, output formats, authentication, and Apple Ads operations.

Runs an offline ASO audit on canonical App Store metadata, then performs keyword gap analysis via Astro MCP to surface optimization opportunities.

Defines, validates, runs, resumes, and audits repo-local multi-step automations using the `asc workflow` CLI and `.asc/workflow.json`, including step outputs and safe release/TestFlight workflows.

Handles all networked operations through a real browser via CDP, including search, page scraping, login-required actions, and social media content extraction.

Automates job search and applications via the JobGPT MCP server, including job matching, auto-apply, tailored resume generation, application tracking, salary insights, and recruiter outreach.

Create, list, and view GitHub issues through a guided workflow that gathers titles, descriptions, and labels before running gh CLI commands.

Generates images from text prompts using Google Gemini's image generation model, saving them as PNG files for use in UI, documentation, and design assets.

Provides HR guidance and templates for hiring, onboarding, performance management, PTO, and employee relations, with compliance and legal disclaimers.

Estimates memory requirements for running Hugging Face models, including optional KV cache, using HTTP range requests without downloading weights.

Connects AI assistants to the Hugging Face Hub via MCP server tools to search models, datasets, Spaces, and papers, retrieve repo details and documentation, run compute jobs, and use Gradio Spaces as AI tools.

Interact with GitHub issues, pull requests, Actions runs, and the REST API using the gh CLI.

Guides users through an interactive interview to complete their .faf file and reach a 100% AI-readiness score, using Claude Code's AskUserQuestion tool.

Designs collaborative AI agent teams with CrewAI, covering agent roles, task decomposition, crew orchestration, process types, memory, and flows.

Design schemas, write TypeScript functions, and manage real-time subscriptions, auth, file storage, scheduling, and deployment for Convex backends.

Formats git commits with Sentry-style conventional commit messages, including type, scope, subject, body, and issue references, and enforces branch safety by creating a feature branch when on main or master.

Optimize content for AI search and LLM citations across AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and similar systems. Use when improving AI visibility, answer engine optimization, or citation readiness.

Guides distinctive, intentional visual design for new or existing UI, covering aesthetic direction, typography, and avoiding templated defaults.

Guides users through a structured three-stage workflow for co-authoring documents, from context gathering to reader testing.

Creates generative art with p5.js, starting from an algorithmic philosophy and expressing it through seeded randomness, noise fields, and particle systems.

Produces academic papers, literature reviews, grant proposals, and clinical reports with LaTeX formatting and verified citations, using research-lookup and parallel-web skills.

Create publication-quality statistical graphics in Python with seaborn, covering relational, distribution, and categorical plots with pandas integration.

Read, write, and modify DICOM medical imaging files, including pixel data extraction, anonymization, format conversion, and compression handling.

Query the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biological data including genes, drugs, diseases, phenotypes, and more.

Queries the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants, returning variants, carriers, and relatedness with allele frequencies and annotations.

Convert chemical structures (SMILES or RDKit molecules) into numerical representations for machine learning, covering 100+ featurizers including ECFP, MACCS, descriptors, and pretrained models like ChemBERTa, with support for QSAR modeling and virtual screening.