Sheshiyer
UserBrand identity orchestration: strategy → visuals → publishing. Wave-based pipeline with asset fidelity compositing, semantic reference matching, and NotebookLM artifact generation.
Categories
Indexed Skills (79)
newsletter-curation
Newsletter curation with content sourcing, editorial structure, and subscriber growth strategies. Covers issue formatting, link roundups, commentary style, and sending cadence. Use for: email newsletters, link roundups, weekly digests, curated content, creator newsletters. Triggers: newsletter, email newsletter, newsletter curation, weekly digest, link roundup, curated newsletter, newsletter writing, newsletter format, subscriber growth, newsletter strategy, content curation, newsletter template
accessibility
Design, implement, and audit inclusive digital products against WCAG 2.2 Level AA, generating semantic ARIA for Web and accessibility traits for iOS/Android. USE WHEN adding screen-reader support, fixing a11y audit failures, or building accessible web and native UI.
agent-architecture-audit
Full-stack diagnostic that audits the 12-layer agent stack for wrapper regression, memory pollution, tool-discipline failures, hidden repair loops, and rendering corruption, producing severity-ranked code-first fixes. USE WHEN debugging or reviewing agent, autonomous-loop, or LLM-powered apps.
agent-eval
Run head-to-head comparisons of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks, reporting pass rate, cost, time, and consistency metrics. USE WHEN choosing between coding agents or benchmarking agent performance on representative tasks.
agent-introspection-debugging
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. USE WHEN an agent run fails, loops, or behaves unexpectedly and you need a repeatable post-mortem and recovery process.
agentic-os
Build persistent multi-agent operating systems on Claude Code, covering kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and database-free state. USE WHEN designing a multi-agent system, kernel, or file-based memory and automation layer on Claude Code.
ai-regression-testing
Regression testing strategies for AI-assisted development: sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch blind spots when the same model writes and reviews code. USE WHEN guarding AI-generated changes against regressions.
angular-developer
Generate Angular code and architectural guidance covering signals reactivity, forms, dependency injection, routing, SSR, ARIA, animations, styling, testing, and CLI tooling. USE WHEN creating Angular projects, components, or services, or applying modern Angular best practices.
api-connector-builder
Build a new API connector or provider by matching the target repo's existing integration pattern exactly. Use when adding one more integration without inventing a second architecture.
api-design
REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs. USE WHEN designing or reviewing a REST API's endpoints, response shapes, versioning, or error conventions.
architecture-decision-records
Capture architectural decisions as structured ADRs, recording context, alternatives considered, and rationale, and maintaining an ADR log of why the codebase is shaped as it is. USE WHEN a significant design or technology choice is made and should be documented for future developers.
astro-framework
Astro framework specialist for building fast, content-driven websites with islands architecture. Use when creating Astro components, configuring hydration (client:load/idle/visible/media), using server:defer (server islands), Content Layer API (glob/file loaders, live loaders), sessions, astro:env, i18n routing, actions, SSR adapters, view transitions, or integrating React/Vue/Svelte/Solid. Not for full-SPA frameworks (Next.js, Remix, SvelteKit).
automation-audit-ops
Evidence-first automation inventory and overlap audit workflow for an autonomous agent operator. Use when the user wants to know which jobs, hooks, connectors, MCP servers, or wrappers are live, broken, redundant, or missing before fixing anything.
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. USE WHEN building or refactoring Node/Express/Next.js backend code, API routes, or data-access and server-side logic.
benchmark
Measure performance baselines, detect regressions before and after PRs, and compare stack alternatives. USE WHEN establishing a perf baseline, checking whether a change slowed things down, or benchmarking competing libraries or approaches.
blockchain-web3-core
Shared reference for the blockchain-web3 cluster: the adversarial on-chain threat model (immutable, anyone-can-call, MEV), checks-effects-interactions, oracle-manipulation resistance, token-decimals precision, and the non-advisory stance for trading/prediction-market work. USE WHEN writing, auditing, or reasoning about smart-contract / DeFi / on-chain code — the cross-cutting model every web3 spoke shares.
blueprint
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent projects, with self-contained per-step briefs, adversarial review gate, dependency graph, and parallel-step detection. USE WHEN planning a complex multi-PR or multi-session task; skip for single-PR work.
browser-qa
Automate visual testing and UI interaction verification through browser automation. USE WHEN confirming a deployed or in-progress feature renders and behaves correctly in a real browser, or catching visual and interaction regressions.
building-native-ui
Guide to building polished apps with Expo Router, covering fundamentals, styling, components, navigation, animations, patterns, and native tabs. USE WHEN building or styling Expo/React Native UI, setting up Expo Router navigation, or adding native tabs and animations.
bun-runtime
Bun as runtime, package manager, bundler, and test runner, including when to choose Bun vs Node. USE WHEN adopting Bun, migrating from Node, writing or debugging Bun scripts/tests, or configuring Bun on Vercel.
canary-watch
Monitor and verify a deployed URL by checking HTTP endpoints, SSE streams, static assets, console errors, and performance regressions. USE WHEN smoke-testing or canary-watching after a deploy, a risky merge, or a dependency upgrade.
cisco-ios-patterns
Cisco IOS and IOS-XE review patterns for show commands, config hierarchy, wildcard masks, ACL placement, and interface hygiene. USE WHEN reviewing IOS/IOS-XE config before a change, picking read-only show commands, or verifying a change-window landed safely.
ck
Persistent per-project memory for Claude Code that auto-loads context on session start, tracks sessions with git activity, and writes native memory via deterministic Node.js scripts. USE WHEN running /ck:* commands or keeping project context across sessions.
clickhouse-io
ClickHouse schema, query optimization, and data-engineering patterns for high-performance OLAP workloads. USE WHEN designing MergeTree tables, writing or tuning analytical queries, ingesting large data volumes, or migrating from Postgres/MySQL to ClickHouse.
code-tour
Create CodeTour .tour files — persona-targeted, step-by-step walkthroughs anchored to real files and line ranges. USE WHEN building onboarding tours, architecture walkthroughs, PR tours, RCA tours, or a reusable 'explain how this works' artifact.
codebase-onboarding
Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo.
3d-web-experience
Build 3D experiences for the web with Three.js, React Three Fiber, Spline, WebGL, and GLSL — product configurators, immersive sites, interactive scenes. USE WHEN adding 3D, a configurator, or WebGL depth to a web UI.
ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," or "how long should I run this test." Use this whenever someone is comparing two approaches and wants to measure which performs better. For tracking implementation, see analytics-tracking. For page-level conversion optimization, see page-cro.
accesslint-audit
Find and fix WCAG 2.2 accessibility issues in code or live pages, in report mode (prioritized written audit, no edits) or fix mode (audit->edit->verify), preferring direct-CDP live-DOM auditing. USE WHEN an agent's UI output needs an accessibility audit or WCAG fixes before shipping.
accesslint-diff
Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [<name>] to diff against a branch; reports only new violations introduced, violations fixed, and pre-existing count. USE WHEN you want to prove a UI change adds no new WCAG violations before a PR, or to separate a11y issues a diff introduced from pre-existing ones (use accesslint-scan for a full audit with no diffing).
ad-creative
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative testing,' 'ad performance optimization,' 'write me some ads,' 'Facebook ad copy,' 'Google ad headlines,' 'LinkedIn ad text,' or 'I need more ad variations.' Use this whenever someone needs to produce ad copy at scale or iterate on existing ads. For campaign strategy and targeting, see paid-ads. For landing page copy, see copywriting.
agent-evaluation
Test and benchmark LLM agents with behavioral contract testing, capability assessment, statistical/adversarial evaluation, regression pipelines, and production monitoring. USE WHEN you need to measure, benchmark, or regression-test an LLM agent's real-world reliability.
agent-memory-systems
Architect agent memory across short-term context, long-term vector stores, and CoALA-style cognitive layers, with LangMem patterns, vector-DB selection (Pinecone/Qdrant/Chroma), and chunking strategy. USE WHEN designing the memory architecture and vector-store stack for a production agent.
agent-tool-builder
Design agent tools from JSON Schema to error handling and MCP exposure, writing LLM-legible descriptions, validation, and token-efficient interfaces that avoid silent failures. USE WHEN defining or hardening the tools/functions an LLM agent can call.
ai-agents-architect
Design and build autonomous AI agents: ReAct and plan-and-execute loops, tool registries, hierarchical memory, supervisor patterns, and checkpoint recovery. USE WHEN architecting an autonomous agent's control loop, tools, and memory from scratch.
ai-native-cli
Design spec with 98 rules for building CLI tools that AI agents can safely use — structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description. USE WHEN building, retrofitting, or auditing a command-line tool that AI agents or automation pipelines will invoke.
ai-product
Production-grade LLM product engineering — RAG architecture, prompt engineering that scales, structured-output validation, latency/streaming UX, and cost control. USE WHEN building an AI-powered product feature and deciding how to integrate an LLM so it survives production rather than shipping a fragile demo.
ai-seo
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for Perplexity,' 'AI citations,' 'AI visibility,' 'zero-click search,' 'how do I show up in AI answers,' 'LLM mentions,' or 'optimize for Claude/Gemini.' Use this whenever someone wants their content to be cited or surfaced by AI assistants and AI search engines. For traditional technical and on-page SEO audits, see seo-audit. For structured data implementation, see schema-markup.
ai-wrapper-product
Turn an AI API (OpenAI, Anthropic, etc.) into a focused, defensible, paid product — prompt engineering for products, usage metering, rate limiting, model selection, and output quality control. USE WHEN building or pricing an AI-wrapper business and you need it to solve a real problem rather than be a thin ChatGPT clone.
algolia-search
Implement Algolia search: indexing strategies, React InstantSearch hooks/widgets, faceting, and relevance tuning. USE WHEN adding site/app search, type-ahead, faceted filtering, or tuning Algolia relevance.
analytics-tracking
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this," "track conversions," "attribution," "Mixpanel," "Segment," "are my events firing," or "analytics isn't working." Use this whenever someone asks how to know if something is working or wants to measure marketing results. For A/B test measurement, see ab-test-setup.
annualreports
Annual security report aggregation and analysis. USE WHEN annual reports, security reports, threat reports, industry reports, update reports, analyze reports, vendor reports, threat landscape.
apify
Social media scraping, business data, e-commerce via Apify actors. USE WHEN Twitter, Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps, Amazon scraping.
app-store-changelog
Generate user-facing App Store release notes from git history since the last tag, grouped into New/Improved/Fixed with internal commits filtered out. USE WHEN drafting What's New text, release notes, or changelog bullets for an App Store / TestFlight submission.
app-store-screenshots
Create App Store and Google Play screenshots and preview videos with exact platform specs — iOS/Android dimensions, gallery ordering, device mockups — via the inference.sh (belt) CLI. USE WHEN making app store or play store screenshots, app preview videos, device mockups, or store-listing gallery images.
arch-orchestrator
Turn a raw product brief into a consistent, implementation-ready spec pack under specs/ (frontend, backend, API, AI) by coordinating specialist agents and enforcing a project's preferred stack. USE WHEN the user says "create architecture plan/specs", "turn this brief into docs", "generate frontend/backend/api specs", or "write the spec markdown files" — wants end-to-end software architecture documentation from a product brief.
artifacts-builder
Build elaborate multi-component HTML artifacts with React, Tailwind CSS, and shadcn/ui, then bundle them into a single HTML file. USE WHEN a complex artifact needs state management, routing, or shadcn/ui components — NOT for simple single-file HTML/JSX artifacts.
agentic-engineering
Operate as an agentic engineer using eval-first execution, task decomposition, and cost-aware model routing. USE WHEN planning or executing LLM-driven engineering work and you need disciplined evals, decomposition, and model-selection practices.
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing. USE WHEN you want a full a11y audit of a running page or preview URL and a prioritized fix list (use accesslint-diff instead when you only want violations a change introduced).
ai-automation-workflows
Use when you need to orchestrate an approved AI workflow, scheduled automation, or execution backend without bypassing the packet and approval path. This local mirror aligns OpenClaw with inference-sh agent-skills ai-automation-workflows.
ai-content-pipeline
Use when running or coordinating the Tryambakam Noesis source-to-distribution content pipeline. This local mirror aligns OpenClaw with inference-sh agent-skills ai-content-pipeline and binds it to the current OpenClaw, Paperclip, Higgsfield, and inference.sh adapters.
adding-tauri-splashscreen
Add a Tauri splashscreen, loading screen, or startup screen to an app, covering configuration, custom splash HTML, styling, and closing the splash when ready. USE WHEN showing a loading or startup window before a Tauri app's main window is ready.
adding-tauri-system-tray
Implement Tauri system tray functionality including tray icon setup, tray menu creation, event handling, and runtime updates in the notification area. USE WHEN adding a menu-bar or system-tray icon, tray menu, or notification-area behavior to a Tauri app.
agentic-ops-core
Shared reference for the agentic-ops cluster: the evidence-first operator loop (resolve surface → read live state → smallest reversible action → prove it → report exact status), the surface taxonomy, the status-word vocabulary, and the secrets/PII guardrails every operator spoke obeys. USE WHEN operating any live external surface — inbox, repo, tracker, billing, docs — or before any send/push/refund/mutation in this cluster.
agentic-ops-orchestrator
Route a real-world operations task to the right skill among 16 agentic-ops specialists — email, messages, GitHub, Jira, Google Workspace, project flow, unified notifications, terminal/CI, knowledge base, customer + finance billing, automation audit, workspace-surface audit, social connections, and dashboards. USE WHEN an agent must operate, triage, or prove work on a live external surface (inbox, repo, tracker, billing, docs) but the user hasn't named the specific skill.
ai-agents-meta-core
Shared reference for the ai-agents-meta cluster: the eval-first + default-deny-autonomy model every spoke turns on, plus shared conventions (the agent stack, cold-start briefs, cost routing tiers) and the gate/loop/cost matrix. USE WHEN wiring an autonomous loop, granting an agent tools, setting an eval gate, or routing by model cost — the interlocking rules every meta spoke shares.
ai-agents-meta-orchestrator
Route an AI-agent engineering task to the right skill among 14 meta specialists — planning a multi-session build, decomposing a plan into an agent chain, orchestrating a squad, running an autonomous loop, auditing/debugging the agent stack, optimizing prompts, and controlling token/cost budget. USE WHEN a user is designing, building, operating, or hardening an LLM-agent system but hasn't named the specific concern.
android-clean-architecture
Clean Architecture patterns for Android and Kotlin Multiplatform projects, covering module structure, dependency rules, UseCases, Repositories, and data-layer patterns. USE WHEN structuring an Android/KMP codebase, defining module boundaries, or applying UseCase and Repository layers.
animejs
Versatile JavaScript animation engine for DOM, CSS, SVG, and JavaScript objects. Use when creating timeline-based animations, stagger effects, SVG morphing, keyframe sequences, or complex choreographed animations. Triggers on tasks involving Anime.js, timeline animations, staggered sequences, SVG path animations, morphing, or multi-step animation choreography. Alternative to GSAP for SVG-heavy animations and React-independent projects.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
astro-core
Shared reference for the Astro cluster: the rendering-mode decision (static / on-demand SSR / hybrid + server islands), hydration directives, the Content Layer & collections model, astro:env / sessions / actions conventions, and SSR adapter selection. USE WHEN deciding how an Astro page renders or where data comes from — the cross-cutting model the Astro spokes share. Implementation depth lives in astro-framework.
astro-gsap-scrolltrigger
Use when adding, fixing, or reviewing GSAP ScrollTrigger behavior in Astro pages, especially with view transitions, static routes, client scripts, reduced motion, cleanup, or browser-only lifecycle constraints.
astro-orchestrator
Route an Astro task to the right spoke — building the site (components, islands/hydration, content, SSR, actions, i18n) or publishing a docs/wiki/press-kit site. USE WHEN working on an Astro project but the specific concern isn't named, or when deciding the rendering mode (static vs on-demand vs hybrid). For scroll/animation/video on an Astro page, hand off to the creative-frontend cluster.
astro-wiki-publisher
Use when publishing or hardening an Astro docs/wiki/press-kit site with Markdown or MDX content, generated routes, artifact data, public copy QA, browser verification, Vercel or Cloudflare deploy checks, or README/docs media outputs.
backend-architecture-core
Shared reference for the backend-architecture cluster: the dependency-inversion boundary (domain → ports → adapters), the layering contract, REST/transport conventions, and the runtime/framework matrix. USE WHEN drawing a module boundary, designing an API, wiring an integration, or planning a deploy — the interlocking rules every backend spoke shares.
backend-architecture-orchestrator
Route a backend task to the right skill among 8 server-side specialists — architecture boundaries (hexagonal/ports-and-adapters), REST API design, HTTP connector building, NestJS structure, MCP servers, deployment/CI-CD, and decision records. USE WHEN a user is designing, building, integrating, or shipping a backend service but hasn't named the specific concern.
blockchain-web3-orchestrator
Route a blockchain/web3 task to the right specialist among six — Solidity AMM security, autonomous trading-agent security, EVM token-decimal correctness, Node Keccak-256 hashing, prediction-market oracle research, and the cross-cutting market/agent risk review. USE WHEN a user is building, auditing, or wiring an EVM contract, a crypto trading agent, or a prediction-market workflow but hasn't named the specific concern.
brand-voice
Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.
building-tauri-with-github-actions
Set up Tauri CI/CD with GitHub Actions and tauri-action for cross-platform desktop builds. USE WHEN automating Tauri build, test, or release across Windows/macOS/Linux, configuring workflow triggers, or publishing signed releases.
business-content-core
Shared reference for the business-content cluster: the source-derived Voice Profile every lane reuses, the research/evidence substrate, the per-channel message contract, and the publish/market/fund/reach lane map. USE WHEN drafting any launch-, reputation-, or fundraising-sensitive content, building a Voice Profile, or planning multi-channel outbound — the interlocking conventions every spoke shares.
business-content-orchestrator
Route a business-content task to the right skill among 10 specialists — voice profiling, long-form articles, multi-platform content systems, SEO, market/competitor research, launch campaigns, investor decks/memos, investor outreach, lead intelligence, and social-graph ranking. USE WHEN a user is writing, marketing, fundraising, or doing outbound for a product or company but hasn't named the specific concern.
calling-frontend-from-tauri-rust
Call the Tauri v2 frontend from Rust via the event system, channels, and JavaScript evaluation. USE WHEN emitting events from Rust to the webview, streaming data over IPC channels, or pushing state changes from backend to frontend.
calling-rust-from-tauri-frontend
Call Rust backend functions from the Tauri v2 frontend with invoke and #[tauri::command]. USE WHEN defining commands, passing arguments or return values across IPC, handling command errors, or wiring async frontend-to-Rust calls.
compose-multiplatform-patterns
Compose Multiplatform and Jetpack Compose patterns for KMP — state management, navigation, theming, performance, and platform-specific UI. USE WHEN building shared Compose UI across Android/iOS/Desktop/Web, managing Compose state, or optimizing recomposition.
agents-sdk
Build AI agents on Cloudflare Workers with the Agents SDK — Agent class, state, callable RPC, Workflows, durable execution, queues, retries, React hooks. USE WHEN creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat or voice agents, or browser automation.
ai-video-director
Create AI-generated video content using Kling 3.0 (multi-shot sequences with dialogue), Sora (scene generation with character consistency), or Grok (restricted content). Use when writing shot-by-shot video prompts, building character-consistent animated series, or routing between video generation tools.
airflow-dag-patterns
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.
aphorisms
Aphorism management. USE WHEN aphorism, quote, saying. SkillSearch('aphorisms') for docs.
art
Complete visual content system. USE WHEN user wants to create visual content, illustrations, diagrams, OR mentions art, header images, visualizations, mermaid, flowchart, technical diagram, infographic, app icon, or pack icon.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.