Claude Skills by The-AIOS

Implement WCAG 2.2 compliant interfaces with mobile accessibility, inclusive design patterns, and assistive technology support. Use when auditing accessibility, implementing ARIA patterns, building for screen readers, or ensuring inclusive user experiences.

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.

Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use when architecting complex backend systems or refactoring existing applications for better maintainability.

Govern shared resources well using Elinor Ostrom's design principles for the commons — applied to AIOS shared substrate: multi-operator vaults, collaboration spaces, company-synced infrastructure, and multiple agents writing one git repo. Use when designing rules for a shared space, deciding who-decides-what across collaborators or agents, preventing tragedy-of-the-commons or write-collision dynamics, setting boundaries on a shared repo/folder, or standing up collab/company governance. Distri...

Keep the operator's understanding from falling behind what their agents ship — the gap between what the vault and repos contain and what the operator actually grasps. Use when agents (spawned workers, overnight sessions, autonomous loops, /aios:update self-modification) have shipped work the operator didn't author, when deciding whether to trust an autonomous loop, when a repo or venture starts feeling opaque, or during /close-session and /aios:housekeeping. The defensive complement to Arc se...

Turn data into compelling narratives + effective dashboards. Use when presenting analytics to stakeholders, designing KPI dashboards, structuring an executive summary around metrics, building data visualizations, or implementing real-time monitoring patterns.

Execute database migrations across ORMs and platforms with zero-downtime strategies, data transformation, and rollback procedures. Use when migrating databases, changing schemas, performing data transformations, or implementing zero-downtime deployment strategies.

Deep, multi-source research for acting under uncertainty — answers WHAT to aim for, WHY it matters, and HOW to pursue it, when the answer requires surveying a live field rather than retrieving one fact. Output-agnostic by design: the starting intent ('what should I write about?') is treated as provisional, because research routinely reveals the real move is something else — a thing to build, a decision to make, a plan to change, a habit to adopt, a feature to ship. It maps the operator's exis...

Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.

Turn a structured document (an /ingest reflection, role report, weekly-learnings digest, deck outline, research note) into a beautiful, self-contained HTML infographic — a visual one-pager — with brand-aware theme selection. Use when the user asks to "make an infographic," "visualize this note/report," "turn this into a one-pager/poster," or accepts the post-ingest "generate a visual infographic?" offer.

Behavioral guidelines to reduce common LLM coding mistakes — think before coding, simplicity first, surgical changes, and goal-driven execution. Use when writing or editing code to avoid over-engineering, speculative abstractions, scope creep in diffs, and unverified changes.

Decide WHERE to intervene in a system for maximum effect using Donella Meadows' leverage-points lens — push interventions toward high-leverage places (goals, rules, self-organization, paradigm) and away from low-leverage ones (parameters, buffers, taxes/subsidies). Use when choosing where to act on a complex system, prioritizing competing fixes, designing a policy/intervention/process change, diagnosing why a problem keeps recurring despite effort, or when a past fix didn't stick. The systems...

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

Choose the right orchestration primitive for delegated work — a single agent, parallel agents, or a dynamic workflow — using the agent → parallel → workflow ladder, plus the spawn-vs-subagent axis (interactive-and-independent vs. harness-tracked-and-harvested), plus which MODEL/tier the worker runs on. ALSO the reference for talking to other sessions through the AIOS Glass spawn-inbox command bus. Use when deciding how to delegate a task, whether to fan work out, whether you need the result b...

Implement PCI DSS compliance requirements for secure handling of payment card data and payment systems. Use when securing payment processing, achieving PCI compliance, or implementing payment card security measures.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

Python best practices across design patterns, error handling, project structure, and testing. Use when writing Python code, structuring new Python projects, designing APIs for libraries, implementing error handling, or setting up pytest test suites.

Modern React + Next.js patterns. Use when building Next.js apps (App Router, Server Components, streaming, parallel routes), implementing React state management (Redux Toolkit, Zustand, Jotai, React Query), or applying Next.js framework best practices (file conventions, RSC boundaries, metadata, image/font optimization).

The build ORDER and the defaults that decide whether a product is debuggable six months in — what to build first (admin and seed data before the product, which is the part everyone gets wrong), deterministic seed data, non-sequential ids, one-command environments, and PR discipline. Use when starting a new product or service, when planning an MVP's sequence, when a build is about to skip straight to features, when reviewing whether a project has the scaffolding to be supported, or when settin...

Treat the operator's capacity, pace, and rhythm as first-class design inputs — not afterthoughts to optimize away. Use when planning workload or cadence, deciding whether to push hard or pace deliberately, judging whether carried/slow/deferred work is genuine avoidance vs. a legitimate quality gate or rhythm, designing rituals and routines, sequencing a heavy week, or guarding against burnout-by-velocity. The generative complement to the system's defensive anti-values: it says what conditions...

Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.

Compose a team (of people OR agents) by lifecycle posture, not job title, using the five product archetypes — Prototyper, Builder, Sweeper, Grower, Maintainer — and the rule that a healthy mix depends on product stage. Use when deciding which agents/people to deploy on a project, diagnosing why a team or agent bundle feels lopsided (all builders, no maintainers), choosing what posture to take on a given piece of work, staffing a pre-PMF vs growing vs mature product, or selecting an agent mix ...

Measure AI-writing tells in a draft against the operator's own voice — density, bursts, and position — and report rather than rewrite. Use before publishing anything in the operator's name (essay, post, chapter, email, proposal, deck copy, back cover), when a draft "feels AI-ish" and you need to know where, when a ghostwritten piece needs a voice check before it ships, or when calibrating an operator's voice budget from their published corpus. Governs by budget, never by banned list — a banne...

Actually watch or listen to a video/audio source and hold it in context so you can answer questions about it, summarise it, pull quotes, or act on what it says — a QUICK COMPREHENSION action, not a filing pipeline. Covers the local media hooks Claude cannot otherwise discover: hooks/transcribe.py (long-form audio → text, on-device) and hooks/video-watch.py (the VISUAL channel — slides, code, diagrams, terminal, on-screen text that a transcript throws away). Use when the operator shares a vide...

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model...

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when executing implementation plans with independent tasks in the current session

Use when you have a spec or requirements for a multi-step task, before touching code