CatCorner22

@catcorner22 source repo

187 skills
0 followers
6 hours ago last updated

▌
Nyx · catcorner22 bundle
Canonical character bible for Nyx, a recurring original character in this project — appearance, physique, tattoo map, personality, voice, wardrobe, scene variants, and image-generation prompt templates with reference sheets. Use when writing Nyx's dialogue or scenes, generating or reviewing her reference art, keeping a depiction consistent with the bible, or designing UI around her. Scope boundary: this is project reference material, not a capability skill — it carries no general guidance on image tooling, design systems, or coding, and must not fire on unrelated character, art, or UI work. Trigger only when Nyx is named.

0 installs
▌
AI Sdk · catcorner22 bundle
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.

0 installs
▌
Nextjs · catcorner22 bundle
Next.js App Router expert guidance. Use when building, debugging, or architecting Next.js applications — routing, Server Components, Server Actions, Cache Components, layouts, middleware/proxy, data fetching, rendering strategies, and deployment on Vercel.

0 installs
▌
Shadcn · catcorner22
shadcn/ui expert guidance — CLI, component installation, composition patterns, custom registries, theming, Tailwind CSS integration, and high-quality interface design. Use when initializing shadcn, adding components, composing product UI, building custom registries, configuring themes, or troubleshooting component issues.

0 installs
▌
V0 · catcorner22
Vercel's v0 app builder — taking v0 output into a production repo, and driving the v0 Platform API (v2, api.v0.dev/v2) from code with the `v0` npm SDK. Use when the user names v0, v0.dev, v0.app, the v0 Platform API, a v0 chat/preview/deploy URL, `V0_API_KEY`, `@v0-sdk/*`, or is reviewing/merging code described as generated by v0. Scope boundary: this skill owns the v0-specific workflow — the import seam, the Platform API surface, and v0-vs-repo drift. It does not own the topics of the code v0 emits: shadcn/ui and registries → shadcn, App Router and Server Components → nextjs, render performance → react-best-practices, model routing → ai-gateway, repo/env provisioning → bootstrap. Do not claim a request merely because the project is Next.js, uses shadcn/ui, or is deployed on Vercel.

0 installs
▌
Chat Sdk · catcorner22 bundle
Vercel Chat SDK expert guidance. Use when building multi-platform chat bots — Slack, Telegram, Microsoft Teams, Discord, Google Chat, GitHub, Linear — with a single codebase. Covers the Chat class, adapters, threads, messages, cards, modals, streaming, state management, and webhook setup.

0 installs
▌
Env Vars · catcorner22
Vercel environment variable expert guidance. Use when working with .env files, vercel env commands, OIDC tokens, or managing environment-specific configuration.

0 installs
▌
Workflow · catcorner22 bundle
Vercel Workflow SDK expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause/resume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.

0 installs
▌
Bootstrap · catcorner22
Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations). Use when setting up or repairing a repository so linking, environment provisioning, env pulls, and first-run db/dev commands happen in the correct safe order.

0 installs
▌
Turbopack · catcorner22
Turbopack expert guidance. Use when configuring the Next.js bundler, optimizing HMR, debugging build issues, or understanding the Turbopack vs Webpack differences.

0 installs
▌
Supabase · catcorner22 bundle
Canonical source for Supabase development work. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector). For provisioning Supabase on Vercel or comparing storage providers, use vercel-storage / marketplace instead; for general (non-Supabase) Postgres query and index tuning, use supabase-postgres-best-practices.

0 installs
▌
AI Gateway · catcorner22
Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.

0 installs
▌
Next Forge · catcorner22 bundle
next-forge expert guidance — production-grade Turborepo monorepo SaaS starter by Vercel. Use when working in a next-forge project, scaffolding with `npx next-forge init`, or editing @repo/* workspace packages.

0 installs
▌
Vercel CLI · catcorner22 bundle
Vercel CLI expert guidance. Use when deploying, managing environment variables, linking projects, viewing logs, querying metrics, managing domains, or interacting with the Vercel platform from the command line.

0 installs
▌
Hf CLI · catcorner22
Hugging Face Hub CLI (`hf`) for auth, repos, models, datasets, spaces, papers, jobs, buckets, cache, and endpoints. Use when the user needs a terminal/CLI workflow on the Hub (`hf`, `huggingface-cli`). Prefer specialized skills (huggingface-spaces, huggingface-llm-trainer, huggingface-papers, huggingface-best) for task-specific guidance. Do not use this skill for generic AI/ML questions that are not Hub CLI operations.

0 installs
▌
Hf MCP · catcorner22
Use Hugging Face Hub via MCP server tools when the Huggingface-skills (or equivalent) MCP namespace is connected. Search models, datasets, Spaces, and papers; inspect repos; invoke Gradio Spaces. If MCP is disconnected, use the hf-cli skill instead.

0 installs
▌
Hf Mem · catcorner22
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub. Use when you have a specific model and need its exact memory footprint. Complements `huggingface-best`, which works the other direction — given a device's memory budget, it narrows which models fit — and `huggingface-local-models` for local GGUF quantization choice.

0 installs
▌
Cdn Caching · catcorner22
Debug Vercel CDN caching — cache hit rate, stale content, revalidation behavior, ISR + PPR, per-request cache reasons (cacheReason) and PPR state (ppr_state), and costs.

0 installs
▌
Marketplace · catcorner22
Vercel Marketplace expert guidance — discovering, installing, and managing third-party integrations via the `vercel integration` CLI. Use when building any app that needs an external capability without a dedicated skill — commerce (stores, storefronts, selling products), payments (checkout, subscriptions, billing), observability/monitoring, messaging/email, search, or CMS — or when discovering, installing, or managing integrations.

0 installs
▌
Canvas · catcorner22 bundle
Author standalone .canvas.tsx analytical artifacts (charts, tables, audits, metrics) using the cursor/canvas SDK. Use when the deliverable IS structured visual output — not code fixes, PRs, or external dashboards. Skip for short answers and intermediate MCP queries.

0 installs
▌
Build Agents · catcorner22
Default guidance for building AI agents when no framework has been chosen, or when the target is Vercel-native. Use for generic requests to build, create, scaffold, design, architect, or implement an AI agent, agent app, tool-calling agent, durable agent, multi-agent system, or scheduled agent — where the request names no framework and the repo depends on none. Scope boundary: once a framework is named or already present, that pack owns the work — LangChain/LangGraph/Deep Agents to `ecosystem-primer`, Pydantic AI to `building-pydantic-ai-agents`, smolagents to `smolagents`; authoring the agent's prompt text to `prompt-optimizer`. Do not claim a request merely because it contains the word "agent".

0 installs
▌
Verification · catcorner22
Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Use when the user asks to verify a feature, check end-to-end, or debug 'why isn't this working'. Do not auto-load just because a dev server started.

0 installs
▌
Ooda Lean Loop · catcorner22
Run fused OODA and lean loops: observe raw signal, orient with current-state map, decide one small batch, act with standard work, andon on failure, kaizen one improvement. Use when stuck, prioritizing, fighting thrash, or reducing rework. Scope boundary: prep before loop → `workspace-mise-en-place`; coding batches → `deliverable-first` + `real-time-testing`; meta routing → `craft-systems-primer`.

0 installs
▌
Plaud Autoflow · catcorner22
Configure Plaud AutoFlow: automatic device-to-app transfer, auto-transcription, auto-summary with chosen template and LLM, and email delivery. Use when automating repetitive Plaud pipelines for lectures or recurring meetings. Scope boundary: one-off summary edits → `plaud-summary-templates`; export destinations → `plaud-export-integrate`.

0 installs
▌
Runtime Cache · catcorner22
Vercel Runtime Cache API guidance — ephemeral per-region key-value cache with tag-based invalidation. Shared across Functions, Routing Middleware, and Builds. Use when implementing caching strategies beyond framework-level caching.

0 installs
▌
Study System · catcorner22
Plan and execute studying: syllabus to weekly schedule, active recall, spaced repetition prompts, exam prep cadence, and WIP limits on courses. Use when mapping a semester, preparing for exams, or building a study routine. Scope boundary: calendar mechanics → `outlook-email-calendar`; lecture capture → `plaud-lecture-notes`; prioritization loops → `ooda-lean-loop`; week prep → `workspace-mise-en-place`.

0 installs
▌
UI Engineering · catcorner22
Modern UI implementation: component composition, design tokens, Tailwind/shadcn/Radix stacks, responsive layout, and accessible markup foundations. Use when building or refactoring UI components, pages, design systems, or styling. Scope boundary: React/Next render performance → `react-best-practices`; shadcn CLI install and registries → `shadcn`; App Router data fetching and RSC → `nextjs`; UX flows and copy → `ux-engineering`.

0 installs
▌
UX Engineering · catcorner22
User experience engineering: task flows, Nielsen heuristics, loading/empty/error patterns, accessibility (WCAG-oriented), microcopy, and feedback loops. Use when designing or reviewing screens, forms, onboarding, or when the user mentions UX, usability, a11y, accessibility, or user flow. Scope boundary: component implementation and Tailwind/shadcn structure → `ui-engineering`; React render performance → `react-best-practices`; full browser E2E proof → `verification`/`playwright-cli`.

0 installs
▌
Cursor Sdk · catcorner22 bundle
Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor TypeScript SDK (`@cursor/sdk`). Use this skill whenever the user mentions integrating, installing, or writing code against the Cursor SDK; whenever they say `Agent.create`, `Agent.prompt`, `Agent.resume`, `agent.send`, `run.stream`, `CursorAgentError`, or `@cursor/sdk`; whenever they ask to run Cursor agents programmatically from a script, CI/CD pipeline, GitHub Action, backend service, or any other code that isn't the Cursor IDE itself; and whenever they want to pick between local and cloud runtime, configure MCP servers for an SDK agent, or handle streaming, cancellation, or errors from an SDK agent. Also trigger when a user is wiring Cursor into an automation, writing a bot that runs Cursor, or porting REST `/v1/agents` calls to the SDK. Scope boundary — this skill is ONLY for driving Cursor's own coding agent from code (`@cursor/sdk`). For building a user-facing AI agent application, use `build-agents` / `eve` instead; d

0 installs
▌
Microfrontends · catcorner22 bundle
Guide for building, configuring, and deploying microfrontends on Vercel. Use this skill when the user mentions microfrontends, multi-zones, splitting an app across teams, independent deployments, cross-app routing, incremental migration, composing multiple frontends under one domain, microfrontends.json, @vercel/microfrontends, the microfrontends local proxy, or path-based routing between Vercel projects. Also use when the user asks about shared layouts across projects, navigation between microfrontends, fallback environments, asset prefixes, or feature flag controlled routing.

0 installs
▌
Vercel Connect · catcorner22
Vercel Connect expert guidance — securely obtain scoped OAuth tokens for third-party services (Slack, GitHub, MCP servers, OAuth, Snowflake) on behalf of apps or users via Vercel OIDC. Use when wiring up third-party API access, connecting to MCP servers, sending Slack messages, accessing GitHub APIs, receiving webhook events from Slack/Linear/GitHub and forwarding them to your agents and apps, or building eve agent connections.

0 installs
▌
Vercel Sandbox · catcorner22 bundle
Vercel Sandbox + agent-browser guidance — run headless Chrome in Firecracker microVMs for screenshots, accessibility snapshots, and browser automation. Use when building agent-browser or scheduled scraping flows on Vercel. For generic untrusted-code isolation, still use @vercel/sandbox APIs documented here after the browser sections.

0 installs
▌
Vercel Storage · catcorner22
Vercel storage expert guidance — Blob, Edge Config, and Marketplace storage (Neon Postgres, Upstash Redis). Use when choosing, configuring, or using data storage with Vercel applications.

0 installs
▌
Env Setup · catcorner22 bundle
Explain, inspect, configure, and troubleshoot Cloud Agent development environments. Use when the user asks about environment setup, changing/improving the environment, or triggering/testing a build.

0 installs
▌
Subscribe · catcorner22
Wait for external events (GitHub CI results, PR activity, Slack messages, Linear issues) by subscribing with the cursor-subscriptions MCP tools instead of polling.

0 installs
▌
Fix CI · catcorner22
Find failing PR checks, inspect logs or external check links, and apply focused fixes

0 installs
▌
Smolagents · catcorner22
Hugging Face `smolagents`: choosing CodeAgent vs ToolCallingAgent, the model backends (InferenceClientModel, LiteLLMModel, TransformersModel, OpenAIModel), defining tools with `@tool` or a `Tool` subclass, the sandbox choice for the Python that CodeAgent executes, managed-agent hierarchies, and memory/step surgery. Use when the user names smolagents, CodeAgent, ToolCallingAgent, or InferenceClientModel, when code contains `from smolagents`, or when running the `smolagent` CLI. Scope boundary: this covers the smolagents library only — an agent-building request with no framework chosen belongs to `build-agents`/`eve`, Pydantic AI to `building-pydantic-ai-agents`, LangChain/LangGraph to that pack, and Hub API scripting to `huggingface-tool-builder`/`hf-cli`.

0 installs
▌
Vercel Firewall · catcorner22
Vercel Firewall expert guidance — automatic DDoS mitigation, the Vercel WAF (custom rules, IP blocking, managed rulesets, rate limiting), Attack Mode, system bypass, bot management, and the `vercel firewall` CLI. Use when configuring platform-level security, responding to attacks, or staging firewall rules.

0 installs
▌
Vercel Services · catcorner22
Configure and troubleshoot Vercel Services for multiple frontends and backends in one project. Use when composing a polyglot or multi-service application on one Vercel deployment; defining the `services` key, service-targeted rewrites, or service bindings in `vercel.json`; or running all services with `vercel dev`.

0 installs
▌
Langchain RAG · catcorner22
Build a retrieval pipeline with LangChain: document loaders, RecursiveCharacterTextSplitter, embeddings, and the LangChain vector store wrappers (Chroma, FAISS, Pinecone). Use when the retrieval code is LangChain's — the user names LangChain, or the code imports `langchain_community` loaders, `langchain_text_splitters`, or a `langchain_*` vector store. Scope boundary: RAG built on the Vercel AI SDK (`embed`/`embedMany`) belongs to `ai-sdk`; this skill does not claim a retrieval pipeline that is not LangChain's.

0 installs
▌
Langgraph CLI · catcorner22
The `langgraph` / `langgraphjs` CLI: `new`, `dev`, `build`, `up`, `deploy`, `dockerfile`, deployment logs, and the `langgraph.json` config schema. Use when running a `langgraph` command, editing `langgraph.json`, or shipping a graph to LangGraph Platform (LangSmith Deployments). Scope boundary: deploying a Next.js app or any non-LangGraph service to Vercel belongs to `vercel-cli`/`deployments-cicd`.

0 installs
▌
Plaud Ask Queries · catcorner22
Query Plaud recordings with Ask Plaud: cross-file search, cited answers linked to audio timestamps, and follow-up questions. Use when the user wants to find what was said across lectures or meetings in Plaud. Scope boundary: writing new prose from answers → `academic-writing`; naming sources in those answers → `citation-literacy`.

0 installs
▌
Create A Backend · catcorner22 bundle
Backend architecture guidance. Use when planning, building, or migrating an API or backend; choosing between Functions, Services, containers, Workflow, Queues, and Marketplace databases; or selecting a supported backend framework or runtime.

0 installs
▌
Deployments Cicd · catcorner22
Vercel deployment and CI/CD expert guidance. Use when deploying, promoting, rolling back, inspecting deployments, building with --prebuilt, or configuring CI workflow files for Vercel.

0 installs
▌
Knowledge Update · catcorner22
Corrects outdated LLM knowledge about the Vercel platform and introduces new products. Invoke manually when working on Vercel products, Fluid Compute, vercel.ts, or when platform facts may be stale.

0 installs
▌
Vercel Functions · catcorner22
Vercel Functions expert guidance — Serverless Functions, Edge Functions, Fluid Compute, streaming, Cron Jobs, and runtime configuration. Use when configuring, debugging, or optimizing server-side code running on Vercel.

0 installs
▌
Appbuilder Testing · catcorner22 bundle
Generate and run tests for Adobe App Builder actions and UI components. Scaffolds Jest unit tests, integration tests against deployed actions, contract tests for Adobe API interactions, and React component tests using Testing Library. Provides mock helpers for State, Files, Events SDKs, @adobe/aio-lib-* clients, ExC Shell context (@adobe/exc-app), and UIX Guest SDK (@adobe/uix-guest). Use this skill whenever the user mentions testing App Builder actions, writing unit tests for Runtime actions, creating integration tests, mocking Adobe SDKs, setting up test fixtures, running aio app test, or wants to verify action behavior before deployment. Also trigger when users mention Jest configuration for App Builder, test coverage, CI test setup, React component test, Testing Library, UI test, Provider wrapper, test my page, test my form, test my table, test my component, mock shell context, mock extension context, debug test failures, or fix Jest errors.

0 installs
▌
Deliverable First · catcorner22
Plan and implement features by defining the final deliverable first, then reverse-engineering the smallest code path to it. Use when starting a feature, API, UI screen, or refactor; when the user says begin with the end in mind, work backwards, or what should this look like when done. Produces acceptance criteria, contracts, and UI state maps before bulk coding. Scope boundary: after the deliverable is defined, continuous test execution belongs to `real-time-testing`; structural boundaries belong to `stable-architecture`.

0 installs
▌
Real Time Testing · catcorner22
Test code continuously while writing it: red-green-refactor, watch mode, typecheck and lint after every slice, and never report done without fresh command output. Use when implementing features, fixing bugs, or when the user asks for TDD, test as you go, verify while coding, or real-time testing. Scope boundary: full browser/product verification after the feature works → `verification`; Playwright CLI mechanics → `playwright-cli`; Adobe Jest patterns → `appbuilder-testing`; CI loop on a PR → `loop-on-ci`/`fix-ci`.

0 installs
▌
Trl Training · catcorner22
Train and fine-tune transformer language models locally with the TRL CLI (SFT, DPO, GRPO, KTO, RLOO, Reward Model). For managed Hugging Face Jobs, use huggingface-llm-trainer and hf-cli instead.

0 installs
▌
Academic Writing · catcorner22
Structure and revise academic prose: thesis statements, outlines, paragraphs, introductions/conclusions, argument flow, and tone by assignment type (analytic, argumentative, reflective, compare-contrast, lab IMRaD). Use when writing or editing essays, discussion posts, reading responses, or when the user asks for help organizing a paper. Scope boundary: citation formatting → `citation-literacy`; named sources and attribution → `journalistic-attribution`; lecture-to-notes → `plaud-lecture-notes`; slides → `powerpoint-decks`.

0 installs
▌
Clean Minimal Code · catcorner22
Write clear, minimal code: fewer lines with the same behavior, established naming, SOLID and YAGNI, no premature abstraction. Use when implementing or reviewing functions, modules, or refactors; when the user wants clean code, less boilerplate, simplify, or remove unnecessary complexity. Scope boundary: system-wide boundaries and coupling → `stable-architecture`; test loop while editing → `real-time-testing`; React-specific perf → `react-best-practices`.

0 installs
▌
Plaud Lecture Notes · catcorner22
Turn Plaud lecture recordings into study materials: capture setup, summary templates for classes, Cornell-style refinement, exam prep loops, and pairing with spaced repetition. Use when a student records classes with Plaud for coursework. Scope boundary: general Plaud routing → `plaud-ecosystem-primer`; study scheduling → `study-system`; prep → `workspace-mise-en-place`; essay writing → `academic-writing`.

0 installs
▌
Plaud Transcription · catcorner22
Improve Plaud transcripts: language selection, speaker diarization, custom vocabulary, formatting, and fixing common ASR errors before summarizing. Use after a Plaud recording syncs or when transcript accuracy is poor. Scope boundary: summary templates → `plaud-summary-templates`; querying transcripts → `plaud-ask-queries`.

0 installs
▌
Playwright CLI · catcorner22 bundle
Automate browser interactions, test web pages and work with Playwright tests — the general-purpose Playwright skill for this repo (web apps, Next.js, any non-Adobe project). Scope boundary: for browser-based E2E tests of an Adobe App Builder ExC Shell SPA or AEM extension use `appbuilder-e2e-testing`; for running headless Chrome inside Vercel Sandbox microVMs (agent-browser, scheduled scraping) use `vercel-sandbox`. This skill owns local and CI Playwright usage everywhere else.

0 installs
▌
Routing Middleware · catcorner22
Vercel Routing Middleware guidance — request interception before cache, rewrites, redirects, personalization. Works with any framework. Supports Edge, Node.js, and Bun runtimes. Use when intercepting requests at the platform level.

0 installs
▌
Citation Literacy · catcorner22
Format and check academic citations: APA 7, MLA 9, and Chicago (notes-bibliography), in-text vs bibliography, common mistakes, and when to use which style. Use when the user asks how to cite a source, format references, or fix bibliography entries. Scope boundary: writing the paper body → `academic-writing`; claim-level attribution → `journalistic-attribution`; DOI/URL lookup mechanics only when tied to a citation question.

0 installs
▌
Appbuilder Workfront · catcorner22 bundle
Use when orienting, onboarding, or planning before a concrete task — the entry point for building a customized Workfront UI on Adobe App Builder. Reach for this whenever the user is: brand new to Workfront UI extensions and asking where to start or what the process looks like; describing a Workfront customization idea and asking how to build it; asking for the end-to-end roadmap (set up → scaffold → build → test → deploy → publish); or asking how the React/Spectrum SPA, the serverless Runtime actions, and the Workfront extension points fit together. This umbrella routes each stage to its skill: workfront-ui-extension (front-end SPA + extension points), workfront-actions (Runtime actions + Workfront Public API v21), workfront-local-testing (previewing a build inside Workfront); machine setup and aio app init live in appbuilder-project-init. Skip it and go straight to the matching sub-skill when the user already has one specific task.

0 installs
▌
Parallax Depth · catcorner22
Estimate reasoning depth from the shift between the current query and recent history (deep/medium/shallow). Use to set budget before a long answer. Scope boundary — START classes → `emergency-triage-compute`; zoom level → `cartographic-zoom`.

0 installs
▌
Stable Architecture · catcorner22
Design code that avoids houses of cards: clear module boundaries, dependency direction, fail-fast invariants, and replaceable adapters. Use when structuring a feature, splitting services, reviewing coupling, or when changes in one file break unrelated areas. Scope boundary: line-level clarity → `clean-minimal-code`; defining what done looks like → `deliverable-first`; running tests while editing → `real-time-testing`.

0 installs
▌
Craft Systems Primer · catcorner22
Router for operational craft frameworks in this library: OODA decision tempo, Toyota-style lean loops (small batches, andon, kaizen), and mise en place workspace prep. Use when prioritizing work, eliminating waste, preparing before execution, or when the user mentions OODA, lean, kaizen, kanban, mise en place, or getting organized before starting. Scope boundary: domain execution → academic/coding/m365/plaud packs; raw execution posture → `proactive-agency`.

0 installs
▌
Loop On CI · catcorner22
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.

0 installs
▌
Deep Agents Core · catcorner22
Configure the `deepagents` harness: `create_deep_agent()` / `createDeepAgent()`, middleware selection, built-in filesystem and planning tools, the agent SKILL.md format it loads, and what the harness will and will not let you configure. Use when the user names Deep Agents or the code imports `deepagents`. Scope boundary: an agent-building request with no framework chosen belongs to `build-agents`/`eve`; raw graph code belongs to `langgraph-fundamentals`.

0 installs
▌
Ecosystem Primer · catcorner22
Router for the LangChain ecosystem: choose between LangChain, LangGraph, and Deep Agents, set the LANGSMITH_* env vars, find the right docs.langchain.com page, and hand off to the matching skill in this pack. Use when the user names LangChain, LangGraph, LangSmith, or Deep Agents, or when the repo already depends on `langchain*` / `langgraph*` / `deepagents` / `@langchain/*` and the layer choice is still open. Scope boundary: an agent-building request that has not chosen a framework is not this pack's — TypeScript/Vercel agents belong to `build-agents`/`eve`, and Python agents on another framework to `building-pydantic-ai-agents` or `smolagents`.

0 installs
▌
Transformers JS · catcorner22 bundle
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.

0 installs
▌
Word Documents · catcorner22
Create and format Microsoft Word documents: styles, headings, page layout, tables of contents, track changes, comments, mail merge basics, and export to PDF. Use when working in Word (.docx), formatting essays/reports, or when the user asks for Word-specific help. Scope boundary: citation style rules → `citation-literacy`; argument structure → `academic-writing`; PowerPoint → `powerpoint-decks`.

0 installs
▌
Playwright Trace · catcorner22
Inspect Playwright trace files from the command line — list actions, view requests, console, errors, snapshots and screenshots.

0 installs
▌
React Best Practices · catcorner22 bundle
React performance best-practices for TSX files — 64 Vercel rules across 8 impact tiers (waterfalls, bundle size, server/client fetching, re-renders). Use when optimizing React/Next.js components. This is not an accessibility linter.

0 installs
▌
Appbuilder E2e Testing · catcorner22 bundle
Use this skill whenever the user wants browser-based end-to-end tests for an Adobe App Builder application. Covers Playwright E2E testing for ExC Shell SPAs, AEM extension UIs, and full-stack flows. Use when the user mentions: "E2E test", "end-to-end test", "Playwright", "browser test", "test my SPA in the browser", "test my AEM extension", "test the full flow", "integration test with UI", "headless browser test", "E2E in CI". This skill is for BROWSER-based testing only. For Jest unit tests of actions or React components, use appbuilder-testing instead.

0 installs
▌
Sail Trim Tuning · catcorner22
Read user confusion/satisfaction signals and trim the next beat (more examples vs hold course). Use on multi-turn work. Scope boundary — mid-stream environment loop → `fermentation-feedback`; human OODA → `ooda-lean-loop`.

0 installs
▌
Proactive Agency · catcorner22
Always-on execution posture: do the work instead of describing it. Runs a five-step gate before every response — obtain it yourself rather than asking, reserve confirmation for irreversible/destructive/outward-facing/spend actions, batch legitimate clarifying questions up front, surface optimization findings compactly, and verify before reporting. Sole always-on skill in this library: injected at session start, not trigger-matched.

0 installs
▌
Huggingface Best · catcorner22
Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.

0 installs
▌
Excel Workbooks · catcorner22
Build and debug Microsoft Excel workbooks: formulas, references, tables, charts, conditional formatting, basic pivot tables, and data validation. Use when working in Excel (.xlsx), spreadsheet homework, budgets, or lab data tables. Scope boundary: interpreting results in prose → `academic-writing`; Python/R analysis → `coding-ecosystem-primer`; Google Sheets → not this pack.

0 installs
▌
Plaud Ecosystem Primer · catcorner22
Router for Plaud AI voice recorder workflows: device capture, transcription, summary templates, Ask Plaud queries, AutoFlow automation, and export. Use when the user mentions Plaud, Plaud Note, Plaud NotePin, voice recorder transcripts, or turning lectures/meetings into notes. Scope boundary: writing essays from scratch → `academic-writing`; Word/Outlook delivery → `m365-ecosystem-primer`; live Teams recording → `teams-collaboration`.

0 installs
▌
Plaud Export Integrate · catcorner22
Export Plaud transcripts and summaries to Word, PDF, mind maps, and integrate with OneDrive, Teams, Notion, or email workflows. Use when moving Plaud output into school or work tools. Scope boundary: Word formatting → `word-documents`; OneDrive structure → `onedrive-organization`; Teams sharing → `teams-collaboration`.

0 installs
▌
Next Cache Components · catcorner22 bundle
Next.js 16 Cache Components guidance — PPR, use cache directive, cacheLife, cacheTag, updateTag, and migration from unstable_cache. Use when implementing partial prerendering, caching strategies, or migrating from older Next.js cache patterns.

0 installs
▌
Appbuilder Project Init · catcorner22 bundle
Initialize an Adobe App Builder project end-to-end without Developer Console UI clicks. Creates the Console project and workspace, subscribes APIs (including those needing a product profile), maps user intent to the right template, runs non-interactive `aio app init`, and guides post-init customization. Use whenever the user mentions creating an App Builder app, scaffolding a project, `aio app init`, setting up an Experience Cloud extension, adding actions or web assets, creating a Console project or workspace, adding APIs, or bootstrapping App Builder — even if they don't say "App Builder". Also for SPA templates, AEM extensions, API Mesh, Asset Compute workers, and MCP server projects. Also handles debugging init failures — template not found, `aio app init` hangs or times out, Node version mismatches, npm install failures, post-init build errors, `aio login` issues, `aio app run` showing nothing, or `aio console project create` / `workspace create` / `workspace api add` errors.

0 installs
▌
Cartographic Zoom · catcorner22
Generate country/city/street zoom levels: 1–2 sentences, 1–2 paragraphs, full deep-dive. Detect from query or offer zoom-in. Use when verbosity mismatch hurts UX. Scope boundary: stage layout → `stage-blocking-layout`.

0 installs
▌
Interaction Table · catcorner22
Look up known skill/plugin pairs that fight (context strip vs inject, length vs rhythm, duck vs dual-axis, rewrite vs lock) before loading both. Use when composing an ai-transfer stack. Scope boundary — library routing audit → `skill-library-audit`; compute triage → `emergency-triage-compute`.

0 installs
▌
Weaving Warp Weft · catcorner22
Interleave fixed structural threads (warp: required claims, compliance) with flexible expressive weft (tone, examples). Enforce both — compliant AND engaging. Use for regulated or rubric-bound outputs. Scope boundary: proofreading marks for weft edits → `proofreading-marks`.

0 installs
▌
Workspace Mise En Place · catcorner22
Prepare the workspace before execution: files, folders, env, tools, references, and templates in place so work never stops for a missing ingredient. Culinary mise en place applied to repos, OneDrive, and study sessions. Use before starting an assignment, coding session, lecture day, or deploy. Scope boundary: during-task loops → `ooda-lean-loop`; folder taxonomy → `onedrive-organization`; defining done → `deliverable-first`.

0 installs
▌
Powerpoint Decks · catcorner22
Structure and design Microsoft PowerPoint presentations: slide layouts, master slides, visuals, speaker notes, animations restraint, and export. Use when building .pptx decks for class, work, or conferences. Scope boundary: argument craft for speaker notes → `academic-writing`; Word handouts → `word-documents`; Copilot custom skill upload format → compatible with this SKILL.md structure.

0 installs
▌
Plaud Recording Capture · catcorner22
Capture audio with Plaud devices and app: in-person vs phone-call mode, press-to-highlight, placement, battery, consent, and recording hygiene. Use when starting a Plaud recording, choosing Note vs NotePin, or improving capture quality. Scope boundary: post-capture transcription → `plaud-transcription`; legal advice → remind user of local consent laws only.

0 installs
▌
Plaud Summary Templates · catcorner22
Generate Plaud AI summaries: built-in templates, custom templates, multidimensional summaries, action items, and meeting vs lecture formats. Use when summarizing a Plaud transcript or designing a reusable template. Scope boundary: cross-file Q&A → `plaud-ask-queries`; turning summary into essay → `academic-writing`.

0 installs
▌
Appbuilder Cicd Pipeline · catcorner22 bundle
Set up CI/CD pipelines for Adobe App Builder projects. Generates GitHub Actions workflows using adobe/aio-cli-setup-action@3 and adobe/aio-apps-action@3.3.0, plus patterns for Azure DevOps and GitLab CI. Handles OAuth S2S secrets injection, multi-workspace promotion (stage → prod), deploy gating with manifest validation. Use this skill whenever the user mentions CI/CD for App Builder, GitHub Actions for aio deploy, automated deployment pipelines, continuous integration, continuous delivery, deploy automation, multi-environment promotion, aio app add ci, or wants to automate their App Builder build and release process. Also trigger when users mention deploy workflows, release pipelines, or GitHub secrets for App Builder.

0 installs
▌
Appbuilder UI Scaffolder · catcorner22 bundle
Generate React Spectrum UI components for Adobe Experience Cloud Shell SPAs and AEM UI Extensions. Provides patterns for pages, forms, data tables, dialogs, and navigation using @adobe/react-spectrum. Guides ExC Shell integration with @adobe/exc-app including runtime.done(), IMS token passthrough, and shell theming. Guides AEM UI Extension development with @adobe/uix-guest for Content Fragment Console, CF Editor, Universal Editor, and Assets View surfaces. Trigger on: building App Builder UI, React Spectrum components, ExC Shell pages, forms, data tables, dialogs, modals, navigation, theming, web-src, Spectrum design system, @adobe/exc-app, AEM extension, AEM UI extension, Content Fragment Console, Universal Editor extension, uix-guest, @adobe/uix-guest, extension points for AEM, customizing AEM surfaces.

0 installs
▌
AI Transfer Memory · catcorner22
Router for memory AI-transfer techniques: stratified sessions, tablebase cache, taxonomy retrieval, cross-session bridges. Use for long-horizon context and RAG design. Scope boundary: full catalog → `ai-transfer-ecosystem-primer`.

0 installs

187 published skills · page 2 of 2