Visual design intelligence and UI aesthetics. Integrates: chrome-devtools, ai-multimodal, media-processing. Capabilities: design analysis, visual hierarchy, color theory, typography, micro-interactions, animation, design systems, accessibility. Actions: analyze, design, create, capture, evaluate, implement UI aesthetics. Keywords: Dribbble, Behance, Mobbin, design inspiration, visual hierarchy, color palette, typography, spacing, animation, micro-interaction, design system, style guide, accessibility, WCAG, contrast ratio, golden ratio, whitespace, visual rhythm. Use when: building beautiful UIs, analyzing design inspiration, implementing visual hierarchy, adding animations/micro-interactions, creating design systems, evaluating aesthetic quality, capturing design screenshots.

Paul Graham的思维框架与表达方式。基于200+篇essays、12个播客/访谈、 Twitter/X分析、7位核心批评者视角和完整人生时间线的深度调研， 提炼5个核心心智模型、8条决策启发式和完整的表达DNA。 用途：作为思维顾问，用PG的视角分析创业、写作、产品和人生选择。 当用户提到「用PG的视角」「Paul Graham会怎么看」「PG模式」「paul graham perspective」时使用。 即使用户只是说「帮我用PG的角度想想」「如果PG会怎么做」「切换到PG」也应触发。

How to create and use Account (signer) in @aptos-labs/ts-sdk. Covers Account.generate(), fromPrivateKey(), fromDerivationPath(), Ed25519 vs SingleKey vs MultiKey vs Keyless, serialization (fromHex/toHex). Triggers on: 'Account.generate', 'Account.fromPrivateKey', 'Ed25519PrivateKey', 'SDK account', 'mnemonic', 'SingleKeyAccount', 'KeylessAccount'.

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.

Generate rights-cleared paid-ad product photography variants from an authorized source image and validated brand profile. Triggers on: product photo, product photography, virtual photoshoot, photoshoot, enhance product image, studio shot, lifestyle shot, lifestyle product image, floating product image, ingredient shot.

Load this skill when a user asks how to run Pulumi programmatically, embed Pulumi in an application, orchestrate multiple stacks in code, build a self-service infrastructure portal, replace pulumi CLI shell scripts with code, or use the Pulumi Automation API (LocalWorkspace, createOrSelectStack, inline programs). Also load for questions about multi-stack sequencing, parallel deployments, or passing outputs between stacks via code.

Marks a single auto-triage work-item as BLOCKED on its OWN tracker when a run hit something it could not overcome (permission denial, broken environment, timeout, unrecoverable error). Applies the `triage-blocked` label, returns the item to the queue (Todo), and comments the reason — so it leaves the auto-queue until a human resolves the cause and clears the label. Tracker- and project-agnostic: reuses the triage config + tracker binding (Linear, GitHub, …), never assumes one. The daemon calls it after DETERMINISTICALLY detecting a block; also usable as `triage-block <ITEM-ID> -- <reason>`.

Use when the user asks to "update old content", "refresh content", "content is outdated", "improve declining rankings", "revive old blog posts", "this post is outdated", "traffic is declining on this page", or "rankings dropped for this article". Identifies and updates outdated content to restore and improve search rankings. Analyzes content freshness, adds new information, updates statistics, and optimizes for current SEO and GEO best practices. For writing new content from scratch, see seo-content-writer. For auditing without rewriting, see on-page-seo-auditor.

Use when the user asks to "analyze backlinks", "check link profile", "find toxic links", "link building opportunities", "off-page SEO", "who links to me", "I have spammy links", "how do I get more backlinks", or "disavow links". Analyzes backlink profiles to understand link authority, identify toxic links, discover link building opportunities, and monitor competitor link acquisition. Essential for off-page SEO strategy. For internal link analysis, see internal-linking-optimizer. For competitor link profiles, see competitor-analysis.

Use when the user asks to "analyze competitors", "competitor SEO", "who ranks for", "competitive analysis", "what are my competitors doing", "what are they doing differently", "why do they rank higher", or "spy on competitor SEO". Analyzes competitor SEO and GEO strategies including their ranking keywords, content approaches, backlink profiles, and AI citation patterns. Reveals opportunities to outperform competition. For content-focused gap analysis, see content-gap-analysis. For link profile specifics, see backlink-analyzer.

Use when porting a hand-coded bespoke HTML page (art-directed landing, campaign site, keynote companion, one-off microsite, designer-generated "snowflake") to Adobe Edge Delivery Services with pixel-perfect fidelity, where forcing the design into EDS's standard block library would compromise the visual intent. Also use when the source is static HTML/CSS/JS with no CMS, time-boxed to hours/days, and authoring will be done by an AI agent rather than humans in Docs/SharePoint.

Extract comprehensive brand profiles from URLs, descriptions, or existing assets using a multi-tier AI analysis with web search fallback. Use when "extracting brand identity", "brand analysis", "brand profiling", or "creating brand profiles".

Grassroots-first campaign design for anyone being outspent — startups vs. incumbents, NGOs vs. corporate comms, movements vs. state-backed machines, solo brands vs. big-budget competitors. Ideates awareness, launch, fundraising, mobilization, community-build, counter-narrative, referral, founder-story, and coalition campaigns. Triggers on "campaign plan", "marketing strategy", "ad budget", "should I advertise", "paid vs organic", "launch plan", "grassroots", "low budget marketing", "NGO campaign", "outspent", "competitor has bigger budget", "how do I compete without money". Also trigger on any spend asymmetry, collapsing organic reach, rising CPAs, or a trust/credibility problem — even without the word "campaign". Nudge activation when the user debates buying ads, boosting posts, or hiring influencers; they are likely about to burn money on a channel that will not persuade.

Finds over-permissive RBAC roles and service-account token abuse paths in a Kubernetes cluster using kubectl auth can-i, rbac-police, kubectl-who-can, and rakkess, tracing which subjects can escalate toward cluster-admin. Use when reviewing who can escalate privileges in a cluster, hunting exploitable RoleBindings during an authorized review, or validating least privilege after an RBAC change. Keywords: RBAC, ClusterRoleBinding, service account token, auth can-i, rbac-police, escalate, bind, impersonate. Do not use for designing and applying hardened RBAC - use implementing-rbac-hardening-for-kubernetes.

For client and program development on Solana ~160x cheaper and without rent-exemption for per-user state, DePIN registrations, or custom compressed accounts. Create, update, close, burn, and reinitialize compressed accounts.

Load when reviewing, refactoring, modernizing, debugging, or designing non-trivial C++ code where ownership, lifetime, RAII, concurrency, templates, interfaces, exceptions, or Core Guidelines compliance may affect correctness, safety, maintainability, or performance.

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.

Set up an end-to-end test suite in any repo, following practices that make e2e a reliable per-PR gate: real flows over bypass, layered assertions, a reusable auth/session helper, video+trace evidence, and a compounding suite. Use when a repo has no e2e (or weak e2e) and you want system-level tests — "set up e2e", "add end-to-end tests", "scaffold a test gate".

Create a Telegram-ready Neva release announcement from a GitHub release payload. Use for official Neva Telegram release posts.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.