Menu
Skills in this repository
SkillsMP has collected 495 skills from Kayforkind/skill-slice. Open a skill to review its source and details.
Kayforkind/skill-sliceShowing 40 of 495 collected skills.
Exposes a local port with a Pinggy SSH reverse tunnel to a.pinggy.io:443, returning a public HTTP/HTTPS URL with no extra daemon (free 60-minute tunnels). Use when sharing a dev server, receiving webhooks, or tunneling port N. Not for Cloudflare wrangler…
Scaffolds and hardens Playwright Java E2E tests with Page Object Model, JUnit 5, ThreadLocal parallel browsers, Allure, and CI browser install. Use when writing Java page objects, fixing flake without Thread.sleep, or wiring Maven/Jenkins/GitHub Actions. Not…
Hardens a feature branch for reviewer speed: rebase-clean diffs, leftover-debug sweeps, local test evidence, and a why-plus-verification PR writeup. Use when the goal is fewer review cycles before a human merge. Not a GitHub lifecycle chair for gh pr create,…
Runs a read-only go-live review of deploy readiness: migrations, config, secrets redaction, rollout order, rollback risk, and launch blockers, producing a prioritized report. Use when the user asks for a release audit before tagging or deploying. Not for…
Indexes local notes, docs, and transcripts with qmd hybrid retrieval (BM25 + vectors + LLM rerank) via @tobilu/qmd. Use when searching a personal knowledge base semantically without cloud APIs. Not for Obsidian vault editing (obsidian), Mesh Memory MCP…
Diagnoses REST and GraphQL failures by isolating connectivity, TLS, auth, payload shape, parse, then semantics with curl and Python requests. Use when status or body is unexpected, auth fails, Postman works but code does not, or webhooks, pagination, or rate…
Reviews animation and motion diffs against a craft bar: justified motion, origin-aware scale, GPU-only transform/opacity, interruptible springs, sub-300ms UI, and prefers-reduced-motion. Use when reviewing CSS transitions, keyframes, Framer Motion, WAAPI, or…
Enforces written dollar caps, iteration bounds, concurrency limits, retry policy, and provider-dashboard hard caps before any paid inference call site. Use when writing or auditing loops, agents, webhooks, or queues that hit billed APIs. Not a production…
Generates JSON-LD Schema.org markup (WebSite, SoftwareApplication, BlogPosting, FAQPage, HowTo, BreadcrumbList, Organization) for Next.js. Use when adding or validating structured data for rich results. Not for Open Graph or Twitter cards alone. Never merge…
Fetches and extracts pages with Scrapling HTTP Fetcher, DynamicFetcher for JS-rendered HTML, and Spider crawling via CLI or Python. Use when static or JS pages must be extracted after a generic web extract fails, or when crawling URLs the user is allowed to…
Runs the Sherlock CLI to find where a username exists across 400+ social sites (--print-found, optional --tor/--site). Use when the user asks which networks a handle is registered on, or to check username availability. Not for email, phone, or domain OSINT,…
Drives the SiYuan kernel HTTP API via curl to search, read, create, update, and delete blocks and documents, run SQL, and export Markdown. Use when managing a self-hosted SiYuan (思源笔记) knowledge base. Not for Obsidian vault notes, Apple Notes MCP search, or…
Hardens Open Graph and Twitter Card tags so public URLs unfurl as rich cards on Facebook, LinkedIn, X, WhatsApp, Telegram, Slack, and Discord. Use when shared links show missing, stale, cropped, or broken previews, or when auditing og and twitter metadata…
Manages tmux sessions, windows, and panes, including detached SSH-surviving jobs and scripted send-keys layouts. Use when persisting remote work, multiplexing a server terminal, or automating multi-pane workspaces. Not for Windows Terminal / tmux-less…
Builds end-to-end type-safe tRPC APIs: routers, Zod procedures, dual Next.js App Router context factories, protected middleware, and subscriptions. Use when scaffolding tRPC in a TypeScript monorepo or migrating REST/GraphQL incrementally inside one repo. Not…
Hardens vibe-coded Next.js/React/Node apps by removing proven-dead imports, unused files, and broken refs without rewriting working routes. Use when a rapidly built app works but is messy before launch. Not for greenfield features, broad architecture…
Generates single-wall spiral vase STLs (sine, twisted polygon, Gielis superformula) and Bambu Studio/Cura/PrusaSlicer Spiralize Outer Contour settings for decorative prints, LED lamp shades, and manual/gradient multi-color bands. Use when the user asks for…
Diagnoses and tightens an existing Claude subagent markdown file under `.claude/agents/` from concrete failure transcripts: trigger description, tool list, and output contract. Use when a named subagent drifts, calls the wrong tools, or produces off-task…
Creates and audits lean AGENTS.md / CLAUDE.md agent instruction files (target under 60 lines, hard max 100) from the real toolchain, with a CLAUDE.md symlink. Use when the user asks to create, update, or audit AGENTS.md or CLAUDE.md, or to keep agent docs…
Runs a bounded Spec-Build-Review cycle with an iteration budget, recorded verification commands, and human approval gates. Use when an isolated feature needs a full build from scratch or a heavy modification with checkable requirements. Not for open-ended…
Guides Vercel AI SDK v6 (ai, @ai-sdk/react, ToolLoopAgent, generateText/streamText, Output.object, MCP tools) across LLM providers. Use when building chat, structured output, tool calling, streaming, embeddings, or migrating v5 to v6. Not for the OpenAI…
Deploys, validates, troubleshoots, and stops NVIDIA AI-Q Blueprint 2.1.x (Docker Compose, Kubernetes/Helm, local process, CLI, or web UI). Use when installing or cloning AI-Q, starting the backend, checking /health, fixing port or credential failures, or…
Routes research questions to a reachable NVIDIA AI-Q Blueprint via scripts/aiq.py (health, /chat, async job poll, report). Use when the user asks for AI-Q/AIQ research or to query a trusted AIQ_SERVER_URL. Not for installing, deploying, Docker, Helm, or…
Talks to Airtable's REST API with curl and a personal access token: list/filter records, schema inspect, batch CRUD, and performUpsert syncs. Use when the user wants to read, create, update, delete, or idempotently sync rows in an Airtable base (app/tbl/rec…
Captures Android performance evidence on an adb target: Simpleperf CPU samples, Perfetto/Compose traces, gfxinfo framestats, dumpsys meminfo, Java heap dumps, and native heapprofd allocations. Use when profiling a focused Android app flow, diagnosing jank or…
Guides Angular 16+ state: Signals and signal services, NgRx SignalStore and Store (actions, reducers, effects), ComponentStore, and toSignal/toObservable bridges. Use when choosing Signals vs NgRx vs Akita, migrating BehaviorSubject stores, or implementing…
Converts an existing CLI, script, or Crawlee project into an Apify Actor: Docker image, .actor/input_schema.json, Actor.init/exit lifecycle, apify run then apify push. Use when wrapping software for the Apify platform, adding Apify SDK I/O, or deploying an…
Searches arXiv via the Atom REST API and enriches papers with Semantic Scholar citations, references, and BibTeX. Use when finding preprints by keyword, author, category, or ID, or generating citations. Not for Hugging Face paper pages (hugging-face-papers)…
Configures Godot 4.x import-time assets: texture compression, glTF/.blend scenes, WAV/Ogg, .tres/.res, and .import sidecars plus headless reimport. Use when importing textures, glTF, blend, wav/ogg, tres/res, or running godot --headless --import. Not for…
Transcribes audio or video to text with word-level timestamps via faster-whisper (default large-v3-turbo) or local openai-whisper (word_timestamps=True). Use when the user needs captions, filler-word cut lists, or searchable transcripts with start/end times.…
Authors SST v4 (Ion) AWS infra in TypeScript: sst.config.ts, infra/ modules (sst.aws.Function/Bucket/Dynamo/Cron/Service/Router, sst.Secret, sst.Linkable, raw aws.* Pulumi), resource links, sst deploy, and stack troubleshooting. Use when writing Ion stacks or…
Applies a hard English prose contract: concrete nouns, varied sentence length, banned em dashes, reversal pivots, filler transitions, and therapeutic cadence. Use when the user wants essays, literary rewrites, punchy long-form, or text free of AI tells. Not…
Orchestrates first-run setup for Vercel-linked repos: vercel link, env pull, AUTH_SECRET, then db:push/seed/dev in that order (next-forge uses pnpm migrate). Use when cloning or repairing a project that depends on Neon, Auth, Blob, or other Vercel…
Writes Playwright (preferred) or Puppeteer browser tests and scripts: user-facing locators, auto-wait, storageState auth, traces on failure. Use when the user mentions Playwright, Puppeteer, E2E, page.getByRole, locators, or headless Chromium tests. Not for…
Owns the HTML5/itch.io game shell: fixed-timestep loop, scene stack, input, audio unlock, asset preload, versioned saves, letterbox scaling, and Vite/PWA build. Use when starting or restructuring a Canvas, WebGL, or DOM-hybrid web game. Not for Three.js…
Runs a read-only four-agent swarm that ranks root-cause hypotheses for bugs, regressions, crashes, and flakes. Use when the failure is large or ambiguous and the user wants a diagnosis plus proof path. Not for applying patches or implementing the fix…
Scaffolds ChatGPT Apps SDK apps that pair an MCP server with widget UI (MCP Apps bridge, window.openai, CSP, tool plans, Developer Mode, directory submission). Use when designing ChatGPT app tools, registering UI resources, wiring ext-apps, or producing a…
Builds stateful Cloudflare Agents SDK workers: Agent/AIChatAgent, Durable Object setState/SQL, WebSockets, this.schedule(), Workers AI, and wrangler.toml class migrations. Use when the user wants a Cloudflare chat or stateful edge agent, the Agents SDK, or…
Scaffolds ChatGPT Apps SDK apps that pair an MCP server with a widget UI: tool plans, resource registration, MCP Apps bridge, window.openai extensions, CSP/domain metadata, and directory submission. Use when designing tools, wiring widgets, or producing a…
Runs Chroma (chromadb) locally or as a server: PersistentClient, create_collection/add/query/get, metadata where filters, and LangChain or LlamaIndex vector stores. Use when building self-hosted RAG, notebook semantic search, or embedding documents with…