dreamlab-ai
- 163 skills
- 0 followers
- 23 hours ago last updated
- ▌ Gemini Url Context · dreamlab-aiExpand and analyze URLs using Google Gemini 3.8 Flash URL Context API. Efficiently fetches, summarizes, and extracts information from up to 20 URLs per request with grounding metadata and source citations. Use when analysing or summarising specific URLs using Gemini's 1M-token context window.
- ▌ Github Code Review · dreamlab-ai bundleMulti-agent code review for GitHub PRs. Use when reviewing a pull request, running security/performance/architecture/style checks on a diff, or coordinating specialized review agents and posting findings back to a PR.
- ▌ Hive Mind Advanced · dreamlab-ai bundleQueen-led multi-agent coordination in Claude Flow — one strategic queen directs specialized workers through structured voting and shared persistent memory. Use when a task needs formal consensus (majority, weighted, or Byzantine fault tolerance) and cross-agent collective memory, not just topology-based swarming.
- ▌ Architecture Studio · dreamlab-ai bundleAEC (Architecture, Engineering, Construction) studio for building and site work. Use when designing a building, planning or assessing a site, running NYC zoning or property due diligence, programming workplace space from headcount, comparing material sustainability (EPD/embodied carbon), building FF&E schedules, or writing CSI specifications — the physical-building AEC domain, not software architecture or UI design. Entry point: /studio [task], or call any sub-skill directly.
- ▌ Flow Nexus Platform · dreamlab-aiManage Flow Nexus cloud platform resources — authentication, E2B sandboxes, app/marketplace deployment, credits & billing, coding challenges. Use when a task targets a Flow Nexus account. Requires credentials; not installed here by default.
- ▌ Perplexity Research · dreamlab-ai bundleLive web research through Perplexity's closed synthesis engine — structured web results, deep multi-step investigations with reasoning, and quick sonar answers. Use when you need authoritative primary sources (gov/academic), academic citation discovery, or UK ecology/policy lookups; reach for it as the secondary engine after ceramic-search, or alongside it for important queries.
- ▌ Podcast Bulk Ingest · dreamlab-aiBulk backfill markdown transcript files for a YouTube podcast series. Downloads transcripts, show notes, and links for all episodes in a date range, then runs source extraction and applies enrichment tables. Designed for one-off historical backfill — for ongoing weekly ingest, see podcast-knowledge-ingest. When the podcast covers a domain not yet in the ontology, guides the user through OntoCast-based ontology bootstrapping.
- ▌ Provenance Tracking · dreamlab-aiAdd provenance tracking to any research or analysis output. Use when you need source verification, citation tracking, or evidence chains. Creates a .provenance.md sidecar documenting sources, verification status, and confidence levels. Integrates with RuVector.
- ▌
- ▌ UI UX Pro Max Skill · dreamlab-ai bundleUI/UX design intelligence for web and mobile: recommends styles, colour palettes, font pairings, layouts, and chart types, plus stack-specific implementation guidance (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Use when designing, building, reviewing, or refining a UI — landing pages, dashboards, admin panels, SaaS, e-commerce, portfolios, mobile apps — or when choosing palettes, typography, components, spacing, animation, or accessibility fixes. Not for backend-only code, 3D (blender), text-to-image (comfyui), or diagrams (mermaid-diagrams).
- ▌ Host Webserver Debug · dreamlab-ai bundleTrigger on "https bridge", "CORS error accessing host", "debug host webserver", "reach host dev server from container", or needing a secure-context (HTTPS) origin for a host HTTP server (Vite/Next/Express on the Docker host). Stands up a self-signed HTTPS bridge that proxies container→host so browser secure-context APIs work. NOT for general browser automation, screenshots, form filling, or scraping (use the browser/playwright skills — this skill delegates all browser work to the browsercontainer sidecar), NOT for API testing without a browser (use curl), and NOT for apps that are not on the Docker host.
- ▌ Performance Analysis · dreamlab-ai bundlePerformance analysis, bottleneck detection, and optimisation for Claude Flow swarms. Use when profiling swarm performance, diagnosing slow agents, or tuning topology and resource allocation.
- ▌ SEO Analysis · dreamlab-ai bundleFull SEO audit: Google Search Console data + technical crawl + search intent analysis. Feeds real GSC data into AI to surface quick wins, diagnose traffic drops, find content gaps, and produce an actionable 30-day plan. Use this skill whenever the user asks about SEO, search rankings, organic traffic, Google Search Console, keyword performance, traffic drops, content gaps, search visibility, or technical SEO. Also trigger on: "why is my traffic down", "what keywords am I ranking for", "improve my rankings", "check my search console", "SEO audit", "analyze my SEO", "technical SEO", "meta tags", "indexing issues", "crawl errors", "content strategy", "keyword cannibalization", "search intent", or any organic search question. If in doubt, trigger. This skill handles everything from quick GSC checks to deep technical audits.
- ▌ Verification Quality · dreamlab-ai bundleVerify an installed artifact against the signed witness manifest via `ruflo verify`, and read the real in-CI regression-guard stack (smoke tests, discoverability audit, cryptographic witness, temporal history). Use when you need to check that documented fixes are still present in the tree, or to understand what's actually enforced in CI vs. designed-but-unshipped. Not for per-file truth scoring, confidence thresholds, or auto-rollback — that surface is design only, see references/design-aspirational.md.
- ▌ Agentdb Vector Search · dreamlab-ai bundleUse when building RAG pipelines, running semantic/similarity vector search, optimising search speed, tuning HNSW indexing or quantization, or scaling to millions of vectors with local AgentDB. Covers CLI, TypeScript API, caching, batch operations, and MCP integration. NOT for distributed multi-database/QUIC sync or RL training plugins (use agentdb-advanced), conversation-memory patterns (use agentdb-memory-patterns), plain full-text search, or cloud vector services (Pinecone/Weaviate).
- ▌ Voyager Skill Library · dreamlab-ai bundleStore and retrieve verified, executable Python skill primitives (a function plus assertions plus at least one example) in the code-harness procedural memory tier. Use when a reusable utility, parser, validator, or algorithm has proven general-purpose across tasks and should be verification-gated and persisted for future reuse, or when retrieving such helper functions at task start to inject as a CodeAct prelude. Covers the VerificationGate write path, the VerifiedSkill record schema, immutable versioning, and task-start retrieval — details in the body. Not for one-off scripts, project-specific domain logic, or functions using banned APIs (subprocess, socket, ctypes, os.system) that cannot pass the VerificationGate.
- ▌ Expel Lesson Extractor · dreamlab-ai bundleFires as a post-task hook after a non-trivial completed task (3+ tool calls, observable terminal outcome) to distil 0-N generalisable IF/THEN lessons from the trajectory and store them in RuVector so they surface at the start of similar future tasks; also invocable manually to record a lesson after a complex or failed task. NOT for trivial (<3 tool calls) or interrupted tasks, and NOT a general memory-write tool — it writes only ex:DistilledLesson records to the code-harness-lessons namespace. Schema, gates, prompt, and contradiction/archive policy live in references/.
- ▌ Content Writer · dreamlab-ai bundleWrite SEO-optimized blog posts, landing pages, and content improvements following Google's E-E-A-T and Helpful Content guidelines. Handles new content creation from a keyword or topic, and improving existing pages. Use when asked to "write a blog post", "create a landing page", "improve this page", "write content about X", "content for keyword X", "draft an article", "blog post about", "landing page for", "service page", "product page copy", "rewrite this page", "make this page rank better", "content brief", "how-to guide", "listicle", or any content creation or improvement task for a website.
- ▌ Agentdb Memory Patterns · dreamlab-ai bundleImplement persistent memory patterns for AI agents using AgentDB — session memory, long-term storage, pattern learning, hierarchical memory, consolidation, ReasoningBank migration. Use when building stateful agents, chat systems, or intelligent assistants. NOT for distributed multi-DB/QUIC sync or RL algorithms (use agentdb-advanced), vector-search perf tuning (use agentdb-vector-search), or non-persistent session state.
- ▌ Bencium Impact Designer · dreamlab-aiDEPRECATED — replaced by bencium-creative. Use bencium-creative with --design flag for bold creative UX and --build flag for production frontend implementation.
- ▌ Human Architect Mindset · dreamlab-ai bundleSystematic architectural thinking for the decisions AI can't own — domain modeling, systems thinking, constraint navigation, AI-aware decomposition. Use when facing system design, technology choices, integration or breaking-change planning, or any decision spanning multiple components, teams, or compliance boundaries. Trigger proactively on system design, architecture discussions, technology choices, problem decomposition, integration planning, or breaking-change discussions.
- ▌ Toprank Upgrade · dreamlab-aiUpgrade toprank skills to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade toprank", "update toprank skills", or "get latest version". Also handles inline upgrade prompts when a skill detects UPGRADE_AVAILABLE at startup.
- ▌ Bencium Code Conventions · dreamlab-aiBence's personal code style, tech stack, and workflow conventions for his own projects. Use ONLY when the active project is identified as Bence's own repository (explicitly named as his, or the user identifies themselves as Bence) — not general React/Next.js/TypeScript/Tailwind guidance for other users' work, even when the tech stack overlaps.
- ▌ Podcast Knowledge Ingest · dreamlab-ai bundleTrigger on "/podcast-ingest", "weekly podcast ingest", "process new podcast episodes into the ontology", or setting up/debugging the podcast-cron schedule. Weekly cron that downloads new episodes from configured YouTube podcasts, extracts evidence-backed assertions via the Ontology Loom (Qwen 3.8), verifies them with Perplexity, and lands them on podcast-evidence ledger pages. Also trigger on "promote podcast evidence", "ledger promotion", or "podcast candidate dossiers" — the podcast-promote binary stage that pre-filters accumulated ledger evidence into scored proposal dossiers. NOT for one-off historical backfill (use podcast-bulk-ingest), interactive on-demand transcript fetching (use youtube-transcript-archiver), or non-podcast KG enrichment.
- ▌ Renaissance Architecture · dreamlab-ai bundleFirst-principles architecture and UI/UX guidance for building genuinely new software rather than derivative "X-but-for-Y" work. Use when designing or architecting a feature, choosing a stack or framework, reviewing a design, or in strategy discussions — to check whether complexity is earned, tools fit the problem, and the thing is a creation not a commentary.
- ▌ Keyword Research · dreamlab-ai bundleDiscover, analyze, and prioritize keywords for SEO and GEO content strategies. Identifies high-value opportunities based on search volume, competition, intent, and business relevance. Generates topic clusters and content calendars. Use when asked to "find keywords", "keyword research", "what should I write about", "keyword analysis", "find me topics to write", "search volume", "keyword difficulty", "content ideas", or any keyword discovery task.
- ▌ Github Project Management · dreamlab-ai bundleUse when creating GitHub issues, managing project boards, planning sprints, decomposing work into vertical-slice tracer bullets, or triaging an issue backlog with swarm coordination. NOT for PR review (use github-code-review), release versioning (use github-release-management), CI/CD workflows (use github-workflow-automation), or cross-repo sync (use github-multi-repo).
- ▌ Github Release Management · dreamlab-ai bundleOrchestrate GitHub releases end-to-end: version bumps, changelog/release-note generation, multi-platform builds, staged deployment, and rollback. Use when cutting a release, generating a changelog, coordinating a multi-package or multi-repo release, or running an emergency hotfix.
- ▌ Vanity Engineering Review · dreamlab-ai bundleIdentifies code, architecture, and technical decisions built to impress rather than to ship. Use when checking for over-engineering, unnecessary complexity, or vanity architecture decisions. Reviews codebases, PRs, and architecture proposals for unjustified complexity and resume-driven choices.
- ▌ Github Workflow Automation · dreamlab-ai bundleAutomate GitHub Actions workflows and CI/CD pipelines with claude-flow swarm coordination. Use when creating, optimizing, or debugging GitHub Actions workflow YAML, CI/CD pipelines, or GitHub repository automation — not for PR code review, releases, issues, or multi-repo sync (see the github-* sibling skills).
- ▌ Meta Tags Optimizer · dreamlab-ai bundleOptimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media preview", "my click rate is low", "title optimization", or any meta tag task.
- ▌ Youtube Transcript Archiver · dreamlab-aiBatch-download YouTube channel transcripts, show notes, and links as markdown files. Enriches each file with source extraction from transcripts, cross-checked via Haiku, and optionally downloads referenced reports/papers to a local assets directory. Designed for podcast and video series archival.
- ▌ Geo Content Optimizer · dreamlab-aiOptimize content for AI citations (ChatGPT, Perplexity, AI Overviews, Gemini, Claude, Copilot) inside a toprank SEO workflow. Use when the task needs "optimize for AI", "get cited by ChatGPT", "GEO optimization", or "appear in AI answers" AS PART OF a broader SEO engagement (alongside seo-analysis, keyword-research, content-writer). For AI-citation work with NO SEO context, use `bencium-aeo` directly — this skill's technique library now lives there.
- ▌ Bencium Controlled UX Designer · dreamlab-ai bundleCollaborative UI/UX design guidance for building unique, accessible, non-generic web interfaces. Use when building or styling web components, pages, or apps and making visual decisions about colour, typography, layout, motion, or accessibility — especially when the goal is to break away from generic AI/SaaS-template aesthetics.
- ▌ Schema Markup Generator · dreamlab-ai bundleGenerate JSON-LD structured data markup for rich results in Google Search. Supports FAQ, HowTo, Article, Product, LocalBusiness, and multi-type schemas. Validates against Google requirements and provides implementation guidance. Use when asked to "add schema markup", "generate structured data", "JSON-LD", "rich snippets", "FAQ schema", "product markup", "add structured data to my page", "how to get rich snippets", or any structured data task.
- ▌ Studio · dreamlab-ai bundleSmart router — describe your task and get routed to the right agent or skill. Start here if you don't know which skill to use.
- ▌ History · dreamlab-ai bundleNeighborhood context and history — adjacent uses, architectural character, landmarks, commercial activity, and planned development from an address.
- ▌ Skills Menu · dreamlab-ai bundleShow all available skills, agents, and how to use them — organized by task.
- ▌ Nyc Acris · dreamlab-ai bundleLook up ACRIS property transaction records — deeds, mortgages, liens.
- ▌ Epd Parser · dreamlab-ai bundleParse EPD (Environmental Product Declaration) PDF documents to extract structured environmental impact data — GWP, life cycle stages, certifications, and compliance metrics.
- ▌ Spec Writer · dreamlab-ai bundleCSI outline specification writer — takes a materials or products list and generates structured specs with MasterFormat divisions, performance criteria, and acceptable manufacturers.
- ▌ Epd Compare · dreamlab-ai bundleCompare 2+ products side-by-side on environmental impact metrics. Normalizes declared units, checks system boundary alignment, and flags LEED MRc2 compliance.
- ▌ Epd To Spec · dreamlab-ai bundleGenerate CSI-formatted specification sections requiring EPDs and setting maximum GWP thresholds. References ISO 14025, ISO 21930, EN 15804.
- ▌ Epd Research · dreamlab-ai bundleSearch for EPDs by product category, CSI division, or material type. Finds EPDs from EC3, program operator registries, and manufacturer sites.
- ▌ CSV To Sif · dreamlab-ai bundleConvert a CSV or Excel FF&E product list to SIF (Standard Interchange Format) for dealer and procurement systems.
- ▌ Sif To CSV · dreamlab-ai bundleConvert a SIF (Standard Interchange Format) file to a clean, readable CSV or Google Sheet.
- ▌ Mobility Analysis · dreamlab-ai bundleTransit and mobility site analysis — subway, bus, bike, pedestrian infrastructure, walk scores, and airport access from an address.
- ▌ Zoning Envelope · dreamlab-ai bundleGenerate interactive 3D zoning envelope viewers from zoning analysis reports. Requires a zoning analysis report as input.
- ▌ Product Pair · dreamlab-ai bundleSuggest complementary products that pair well with a given item — side tables for sofas, task lights for desks, etc.
- ▌ Workplace Programmer · dreamlab-ai bundleAI workplace strategy consultant that builds office space programs through conversation — area splits, room schedules, seat counts, and reports.
- ▌ Product Match · dreamlab-ai bundleFind visually or functionally similar products from an image, name, or description.
- ▌ Nyc Property Report · dreamlab-ai bundleCombined NYC property report — landmarks, DOB permits, violations, ACRIS records, HPD, and BSA variances.
- ▌ Product Enrich · dreamlab-ai bundleAuto-tag FF&E products with categories, colors, materials, and style tags using AI.
- ▌ Slide Deck Generator · dreamlab-ai bundleGenerate a polished HTML slide deck from a topic, outline, or data. Outputs a self-contained .html file with keyboard/touch navigation, responsive typography, and the ALPA (Alpaca Labs) design system — Helvetica, editorial layout, clean white backgrounds.
- ▌ Demographics Analysis · dreamlab-ai bundleDemographics and market site analysis — population, income, age, housing market, and employment data from an address.
- ▌ Zoning Analysis Nyc · dreamlab-ai bundleAnalyze zoning envelope rules for lots in New York City using PLUTO data and the NYC Zoning Resolution
- ▌ Product Research · dreamlab-ai bundleFF&E product research — receives a brief from the designer, searches the web for matching products, and returns structured candidates to save to the master Google Sheet.
- ▌ Environmental Analysis · dreamlab-ai bundleClimate and environmental site analysis — temperature, precipitation, wind, sun angles, flood zones, seismic risk, soil, and topography from an address.
- ▌ Color Palette Generator · dreamlab-ai bundleColor palette generator — creates harmonious color palettes from descriptions, moods, or images. Outputs a self-contained HTML file with swatches, hex/RGB/HSL codes, contrast ratios, and example pairings.
- ▌ Zoning Analysis Uruguay · dreamlab-ai bundleAnalyze zoning envelope rules for lots in Maldonado, Uruguay using GIS data and TONE regulations
- ▌ Product Image Processor · dreamlab-ai bundleDownload, resize, and remove backgrounds from product images at scale
- ▌ Product Spec Bulk Fetch · dreamlab-ai bundleFetch structured FF&E product specs from a list of URLs. Extracts name, brand, dimensions, materials, price, and images into a standardized schedule.
- ▌ Product Spec PDF Parser · dreamlab-ai bundleExtract structured FF&E product specs from PDF files — price books, fact sheets, and spec sheets. Claude reads extracted text and structures products into a standardized schedule.