Coding & Development

Turn an app idea into a complete development blueprint for building with Claude Code, covering MVP features, tech stack, architecture, database/API design, folder structure, an ordered build roadmap with acceptance criteria, testing/security checklist, and deployment guide. Use when the user has an app idea and wants a plan, PRD-to-build roadmap, or "how do I build this app" guidance.

Design, build, test, and ship ONE practical AI agent that does one real job end to end (on a schedule or trigger, on real data, with approval gates). Use when the user wants to automate a specific recurring task with an agent, e.g. "build me an agent that every morning finds X and drafts Y". Supports any runtime, including Claude Code, scripts, or Grok Bot.

Design and review product screens around real user tasks, information priority, and state transitions. Use for new or changed UI flows and cluttered interfaces; skip UI design for non-UI tasks.

A borehole logging engineer's knowledge: field logging at the rig, soil and rock description systems (USCS/ASTM, Canadian, AS 1726, BS 5930), sampling and in-situ tests (SPT, pocket penetrometer, torvane, vane, DCPT, CPT), rock core logging (TCR, RQD, weathering, fractures), groundwater, wells, the field-log to final-log transformation, and what a reviewer checks before sign-off. Use it whenever work needs that judgement: designing or reviewing a GroundScribe logging feature, QA rule, extraction prompt, export template or fixture; interpreting a field-sheet value; checking a log; onboarding a new firm's conventions; or judging the product as a logger would. Trigger even without the word "logging", e.g. "is N=6 dense sand ok", "what does 50/5 mean", "how should we store torvane", "S.A.A.", "RQD", "EOH".

Système de marque sobre et éditorial, fourni comme marque par défaut : palette bleue sur fond clair, typographie Inter, dégradé doux, boutons en pilule, cartes à ombre légère, icônes Phosphor. Appliquer à tout livrable (présentation, document, page, artefact web) quand aucune autre charte n'est donnée, ou s'en servir comme modèle à remplacer par la charte d'un projet. À combiner avec `slides` (mises en page) et `pptx` (génération du fichier). Déclencher dès qu'on demande une mise en forme soignée, une identité visuelle, des tokens de design, ou un livrable client à l'aspect professionnel.

Planning heating, hot-water and solar control systems with Technische Alternative (TA) products – for homeowners planning their own system and for installers. Use when someone wants to choose a TA controller (UVR16x2, UVR610, UVR67, CAN-I/O45, CAN-EZ3, CAN-BC2, CAN-MTx2, C.M.I.), count inputs and outputs, pick sensors, immersion sleeves, flow sensors, room sensors or auxiliary relays, design the CAN or DL bus, write a bill of materials with article numbers and list prices, find the right datasheet or manual on ta.co.at, pick a program from the TA program library, or check which Austrian standards, OIB guidelines, state law and funding conditions apply. Also use for German requests like "welchen Regler brauche ich", "Stückliste UVR", "Fühler planen", "Heizungsregelung planen", "Kesseltausch Förderung Regelung". For operating or analysing an existing TA installation use the skill technische-alternative instead.

Make a single-image editorial infographic (1080x1350) that explains one idea at a glance — two-tone headline, one-sentence dek, a hero visual with 2–4 numbered callouts and leader lines, an optional side note, a three-column "why it matters" row with icons, byline and sources. Use for "explain X in one graphic" posts about a company move, a framework, an architecture or a trend; the PNG can also be a carousel slide.

Build or refresh a shortform brand reference pack for any app from its real surfaces — website, App Store listing and reviews, socials, the live app (driven end to end on the simulator) and its code tokens — plus a status check of the upstream foundations (ICP, voice of customer, brand voice). Produces the context that content formats and design decisions are made from, as markdown, tokens.json and a PDF. Use for "build a brand pack for <app>", "refresh the brand pack", "capture the site/app/socials for shortform", "/brand-reference-pack".

Design technically accurate telecom architecture infographics, interactive HTML explorers, animated signaling flows and architecture comparisons. Use this skill whenever the user wants to visualize, illustrate, diagram, explain or compare any telecom topic (2G/3G/4G/5G, IMS, VoLTE, roaming, S8HR vs LBO, IPX, Diameter, SIP, GTP, SS7/MAP, SMS routing, CAMARA / GSMA Open Gateway APIs, SIM Swap, Number Verification) as an infographic, interactive architecture explorer or animated signaling flow, even if they never say "infographic" or "skill". For LinkedIn packaging of the result, hand off to telecom-linkedin-publisher.

Pitfalls, surprising defaults, PostgreSQL 18 changes and recommended patterns from the official PostgreSQL 18 documentation, each backed by its postgresql.org URL. Use when writing or reviewing PostgreSQL SQL, schema design, migrations and ALTER TABLE locks, indexes, transactions, isolation levels and retries, locking, upsert and MERGE, COPY, JSONB, timestamptz, generated and identity columns, partitioning, EXPLAIN, vacuum, roles, row-level security, PL/pgSQL, full-text search, connection settings, and upgrades to PostgreSQL 18.

Use only when the user asks to design a mobile UI screen or flow (phone-sized layouts, touch targets, thumb reach). Do not use for tablet, desktop, or non-UI work.

Grafana Cloud pitfalls, defaults, limits and current patterns from the Grafana, Mimir, Loki and Tempo docs, each tied to its docs URL. Use when sending OpenTelemetry data to Grafana Cloud, writing PromQL, LogQL or TraceQL, controlling cardinality and cost, designing alert rules, routing notifications, provisioning alerting, building Synthetic Monitoring checks, using the /apis dashboard API, choosing access policy tokens or service accounts, or migrating off API keys, the Loki Exporter and legacy /api routes.

Use only when the user asks for a UX review or critique of an existing UI design, screen, or flow. Do not use for code review or non-UI work.

Pitfalls, surprising defaults and recommended patterns of the Typesense search engine, distilled from the official docs. Use when designing a Typesense collection schema, writing search parameters (q, query_by, filter_by, sort_by, facet_by, group_by), tuning typo tolerance and ranking, building vector, semantic or hybrid search, conversational RAG or natural language search, creating API keys and scoped search keys for multi-tenancy, indexing and import (JSONL, upsert, emplace, dirty_values), syncing from a primary database, reindexing through aliases, managing synonyms (synonym sets), curation sets and stopwords, joins, analytics rules and query suggestions, InstantSearch, migrating from Algolia, or running, clustering, backing up and upgrading a Typesense server.

Use only when the user asks to design a tablet UI screen or flow (split view, adaptive layouts, touch plus pointer). Do not use for phone, desktop, or non-UI work.

Use only when the user asks to design a desktop UI screen or flow (resizable windows, min/max sizes, pointer and keyboard). Do not use for mobile, tablet, or non-UI work.

Use this skill whenever your answer will contain Rust code or Cargo/clippy/rustfmt config, or a verdict on existing Rust code. Simple-looking Rust tasks still need it - it holds the required conventions and a fmt/clippy/doc/test check that every Rust change must pass. That covers writing any new Rust (one function counts), fixing a compiler or borrow-checker error, adding rustdoc comments and examples, redesigning error types, refactoring, reviewing or auditing a .rs file or crate, and tidying a Cargo workspace (shared lints, editions, dependency versions). When the language is Rust, use this skill first and do not let a general debugging, documentation, refactoring, or code-review skill replace it. Skip it only when no Rust gets written or judged - explaining concepts, comparing languages, summarizing editions, or working in another language even inside a repo that also has Rust.

Turns a one-line product idea into a researched system design. It first tests whether an existing product would do, finds the laws and platform rules in force, compares structurally different stacks on real cost, then writes a stack card, two hosting cost tiers with dated prices and measurable upgrade triggers, C4 diagrams, data model, ADRs, a CI pipeline and a deployment runbook. Use it whenever someone describes software they want to build and asks what stack, database, hosting or architecture to use, what it will cost, how to deploy it, or how to "design the system", even if they only paste an idea like "an HRMS for my 20-person company" or ask "cheapest way to host X" or "should I use Supabase or Firebase for this". Covers web, mobile and desktop. Not for refactoring an existing codebase's architecture and not for writing the application code.

Designs one opinionated "Grand Slam Offer" for any app idea, new or already shipped, by running Alex Hormozi's $100M Offers method adapted to app stores. It covers the market and niche, the commodity check, a value-equation audit, the problem inventory, delivery vehicles, the trimmed value stack, pricing and tiers, scarcity, urgency, bonuses, the guarantee, naming, the paywall per placement, the onboarding fast win, a test plan and a ship plan. It works within App Store and Google Play rules. For a shipped app it reads the code and notes first and produces a before/after. Use it when the user says "/app-offer", "run app-offer on <idea>", "make a grand slam offer for my app", "Hormozi my app", "price my app" or "design my paywall offer", or asks how to package, price, name, guarantee or paywall an app. It writes offer/grand-slam-offer.md (or ./<app-slug>-grand-slam-offer.md for a new idea).

Competitor change tracker for GTM teams. Snapshots competitor pages (homepage, pricing, changelog, careers), diffs them against the last scan, and turns the changes into a GTM readout - what moved, why it matters, what to do. Use whenever the user asks what competitors changed, wants a competitor scan or weekly digest, asks about a competitor's pricing / launches / messaging / hiring changes, or wants to add or remove a competitor or page from the watch list. Triggers - "what did competitors change", "competitor scan", "run tripwire", "weekly competitor digest", "did X change their pricing", "watch this competitor", "竞品有什么变化", "竞品更新", "看看竞品这周改了什么", "加一个竞品".

Framework en 7 phases pour transformer un prototype en case study portfolio avec vidéos animées, contenu narratif bilingue et pack d'intégration. Déclencher quand l'utilisateur veut documenter un prototype, créer un case study, produire des vidéos de démonstration d'une interface, ou publier un projet dans un portfolio. Entrée : un fichier de code ou un prototype. Sortie : case study complet publié avec vidéos.

Turns the founder folder into the thing that gets one real person to say yes to the next step: a one-page pilot offer for a customer, an NSF Project Pitch or grant answer for a funder, an investor or lender one-pager, a business case for a boss, or an invite for the people who will use it. Always writes the one-sentence, three-sentence and three-minute versions first. Builds only from claims in the evidence ledger that the audience may see, never from simulated buyers, and checks the finished pitch with the ledger before it goes out. Use when the user says "pitch this", "write a pilot offer", "one-pager", "grant pitch", "NSF pitch", "deck for", "email this customer", "business case", or "what do I send them".

Delegate a general-purpose task to Google's Antigravity CLI (agy staffer, fast Gemini) with a minimal, unopinionated prompt. Use when the user says /agy:staffer, "have agy do/handle X", "have agy generate an image", or the task fits none of the specialist personas (researcher / reviewer / implementer / ask) — the template adds no role or output format, only the shared working rules and guardrails, so the task text shapes the output. Also the route to agy-native tools no specialist covers, notably image generation (generate_image).

Enforce Rule Cascade rules in Python services and jobs (FastAPI, Django, Flask, Celery, batch scripts) with the rule-cascade package. Use when wiring rules into a Python code path, replacing Pydantic validators or hand-written checks with the engine, or evaluating many records in a batch.