Latest Agent Skills

Creates or modifies OpenAI Agents SDK tools with Zod parameters, caching, metrics, and agent registration, following established patterns and best practices.

Writes unit, smoke, and e2e tests for AI agents, covering tools, instructions, routing, citations, and guardrails.

Audits and fixes responsive design issues across specified pages or sections, covering breakpoint coverage, layout collapse, touch targets, typography scaling, overflow, and navigation, with mobile-first enforcement for Next.js and Tailwind projects.

Pulls pathway, book, course, article, and content item records from a Supabase database for the alan-hirsch tenant, organizes them by portal, and exports the results as markdown files into a local docs repository.

Audits type-safety documentation against the live codebase, checking for drift from validators and folder layout.

Applies universal TypeScript, JavaScript, React, and Node.js quality conventions for this repo. Use when reviewing or writing TS/TSX, refactoring for clarity, or enforcing naming, immutability, and error-handling patterns.

Audits the course learn experience for section coverage, sidebar rendering, layout, design token compliance, tenant isolation, accessibility, data flow, and component quality. Use when reviewing course UI code quality or diagnosing learn experience issues. Pass a course slug or "all".

Researches authoritative APIs and data sources for a project, producing per-API docs, a data catalog, and an integration blueprint for a React + Supabase + Vercel + AI stack.

Add scroll animations, micro-interactions, or page transitions to a component using GSAP, with reduced-motion support and performance best practices.

Generates or executes a remediation prompt for a book flagged YELLOW or RED by /book-audit, writing a fix-<book-slug>.md that enumerates defects with verbatim PDF source text and verification commands, then optionally executes the fixes to bring the book to GREEN.

Regenerates a specific code layer (schemas, services, routes, hooks, ui) or all layers, then runs the corresponding validation checks.

Converts markdown, text, or HTML files into a styled PDF e-book using WeasyPrint, with support for directories, custom styling, and metadata.

Builds or modifies a RAG pipeline with intent-based routing, vector store search, citation rendering, and book fidelity enforcement.

Build or modify a RAG retrieval pipeline with vector store search, corpus routing, citation rendering, and book fidelity enforcement.

Converts Stitch designs into modular Vite and React components, using MCP networking and AST-based validation to ensure code quality.

Migrates a Stitch screen to production React: fetches and caches wireframes, archives existing pages, converts to shadcn/ui components with semantic tokens, and documents the design system layers.

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

Bootstraps a two-part _docs directory (_build/ for technical docs, _public/ for research and proposals) with a CONSTITUTION.md governing the split, and can audit or migrate an existing structure.

Scaffold a new public page under the (public) route group, following project conventions for server components, tenant config, and shadcn/ui styling.

Creates programmatic videos with React using Remotion, covering compositions, animations, motion graphics, and MP4 rendering, plus walkthrough and content-to-animation workflows.

Creates or modifies agent tools for OpenAI Agents SDK, covering search, analysis, API integration, and database query patterns with caching and metrics.

Scrapes YouTube channel or video metadata via the YouTube Data API, downloads transcripts with yt-dlp, chunks them for search, and upserts results into a database.

Builds detailed voice profiles for characters, narrators, brands, or AI agents, covering diction, syntax, rhythm, worldview, signature patterns, and failure modes, and can reverse-engineer profiles from writing samples or audit existing ones.

Designs and structures the Movemental living SSOT dashboard (HTML/CSS/JS), aligning docs into a docs-first, token-based, agent-friendly dashboard.

Collates a movement leader's voice and theme documents into a professionally styled PDF using WeasyPrint.

Restores and normalizes footnotes/endnotes in books by extracting from PDF/EPUB, matching anchors, staging markers, and compiling to HTML with assertions.

Writes a complete evergreen pillar article in the author's voice, including source research, SEO/GEO architecture, and citations.

Improves typography by fixing font choices, hierarchy, sizing, weight consistency, and readability, making text feel intentional and polished.

Manages career workflows: resume review and scoring, job evaluation with apply recommendations, rubric development, content extraction from conversations, and pipeline quality audits.

Exports a platform feature as a product constitution and data reference, including data model, API contracts, and acceptance criteria, for use in AI prototyping tools.

Safely land one or many topic branches onto main via GitHub PR: inventory, commit leftovers, push, open/update PR, wait for green CI, merge or squash (repo norm), sync local main, then delete local/remote branches only after main contains the work.

Scans repositories for markdown and HTML documentation, classifies files as repo-local or centralizable content, generates an inventory report, and optionally consolidates content into a centralized docs repository.

Audits and iteratively fixes chat-based AI user interfaces against production best practices drawn from Claude, ChatGPT, and modern conversational AI, covering layout, rendering, input, responsiveness, scrolling, streaming, and accessibility.

Audits an article against voice, SEO/GEO, section architecture, citation, and pillar criteria, returning per-criterion scores and a prioritized revision list.

Configures Vite projects, covering vite.config.ts, plugin API, SSR, and Vite 8 Rolldown migration.

Reviews resumes for formatting, design, content, and job-specific fit; scores job postings for fit and interview odds; develops rubrics; extracts content from conversations; and audits the resume generation pipeline.

Audits a page or component against the Digital Curator design spec and movemental conventions, checking visual quality, accessibility, token compliance, and consistency before shipping.

Discovers podcasts via the iTunes Search API, parses RSS feeds, downloads audio, transcribes with OpenAI Whisper, chunks transcripts, and upserts results into a database table.

Plan an evergreen article with pillar assignment, keyword strategy, section outline, source references, internal links, and CTA.

Writes or updates pathway pages for Alan Hirsch's platform, following a 12-section architecture that grounds frameworks in Scripture and story, offers practices, and invites course-based formation.

Writes cornerstone articles in Alan Hirsch's voice with SEO/GEO architecture, corpus research, and citations to drive organic discovery.

Build and manage Trigger.dev v4 background jobs: durable TypeScript tasks, scheduled/cron jobs, waits, Realtime, React hooks, and the Management API, with live docs fetched first.

Reads existing per-leader research files to map co-authorships, endorsements, and organizational ties across movement leaders, producing a cross-leader network graph with clusters, bridges, and isolates.

Audits a color palette for semantic token completeness, WCAG contrast compliance, 60-30-10 distribution, and tonal stacking correctness, with a focus on a light-primary site.

Writes Alan Hirsch's 8-week transformational course content, including video scripts, readings, case studies, reflection questions, and field experiments, in his voice with formation-over-information pedagogy.

Discovers and installs agent skills from the open ecosystem using the Skills CLI, helping users find capabilities for tasks like web development, testing, and design.

Audits any movemental.com page across UI, content, architecture, UX, and conversion, then writes a markdown report and a standalone fix prompt.

Builds or debugs OpenAI Chat Completions, Responses API, and OpenAI Agents SDK patterns, including function calling, structured output, streaming, and handoffs.

Audits icon usage in a codebase, enforcing lucide-react as the single icon library, correct sizes, semantic colors, and accessibility standards, then applies fixes.

Generates a complete Custom GPT knowledge package from the current workspace project, producing 20 markdown documentation files plus optimized custom instructions for a strategic consultant.

Builds or debugs Google Gemini features using @google/generative-ai, covering generateContent, function calling, grounding, multimodal input, and streaming, with guidance for editing src/lib/ai/clients/google.ts.

Builds or debugs Anthropic Claude integrations using @anthropic-ai/sdk, covering messages, tool use, extended thinking, prompt caching, and streaming.

Audits type safety documentation against the live codebase and fixes errors, gaps, or stale information to keep docs authoritative.

Generates illustrations, diagrams, flowcharts, infographics, thumbnails, comics, and icons using multiple rendering backends, with workflows for various visual content types.

Summarizes, condenses, or extracts text, transcripts, and key points from URLs, articles, web pages, PDFs, podcasts, YouTube videos, and local files. Acts as a fallback transcription tool when the user asks to transcribe, digest, recap, or get the gist of a link, video, or document.

Scaffolds or audits Zod-validated environment variables for a Next.js service, including src/lib/env.ts, .env.example, scripts/check-env.ts, and pnpm check:env. Use when adding env vars, auditing process.env usage, or aligning with deployment secrets.

Runs bottom-up type-chain validation across database, hooks, and UI layers, then fixes errors at the failing layer for project health checks before large changes.

Translates a Chinese article into English Markdown, generates bilingual detailed summaries, and writes the results back to LanceDB while preserving structure.

Queues many Codex auth JSON files through a public batch submission API to create pending account-contribution requests for later admin review, with dry-run support and rate-limit handling.

Manage Hugging Face dataset Git repositories with Git Xet/LFS-compatible tracking, including setup, safe snapshot commits, push verification, binary rejection recovery, and README track-rule maintenance.