Claude Skills by ericrisco

Use when building, scripting or debugging a game in Unreal Engine 5 with Blueprint or C++ — the gameplay framework (Actor, Pawn, Character, GameMode, PlayerController), Actor lifecycle and tick, the reflection macros and garbage collection, Enhanced Input, multicast delegates, UMG widgets, Paper2D, and Blueprint-to-C++ parity in both directions. NOT Godot (that is `godot`), NOT Unity or MonoBehaviour (that is `unity`), NOT language-only C++ memory and RAII questions with no Unreal types (that...

Use when a written text must be audited against a named catalogue of AI tells before it ships: puffery, `not just X but Y`, the rule of three, em dashes, filler, hedging, abstract metaphor nouns. Names each hit and fixes it. NOT the register rewrite in the user's own voice (that is `bro`), NOT a reusable voice guide (that is `brand-voice`).

Use when fine-tuning an open-weight LLM fast on ONE GPU with low VRAM — Unsloth's fast model loaders with 4-bit QLoRA and the trl trainer, response-only loss masking so the prompt is not trained on, GRPO reasoning fine-tunes, and export to merged 16-bit, GGUF or the Hub. NOT whether, why or which method to fine-tune (that is `finetuning`), NOT running the exported GGUF locally (that is `ollama`), NOT serving-engine flags and throughput (that is `vllm`), NOT building the JSONL dataset (that is...

Use when someone wants OPTIONS rather than an answer — 'show me a few versions', picking between approaches by seeing them. Genuinely different candidates, cheap to throw away, trade-off named. NOT the critique that judges one (`design-loop`), NOT the spec (`specify`).

Use when operating a vector store as a data layer — choosing or migrating between Pinecone, Qdrant, Weaviate and pgvector; designing a collection or index (distance metric, dimensions, HNSW parameters, named vectors); filtering on metadata; hybrid dense-plus-sparse search; and quantization to cut RAM and cost. Covers garbage results, silently ignored filters, low recall, slow queries, and filtered queries returning fewer than k rows. NOT producing, chunking or judging embeddings (that is `emb...

Use when operating an already-chosen Vercel project from the CLI or its config file — preview versus production deploys, debugging builds, pushing and pulling env vars across environments, custom domains, function runtime, duration and regions, crons, rewrites and headers, and deployment protection. NOT host choice, Docker or CI (that is `deployment`), NOT Next.js app code or next.config (that is `nextjs`), NOT DNS records or registrar transfers (that is `domains-dns`).

Use when implementation is finished and about to be called done or merged — the rsc-sdd evidence gate: runs the stack's scripts/verify.sh (lint, type, test, audit), walks every task done-check and acceptance criterion, records a dated verdict. NOT judging the diff by eye (that is `review`, spec-less `code-review`), NOT diagnosis (that is `debug`).

Use when scripting or directing the edit of a single vertical short that has to hold attention from the first frame — turning a topic, a clip or a long video into a shot-by-shot script and an edit decision sheet, fixing a hook that dies in second three, generating hook variants to test, and planning cuts and on-screen text. NOT scheduling or cross-platform cadence (that is `social-publisher`), NOT running the editorial calendar (that is `content-engine`), NOT defining the durable brand tone (...

Use to judge whether a short-form clip is worth publishing — scores a reel, short or podcast excerpt 0-100 on ten weighted criteria with automatic penalties, then ranks a batch and says where the cut-off falls. Run it on transcript candidates before rendering. NOT writing the hook or caption (that is `shortform-packaging`), NOT inventing the idea (that is `shortform-ideation`), NOT executing the edit (that is `shortform-editing`).

Use when self-hosting an open-weight LLM for high-throughput concurrent serving with vLLM — running an OpenAI-compatible endpoint, splitting a model across GPUs with tensor or pipeline parallelism, loading quantized weights, serving one or many LoRA adapters, and debugging KV-cache OOM from memory-utilisation and context-length flags. NOT renting or provisioning the GPU box (that is `runpod` or `modal`), NOT single-user laptop inference (that is `ollama`), NOT a hosted inference API you do no...

Use when building or reviewing a Vue 3 + Nuxt 4 app — `<script setup>` reactivity, SSR/SSG/hybrid `routeRules`, the `app/`+`server/` layout, SSR-safe fetching (`useFetch`/`useAsyncData`) and state (`useState`/Pinia), Nitro routes, hydration mismatches, Nuxt 3→4 migration. NOT React/RSC (that is nextjs), NOT a static islands site (that is astro).

Use when building the receiving end of a webhook — a provider-agnostic endpoint that proves pushed events are authentic and never processes one twice: raw-body HMAC, ~5-min replay window, idempotency on the event id, fast-ack-then-queue. NOT the Stripe-Signature scheme (that is stripe), NOT outbound clients you call (that is api-connector-builder).

Use when planning, promoting or running a webinar meant to convert — deciding the offer before the title, building the registration and reminder funnel, scripting the run-of-show, and splitting post-event follow-up by segment. Covers a low live attend rate, attendees who do not buy, and the transition into the pitch. NOT the slide visuals themselves (that is `presentations`), NOT the registration page copy (that is `landing-copy`).

Use when wiring an app or agent to message customers over the WhatsApp Cloud API or a Telegram bot — order updates, OTP codes, reminders, alerts and broadcasts — or when debugging undelivered messages, 24-hour-window errors, rejected templates, webhook signature verification, or rate limits and their retry headers. NOT the reply content you send (that is `customer-support`).

Use when building or hardening WordPress sites or WooCommerce stores and treating WordPress as the product rather than just writing PHP — block themes with theme.json, plugins with block.json and proper hooks, wp-config security hardening, performance (object cache, asset loading, autoloaded options), and WP-CLI operations. NOT a Laravel app (that is `laravel`).

Use when work is about to become commits and needs isolation first — check the tree state, then branch or cut a git worktree off a clean base (native EnterWorktree first, git fallback) so implement never runs on main. NOT what may run concurrently inside those workspaces (that is `parallel`), NOT the merge/cleanup after (that is `ship`).

Use when wiring code to a real YouTube channel: user OAuth 2.0, resumable videos.insert uploads, editing metadata after publish, pulling views/watch time/retention/traffic from the Analytics API v2 into a dated 02-DOCS/wiki/youtube/ feedback log. NOT what to publish or how to title and thumbnail it (that is youtube-strategy / youtube-packaging).

Use when deciding which videos a channel should make next and tracking whether each bet beat baseline — generating, scoring and prioritising candidate ideas from the channel's own performance log plus outlier and search-trend research, then recording each promoted idea as a dated hypothesis with its measured outcome. NOT writing the title or thumbnail text for a chosen idea (that is `youtube-packaging`).

Use when writing or fixing the text that ships with a YouTube upload — title, description, tags, hashtags and chapters — when click-through is weak and the words are the suspect, or when closing the loop on what last performed. NOT designing the thumbnail image (that is `youtube-thumbnails`), NOT inventing the idea or angle (that is `youtube-ideation`), NOT the channel growth plan (that is `youtube-strategy`), NOT pushing the fields via the Data API (that is `youtube-api`).

Use when a YouTube channel needs a system-level decision — positioning and niche, upload cadence, how videos chain into playlists and series, end-screen routing, or a what-is-working review — read from and written back to the channel's own learning wiki rather than one video's choices. NOT generating next-video topics (that is `youtube-ideation`), NOT per-video titles or thumbnail text (that is `youtube-packaging`), NOT designing the thumbnail image (that is `youtube-thumbnails`), NOT fetchin...

Use when designing or fixing a YouTube thumbnail, making variants for an A/B test, or working out which thumbnail style wins on a channel — including the trap where CTR looks fine but the test keeps selecting the duller image on watch-time share. NOT pairing the title with the thumbnail as one click-promise (that is `youtube-packaging`), NOT channel positioning or niche (that is `youtube-strategy`), NOT setting a thumbnail through the Data API (that is `youtube-api`).

Use when operating Zapier from an agent through the official hosted Zapier MCP server — connecting with a bearer key, discovering an app's actions, enabling one, and invoking a read or write action or firing a Catch Hook trigger across thousands of apps by natural language. Note there is no public API for creating or updating your own Zaps on a normal account, so say so and route onward. NOT deciding what a flow should be or its error and dedup design (that is `automation-flows`), NOT workflo...