dreamers-laboratory
- 30 skills
- 0 followers
- 2 hours ago last updated
- ▌ AWS Static Site · dreamers-laboratory bundlePlan, provision, deploy, or audit a guarded AWS static website using S3, ACM, Route53, and CloudFront. Use when the agent is asked to make a static site live on AWS, create or review an S3/CloudFront/ACM/Route53 setup, publish a local static site, debug a static-site AWS deployment, or prepare a safe deployment plan with rollback. Includes account-verification guardrails, read-only-by-default AWS CLI handling, and target-aware-security requirements for public cloud/DNS changes.
- ▌ Get Stats · dreamers-laboratory bundleCompute required descriptive and inferential statistics for measured samples. Use when the agent is analyzing latency, throughput, event timing, experiment baselines, A/B effects, benchmark results, production-vs-baseline comparisons, or any numeric measurement where outputs must include sample count, min, max, mean, median, standard deviation, standard error when relevant, confidence intervals when useful, and t-tests for measured effects.
- ▌ Target Aware Security · dreamers-laboratoryApply an adversarial security posture to infrastructure, server, database, DNS, firewall, credential, deployment, and automation work. Use when the agent is changing or reviewing anything exposed to networks or other users, handling secrets, creating public URLs, configuring SSH/sudo/systemd/databases/cloud/DNS, or when the user says security is important, the host is a target, or attack vectors must be considered.
- ▌ Directory Management · dreamers-laboratoryKeep working directories clean with minimal files and no unnecessary copies. Use when the agent is asked to clean, organize, declutter, deduplicate, archive, prune, or consolidate folders; create or manage temporary scripts, previews, logs, manifests, generated analysis, backups, CSV/XLSX exports, screenshots, drafts, or stale historical versions; decide where temporary artifacts should live; or prevent a tool or skill from creating a relative project-local `tmp/` folder for scratch work.
- ▌ Frontend Design · dreamers-laboratoryCreate distinctive, production-grade frontend interfaces for web components, pages, and applications. Use when the agent needs to design or implement frontend UI with a strong visual point of view, polished interaction details, responsive layout, and real working code, especially when the request risks drifting into generic AI-looking design. Preserve existing design systems when they already exist; otherwise establish a clear aesthetic direction and execute it consistently.
- ▌ Responsive Design · dreamers-laboratory bundleMake web pages and application UIs hold up across a fixed 10-viewport suite with screenshot-based validation. Use when the agent needs to implement or review responsive behavior, adapt a frontend for phone, tablet, laptop, desktop, ultrawide, or odd aspect ratios, remove overflow or overlapping text, rebalance crowded layouts and accidental whitespace, or replace brittle breakpoint-only fixes with fluid sizing and spacing.
- ▌ Git Deploy Release · dreamers-laboratoryDisciplined git, release, and deployment workflow. Use when the agent is asked to commit, push, branch, merge, release, deploy, publish, clean up git state, or prepare production web changes; enforces main-first work, semantic version increments when present, local testing before deploy, live testing after deploy, and neutral branch/commit naming.
- ▌ Cloudflare Static Site · dreamers-laboratoryPlan, provision, deploy, migrate, or audit a static site on Cloudflare (Pages, DNS, Redirect Rules, Workers). Use when the agent is asked to host a static site or SPA on Cloudflare Pages, move a domain's DNS from Route53 to Cloudflare, set up a Pages custom domain, build redirects between hosts, retire an S3/CloudFront/ACM stack in favour of Pages, or debug a Cloudflare-hosted site that serves stale content. Includes account guardrails, an email-safe DNS migration gate, and the service-worker and cache traps specific to Pages.
- ▌ Arxiv Researcher · dreamers-laboratory bundleFind and digest recent research papers through the alphaXiv MCP server (discover_papers, get_paper_content, answer_pdf_queries, researcher and library tools), with an arXiv/OpenAlex fallback when the MCP is not configured. Token-aware by design. The agent frames a token budget per goal before reading anything, keeps a ledger, and reads abstracts before reports before full text. Offers OpenResearch (openresearch.sh) autoresearch as an option when the question is empirical and the user has code to run it against. Use when the user asks what is new on a topic, wants a literature scan, needs the latest method for a problem, wants a specific paper read or queried, or wants to find who works on something.
- ▌ Scientific Rigor · dreamers-laboratoryDesign, run, and evaluate controlled empirical experiments with one variable changed at a time, explicit hypotheses, reproducible protocols, statistical significance checks such as t-tests where appropriate, and conclusions backed by measured evidence. Use when the agent is planning or judging performance tests, latency experiments, A/B comparisons, benchmark runs, optimization claims, production-vs-baseline comparisons, or any investigation where assumptions must be minimized and results must be statistically defensible.
- ▌ Automated Test Case · dreamers-laboratory bundleDesign, implement, and empirically verify high-value automated regression tests against historical application defects. Use when the agent must mine issue history, cluster recurring failure modes, build code or data-integrity tests, and prove each claimed catch by failing on the historical defect while passing on corrected application code.
- ▌ Webapp Rigorous Testing · dreamers-laboratoryRigorously verify web application changes before claiming they are done. Use when the agent builds, debugs, reviews, deploys, or regression-tests any web UI, browser flow, API-backed page, or full-stack web feature and must prove behavior with multiple checks such as code audit, targeted tests, Playwright/browser automation, screenshots, raw API probes, and post-deploy live verification.
- ▌ PDF Form Entry And Verification · dreamers-laboratory bundleFill, stamp, or prepare PDF forms only when visual alignment matters. Use when the agent needs to add text to PDF forms, prefill government/vendor PDFs, prepare sign-ready packets, repair bad PDF fills, center text in boxes, or verify that generated PDFs look correct from rendered page screenshots before sharing or attaching them.
- ▌ Adversarial Review Loop · dreamers-laboratoryRun a clean-room adversarial review loop on any artifact until fresh reviewers come back clean — software, websites, designs, proposals, documents, diagrams, pricing, presentations, emails, anything with a "done" state. Use this skill whenever the user asks to review until clean, red-team, poke holes, stress-test, "make it squeaky clean," QA rigorously, get a second opinion, or run reviewers/subagents on something — and proactively before declaring ANY substantial deliverable finished, ready, or submission-ready, even if the user never says the word "review."
- ▌
- ▌ Task Cost · dreamers-laboratory bundleMeasure the weight of one agent task from explicit start and finish snapshots. Use when the user asks for task cost, token usage, elapsed time, model and reasoning configuration, subagent cost, account-usage percentage change, or a concurrency-adjusted estimate of how much usage one task consumed. Currently supports the OpenAI Codex CLI's local session state; the measurement pattern generalizes to any agent runtime that logs per-session token snapshots.
- ▌ Find Flights · dreamers-laboratoryBuild decision-ready flight plans from live fare searches. Use when the agent needs to compare one-way, round-trip, or piecemeal flight builds across aggregators, airline-direct sites, and credit-card travel portals; evaluate hard constraints such as weddings, must-arrive-by times, max duration, stop count, airport flexibility, passenger count, cabin/bag needs; and treat points as money by checking whether portal fares are competitive or inflated.
- ▌ Skill Sync · dreamers-laboratory bundleFind every place agent skills live on this machine (Claude Code, Codex, Cursor; user-level and project-level) and bring them into sync, bidirectionally, newest copy wins. Use when the user asks to sync skills between tools, says a skill is missing or stale in one tool, wants to know which tools share a skills directory, or after editing a skill that other tools should see. Reports before it changes anything; backs up anything it overwrites; never deletes.
- ▌ Security Audit · dreamers-laboratoryPerform a general Linux security breach check and compromise audit. Use when the agent is asked to audit a Linux server for unauthorized access, bad actor SSH keys, suspicious users, privilege escalation, persistence, suspicious processes/services, network listeners, containers, writable temp-path activity, or post-compromise access cleanup via SSH, console, GRUB, initramfs, or rescue/live boot.
- ▌ Nice And Concise · dreamers-laboratoryWrite and answer laconically and tersely, with maximum information density — decide the full set of facts first, then express them in the fewest words. Use for every deliverable and reply (proposals, content, memos, demos, docs, chat) and alongside any drafting skill. Dense ≠ less information; it means no filler.
- ▌ Codex Handoff · dreamers-laboratoryCollaborate with OpenAI Codex, through its own app or CLI, as a respectful second-opinion partner for engineering, refactor review, analysis, verification, and gap analysis. Use when the user asks another agent to talk to Codex, hand work to Codex, learn from Codex's output, compare Codex's critique, get Codex's implementation or debugging ideas, or use Codex as a peer reviewer before finalizing an artifact.
- ▌ Content Generator · dreamers-laboratoryResearch, draft, revise, and verify high-authority website content pages. Use when the agent needs to create or substantially update SEO/GEO/LLM-readable content, technical explainers, service pages, education pages, work pages, landing pages, FAQ sections, or long-form site copy that should be current, source-grounded, non-generic, readable, and aligned to an existing site voice.
- ▌ Claude Handoff · dreamers-laboratoryCollaborate with Claude, through its own app or CLI, as a respectful second-opinion partner for formatting, diagrams, document and deck review, writing, visual critique, and gap analysis. Use when the user asks another agent to talk to Claude, hand work to Claude, learn from Claude's output, compare Claude's critique, get Claude's formatting or design ideas, or use Claude as a peer reviewer before finalizing an artifact.
- ▌ Usage Analysis · dreamers-laboratory bundleRead and analyze live OpenAI Codex account usage limits from the local authenticated app server. For users of the OpenAI Codex app/CLI only. Use when the agent needs to report current 5-hour or weekly usage, reset times, average weekly percentage used per elapsed day, sustainable percentage remaining per day, pace against the window, or available reset credits without opening the GUI.
- ▌ Build Demo · dreamers-laboratory bundleEvaluate, plan, build, verify, and optionally deploy source-grounded evaluator demos that help win proposals, RFQs, RFPs, and sales pursuits. Use when the agent must decide whether a demo helps or harms a pursuit, extract the verbatim source language a demo must serve, plan an evaluator demo, build and test a static demo, deploy it to static hosting, or hand a proposal agent instructions for incorporating the demo and its screenshots. This workflow intentionally excludes analytics, tracking, Search Console, and SEO campaigns.
- ▌ Context Sharing · dreamers-laboratoryCreate a secret-safe project context handoff file in /tmp for another model, agent, thread, or teammate. Use when the agent needs to summarize everything relevant to an overall objective across repositories, docs, dashboards, deployment systems, access paths, credentials, live services, open decisions, blockers, and next actions, especially before handing off complex work or preserving project state.
- ▌ Model Comparison · dreamers-laboratory bundleSource-grounded AI model comparison workflow for comparing frontier LLMs, coding agents, chatbots, and unreleased or preview models. Use when the agent needs to research model benchmarks, verify published model claims, build coding, general-task, or design benchmark tables, compare OpenAI/Anthropic/Google/xAI/Meta/Mistral/DeepSeek or similar models, update model-comparison content pages, or explain uncertainty around unpublished, gated, preview, or rumored models.
- ▌ Gsc Indexing · dreamers-laboratory bundleBuild sitemap-based Google Search Console indexing queues, inspect URLs, request indexing until quota is hit, and update Google Sheets trackers across one or many verified properties.
- ▌ SEO Auditing · dreamers-laboratory bundleAudit and improve technical SEO and organic-search performance for small and medium websites, including Search Console, GA4, rendering strategy, raw HTML crawlability, metadata, canonical URLs, redirects, sitemaps, robots directives, JSON-LD, internal links, social previews, accessibility, and Core Web Vitals. Use when the agent builds, reviews, launches, migrates, or diagnoses indexing, traffic, CTR, conversions, or performance for a public website.
- ▌ LLM To Human · dreamers-laboratoryConvert LLM-sounding prose into plain human English on any user-facing text — proposals, web copy, demos, docs, UI strings, emails, slides. Run as the final pass of every drafting skill. Includes the nice-and-concise process; density stays, machine tells go.