Claude Skills by NeverSight

Run a comprehensive health audit across all skills — checks staleness, safety guards, cross-skill consistency, context efficiency, step compliance, and learning pipeline. Use when you want to verify skill quality, after bulk skill edits, or as a periodic maintenance check.

Process Obsidian Ideas.md inbox — route ideas to project roadmaps. NOT for direct roadmap edits or reviews.

Evidence-based completion check before claims persist to persistent state, session notes, or roadmap. Use BEFORE writes that say items are done, BEFORE answering 'how much is done?', or before any multi-item completion claim.

Emit and maintain a dagr run file — a live, contract-valid JSON description of recursive projects, tasks, attempts, gates, evidence, policies, events, and operator-message resolutions that `dagr view` renders as a DAG. Use when orchestrating agents or tracking multi-step work that a dagr pane should display.

Use when acting as an AEM Experience Solution Consultant (XSC) — designing demo plans, scripting AI agent flows, building custom demo environments, selecting repos and MCP tools, explaining DA vs Universal Editor authoring, answering "how do we show X to customer Y?", or doing any AEM technical presales work for ASO, AI Agents, LLMO, CSC, EDS/XWalk, or DMwOA.

Use only when the task explicitly mentions the historical basic-admin foundation, basic-admin plan/progress docs, or drift between old stage notes and the current admin surface. This helper forces current page scope back to owner docs instead of historical phase notes.

Enforce the pveCloud document-first workflow. Use whenever work may change API, schema, frontend behavior, permissions, config, deployment, business process, or AI collaboration workflow/skills. This skill defines AI workflow only and never replaces project contracts in docs/, migrations, or config.example.yaml.

Trigger this skill when the user expresses intent to create, manage, or query a virtual card. This includes intents such as: - "get a virtual card" - "create a card" - "card status" - "set up a card for an agent" Also, any request involving the creation of a one-time-use virtual Visa/Mastercard funded with cryptocurrency for agent use.

Comprehensive skill for Evolution API - open-source WhatsApp integration platform with multi-service chatbot and automation support

Identify, evaluate, and prioritize design opportunities using impact-effort frameworks and strategic criteria.

Search, score, and compare flights with jetlag impact analysis.

Local dev E2E environment — Aerospike in container, Backend + Frontend running locally

Build aerospike-py and run sample-fastapi integration tests to verify changes work in a real FastAPI application

한 repo의 변경이 다른 repo에 미치는 영향을 분석하고, 업데이트 체크리스트를 제공

Run all remaining phases autonomously — discuss→plan→execute per phase

Capture ideas, tasks, notes, and seeds to their destination

Retroactively audit and fill Nyquist validation gaps for a completed phase

Configure the enhanced statusline in Claude Code settings. Run this once after installing the plugin.

Use when a user wants to sell an API, monetize an endpoint, set up a paid API, become an x402 provider, add payment gating to their HTTP service, or deploy an ag402 gateway in front of their backend

Aplica mejoras transformacionales de UX móvil sobre componentes existentes. Agrega haptic feedback, drag-to-dismiss en sheets, swipe gestures, pull-to-refresh, skeleton loaders, tactile feedback (active:scale), safe-area handling, y ajustes de touch targets. Úsalo después de mobile-audit para corregir los issues encontrados, o sobre un componente específico que quieras llevar a calidad premium.

Audit and optimize SEO for static portfolio/personal websites. Use when the user mentions SEO, search visibility, meta tags, schema markup, sitemap, robots.txt, Open Graph, search rankings, Google indexing, or wants their site to show up in search results. Also trigger on "why can't I find my site on Google" or any search discoverability concern.

Enforces clear, unambiguous, testable, FULL-STACK specification writing rules for Phase II web applications (Frontend + Backend + Auth + Database). Apply before any code is written.

Bubble.io plugin development rules, API reference, and coding standards. Use when working on any task in this repo: writing, reviewing, refactoring, or creating initialize.js, update.js, preview.js, header.html, element actions, client-side actions, server-side actions (SSA), Plugin API v4 async/await code, JSDoc, setup files, README, CHANGELOG, marketplace descriptions, or field tooltips. Also use for security audits, code review, debugging, and publishing plugins. Covers instance/properties...

Estimates the FTE capacity, role mix, seniority, utilization, and delivery load required for agency scopes, campaigns, CRM programs, media operations, or retained services. Applies a 70/30 AI-to-human operating model where 70% of task volume is handled by AI agents and 30% requires human judgment. Use when asked to size a team, build a staffing plan, estimate headcount, design a pod structure, check capacity, or determine if a fee can support a team. Also trigger when someone says "how many p...

Diagnoses why campaigns, CRM journeys, media plans, funnels, landing pages, apps, or business KPIs are underperforming. Use when performance is below target, costs rise, conversion falls, delivery is weak, CRM response drops, creative fatigues, or leadership needs root-cause analysis. Also trigger when someone says "why is performance down?", "CPA is rising", "ROAS dropped", "leads are bad", "what happened?", "diagnose the campaign", or "performance recovery plan". Even casual phrasing like "...

Diagnoses current price-pack assortment, identifies white spaces and improvement opportunities. Trigger when asked to: analyze SKU portfolio, map competitive landscape by price-pack, find white spaces in assortment, evaluate coverage across price tiers, diagnose PPA gaps by channel or region, or benchmark own portfolio vs competitors. Also trigger for: "PPA", "price pack architecture", "surtido", "portafolio de SKUs", "espacios en blanco", "white space", "brechas de precio", "análisis de empa...

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature.

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol.

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.

Engineering operating model for teams where AI agents generate a large share of implementation output.

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.

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.

Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is.

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.

Evidence-first automation inventory and overlap audit workflow for ECC. Use when the user wants to know which jobs, hooks, connectors, MCP servers, or wrappers are live, broken, redundant, or missing before fixing anything.

Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks (Hermes, AutoGPT) by leveraging Claude Code's native crons, dispatch, MCP tools, and memory. Use when the user wants continuous autonomous operation, scheduled tasks, or a self-directing agent loop.

Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.

Use this skill when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where screenshots alone are not enough.

Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is comple...

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.

Use this skill to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance regressions after deploys, merges, or dependency upgrades. Smoke / canary / post-deploy verification.

Codified expertise for managing carrier portfolios, negotiating freight rates, tracking carrier performance, allocating freight, and maintaining strategic carrier relationships. Informed by transportation managers with 15+ years experience. Includes scorecarding frameworks, RFP processes, market intelligence, and compliance vetting. Use when managing carriers, negotiating rates, evaluating carrier performance, or building freight strategies.

Cisco IOS and IOS-XE review patterns for show commands, config hierarchy, wildcard masks, ACL placement, interface hygiene, and safe change-window verification.

Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any major refactor touching shared state stores.

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.