Coding & Development
google-ads-profit
Profit-first Google Ads for WooCommerce shops, including which new countries are worth advertising in. Connects the user's own Google Ads, GA4, Search Console and WooCommerce (everything runs on this computer; keys never leave it), measures real profit after ad spend from shop orders and product costs, finds wasted spend (search terms, products, brand, campaigns below break-even) and proposes changes that are made only after the user says yes, each with one-step undo and a 14-day evaluation. Use when the user asks about Google Ads profit, wasted ad spend, an ads audit, which markets/countries to advertise in (search demand and click prices per country via Keyword Planner or DataForSEO), ROAS or break-even, negative keywords, Shopping products, brand campaigns, or wants to connect Google Ads / GA4 / Search Console / WooCommerce.
$ npx skills add Woo2Woo/google-ads-profitawesome-checklists
Review software and AI projects with evidence-based checklists. Use for code audits, gap analysis, and release readiness.
$ npx skills add Pro-GenAI/awesome-checklistsurban-planning
Develop and review neighborhood-scale urban plans using site evidence, maps, photos, terrain, local rules, and everyday needs. Use for urban design, public space, walking and cycling networks, transit access, green infrastructure, or substantive reviews of an existing plan or its public website, maps, and visual comparisons.
$ npx skills add daniilak/urban-planningfable-method
Complete work method distilled from Claude Fable 5 — how it diagnoses, decomposes hard tasks, verifies its own work, communicates, and decides what to do next. Use at the start of any non-trivial engineering task (multi-step change, debugging, audit, integration, design decision) or when asked to work "like Fable".
$ npx skills add rbenitezm/claude-baseunit-testing
Guidelines for designing, writing, reviewing and improving language-agnostic unit tests: test cases, edge cases, test doubles (mocks, stubs, fakes), flaky or fragile tests, missing scenarios. Use whenever the user asks to add, fix, review or extend tests, cover a function with tests, or reports a flaky or failing test, even if they do not say "unit test". If a language-specific unit-testing skill is available, use it together with this one. Not for end-to-end, performance or infrastructure testing.
$ npx skills add lukeweb/ai-coding-agent-skillsopenfoam-simulation
Run an open-source OpenFOAM finite-volume simulation from an English discussion: elicit the geometry, fluid and operating conditions in plain language, turn them into a checked case file, build and run the OpenFOAM case from the command line, and turn the wall torque back into a physical result (e.g. a Couette flow curve). Use when the user wants a free, no-license CFD simulation — a Couette rheometer, a channel, a stirred tank — or asks for the open-source counterpart to an M-Star run.
$ npx skills add marcocaggioni/openfoam-skilllaravel-coolify-docker
Containerize a Laravel app for production and deploy it with Coolify — build the image on your own machine (including Apple Silicon → amd64 cross-builds), push it to GitHub Container Registry (ghcr.io), and run it as a Docker Compose stack (web + queue worker + scheduler + database). Produces a Dockerfile on serversideup/php, docker-compose.prod.yml, a build-and-push script, trusted-proxy fix, local test setup, and deployment docs. Use this whenever someone wants to dockerize / containerize a Laravel or Filament project, deploy Laravel to Coolify (or Dokploy, EasyPanel, CapRover, a plain VPS with Docker), push a Laravel image to ghcr.io, move off cPanel/shared hosting/Forge to containers, or troubleshoot a Laravel container that falls back to SQLite, can't reach MySQL, never processes queued jobs, serves http:// assets behind a proxy, or fails `npm ci` with missing @rollup/rollup-linux binaries.
$ npx skills add uluumbch/laravel-coolify-dockerharness-bootstrap
Install a complete, team-ready agent harness into any git repository: a short entry file (CLAUDE.md / AGENTS.md), architecture and reliability docs, layered verification scripts, executable architecture rules, a per-task feature list whose status only a verifier can change, session handoff and progress files that stay local (gitignored), a clean-state checklist, an independent evaluator, and integrity checks that enforce it all. Works with any coding agent (Claude Code, Codex, Cursor, Copilot, Devin, Pi and others). Use this whenever someone wants to "set up a harness", make a repo agent-ready, stop agents from forgetting context between sessions, stop agents from claiming "done" before things work, organize handoffs between developers or worktrees, or create AGENTS.md / CLAUDE.md / feature_list.json / init.sh / session-handoff files for a project, even if they never say the word "harness".
$ npx skills add Gabriel-Valin/harness-bootstrapagents-md-audit
Check existing AGENTS.md or CLAUDE.md instructions against project evidence and policy. Use for periodic reviews, drift checks after changes, or establishing or continuing a Git audit record. Report defects and verification limits, retain unresolved findings, and prepare a checkpoint message. Apply corrections or create the checkpoint only when authorised.
$ npx skills add has2k1/agents-grimoireintegral-lens
Apply Ken Wilber's Integral Vision (AQAL — All Quadrants, All Levels, All Lines, All States, All Types) to see anything whole — a problem, decision, project, product, organization, conflict, person, idea, or life situation — from every essential perspective, find the blind spots, and turn the map into a concrete, prioritized action plan with tasks. Use whenever the user mentions integral theory, Ken Wilber, AQAL, the four quadrants, holons, Spiral Dynamics or stages of development, asks for a "360°", holistic, whole-picture or "theory of everything" view, asks what they are missing or blind to, wants to know why something keeps failing despite effort, or wants a multi-perspective strategy, diagnosis, or task list — even if they never say "integral".
$ npx skills add nftvity/integral-lensjason
J.A.S.O.N. (Just Audit, Secure, Observe, Notify) — LLM App Security. Defensive security for software built with LLMs and coding agents. Pre-deploy "think like an attacker" check with a deterministic ship-gate that blocks deploys (secrets, open database rules, missing rate limits), full audit of AI-generated code (secrets, auth, IDOR, Supabase/Firebase rules, injection, LLM/agent tools, supply chain), PR quality gates, passive honeytokens/canaries that alert when an intruder or hijacked agent uses fake credentials, and repo defense against prompt injection aimed at coding agents. Use for security audits or reviews, "is my app safe", "review as if you wanted to break in", exposed API keys, routes without login, database rules, honeytokens/canary tokens/password.txt bait, prompt-injection defense, CI security gates, blocking a deploy, "before the first deploy", or securing a release.
$ npx skills add jasonmello/llm-app-securityagent-coordinator
Use on projects where a separate coding agent (e.g. Antigravity/Gemini, Codex, another Claude) does the research and heavy coding, and when starting a new project with one, adding one to an existing project, importing research results, cutting a release, or asking for project status. Claude sets the project up, writes the agent's prompts, reviews its branches, merges and tags.
$ npx skills add Trooper-code/Trooper-s-Coordinator-Skillsbuild-on-autopilot
build-on-autopilot (BOA, Build On Autopilot). Constrict your code to be right. Teaches and installs a complete, proven working discipline for building software with a lead agent and specialised sub-agents (builder, adversarial reviewer, tester, integrator, analyzer) — plan, lanes, reviews, tests, merge trains, memory, measuring, safety — plus the few generic tools it needs; the agent wires every project-specific part itself. Invoke explicitly as /build-on-autopilot <greenfield|brownfield|refactor> [idea-file] (installed as a plug-in, the plug-in name prefixes it: /boa:build-on-autopilot).
$ npx skills add mrpickles007/boareport
Use when the process misfired: turn the incident into an anti-pattern.
$ npx skills add Uniterra-Solutions/pdd-software-developmentevidence-review
Deep, evidence-based code review of anything - a whole project with no diff, a path, uncommitted changes, a branch, or a GitHub PR / GitLab MR. Reproduces findings instead of guessing, judges layer choice and reuse like a strict maintainer, and writes a structured report with IDs, severity, status and verification.
$ npx skills add avi-dev-user/evidence-reviewsteam-sel-lesson-designer
Designs arts-integrated Social-Emotional Learning (SEL) lesson plans and classroom resources for any subject, using the "Keep Calm and STEAM Ahead!" handbook (doodling, music and drama through the EMC² lens of Empathy, Mindfulness, Critical Inquiry and Compassion), with optional links to real-world issues and the SDGs. Interviews the educator one multiple-choice question at a time, then writes lesson plans, worksheets, doodle guides, soundscapes, scripts, quizzes and rubrics, citing sources and reusing only openly licensed material. Use it whenever a teacher, counsellor, facilitator, NGO worker or parent wants a lesson plan, classroom or SEL activity, or teaching resource, or wants a lesson to be more creative, engaging, inclusive or arts-based, or linked to climate, water, gender equality, waste, peace or another SDG, even if they don't mention SEL or the arts.
$ npx skills add nmg-002/steam-sel-lesson-designerproject-dev-workflow
Development discipline for AI coding agents. Restate the request and get it confirmed before coding; split work into layers with checkable completion criteria and verify each layer before the next (independent verifier when warranted); attack key decisions with adversarial review or explicit self-refutation before committing to them; push forward inside the confirmed scope and propose anything outside it; log every pitfall to PITFALLS.md as it is solved. Use when starting or continuing non-trivial development work — multi-step features, bugs spanning several steps, refactors, architecture or approach choices — even if the user does not name this skill. Also use for standalone requests such as "follow the workflow", "run this properly", "verify this", "critique this plan", "log this pitfall", "update the pitfalls" running only the matching section. Skip for pure Q&A and trivial one-line edits.
$ npx skills add svd748xyz/project-dev-workflowminecraft-builder-img
Analyze an uploaded image or screenshot of a Minecraft build, reverse-engineer its exact dimensions, block palette, roof profile, facade depth, and hidden rear/interior layout into a detailed Component Manifest and Coordinate Anchor Table, and immediately output a downloadable standalone zero-dependency Node.js (.mjs) generator file that exports a vanilla Minecraft .nbt structure file (Minecraft 26.3 / DataVersion 5023) without brainstorming questions. Use whenever the user shares an image/screenshot of a Minecraft structure, house, statue, furniture, or monument and wants it analyzed and rebuilt as an .nbt file or JS generator.
$ npx skills add marvaproject/minecraft-structure-builderssmcp
Operate SSH-connected ssmcp workspaces through list and code_mode. Use for parallel and background commands, bounded waits, client reload, automatically discovered coding harnesses, scoped file access and audit, existing Chrome and native browser discovery, concise tool search, skills and instruction discovery, Linux rsync transfers, and loopback TCP forwarding.
$ npx skills add LIghtJUNction/ssmcpblender-creation
Creates physically calibrated, articulated, PBR-textured 3D MuJoCo assets (MJCF model.xml, .mjz, mjSpec) from scratch using headless Blender (bpy, bmesh, blender_mesh_utils, asset_build_utils), convex collision synthesis, 10-scenario auditing, and Studio preview. Use only when asked to create, model, or build a 3D MuJoCo object from a URL, image, or text description, or when blender-creation is named. Don't use for non-MuJoCo Blender/Cycles/CAD modeling.
$ npx skills add google-deepmind/robotics-antigravity-pluginsecurity-audit
Run a comprehensive pre-launch security audit on any web, mobile, API, or bot project. Detects secrets, auth flaws, access-control gaps, injection risks, payment bugs, AI/LLM vulnerabilities, supply-chain threats, deployment misconfigurations, privacy issues, and more. Supports FastAPI, Django, Flask, Express, NestJS, Next.js, Laravel, Go, and mobile frameworks. Triggers on "security audit", "pre-launch check", "is my app secure", "review for vulnerabilities", "check for leaked keys", "start the audit", or when the user is about to deploy or launch.
$ npx skills add iForge-Technologies/SkillBasemitre-attack
Use for any MITRE ATT&CK work: map incidents/reports to TTPs, validate IDs, detection coverage and gaps, Navigator layers, group profiling, emulation plans, Sigma/Atomic mapping, version migration.
$ npx skills add THARAGESHWARAN-SATHYAMOORTHY/mitre-attack-skillwingbox
Code graph for large repositories and monorepos. Use it, before grep or reading files, when the question is what a change will break (blast radius, impact analysis), who uses a file, function, type or package, where a feature is implemented, which files to read first, or how modules and packages depend on each other; before a refactor, a cross-package change or any non-trivial edit; and when exploring an unfamiliar codebase. Builds and queries architecture-aware code search, dependency graphs, call flows, module boundaries and architecture violations for Python, TypeScript, TSX, Rust, C#, Java, Go, Ruby, Ruby on Rails, PHP, Laravel, Blade, Livewire, Eloquent, Dart and Flutter.
$ npx skills add aileron-tech/wingboxminecraft-builder
Brainstorm, design, and generate ANY static block-based Minecraft structure — from single furniture pieces (chair, table, shelf, bunk bed) and decorative/civic builds (well, street lamp, statue, bridge, fountain, farm) through occupiable shelters (tent, shed, hut, watchtower) and standard buildings (villager house, shop, cottage, lighthouse, temple) up to complex compounds (castle, cathedral, village hall, market square) — using a Coordinate Anchor Table, 5-Pass Constructive Layering, tiered architectural quality rules, and a downloadable standalone zero-dependency Node.js (.mjs) generator file that exports vanilla Minecraft .nbt files (Minecraft 26.3 / DataVersion 5023). Use whenever the user asks to design, plan, or generate any Minecraft build, structure, furniture, villager house/shop, monument, or .nbt structure generator in JavaScript.
$ npx skills add marvaproject/minecraft-structure-builder