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.
Gets schema-constrained JSON from LLMs via OpenAI json_schema, Anthropic tool_use extraction, Gemini responseSchema, or local GBNF. Use when extracting typed objects, enums, or validated JSON from model APIs (zodResponseFormat, instructor, marvin). Not for…
Builds a Karpathy-style interlinked markdown wiki (SCHEMA.md, index.md, log.md, immutable raw/, entity/concept pages) with ingest, query, and lint. Use when the user asks to create, ingest, lint, audit, or query a wiki, knowledge base, or research notes at…
Chains local-GPU lip-sync for stylized or non-photoreal faces (anime, cartoons, CG avatars, puppets, VTubers): Wav2Lip, MuseTalk, LivePortrait, SadTalker, GFPGAN/CodeFormer paste-back, detector fallbacks, feathered mouth composite, CFR conform, and FFmpeg…
Arms a Cursor-session interval loop: parse /loop [interval] <prompt>, emit AGENT_LOOP_TICK sentinels from a monitored PowerShell/bash shell, run the prompt on each tick, and stop by PID. Use when the user says /loop, every 5m, or keep checking. Not for…
Implements Makepad 2.0 turtle layout: Walk (width/height Fill or Fit), Layout (flow, spacing, align), ScrollYView, overlay walk.abs_pos, Splitter, and Filler. Use when building or debugging Makepad UI that is invisible, zero-height, or misaligned. Not for…
Produces Manim Community Edition explainer videos: Scene classes, MathTex, ffmpeg stitch, optional TTS — 3Blue1Brown-style math, algorithms, and architecture diagrams. Use when the user wants programmatic math/technical animation with Manim. Not for…
Designs and implements Model Context Protocol servers from scratch: tools, resources, prompts, stdio and Streamable HTTP transports, JSON Schema, errors, Inspector testing, and packaging. Use when creating an MCP server or exposing a local API or CLI to…
Runs self-hosted semantic agent memory over PostgreSQL/pgvector via MCP tools (mesh_add, mesh_search, mesh_focus) with local e5 embeddings. Use when persisting worklogs, decisions, and notes for cross-session recall by meaning. Not for Chroma RAG stores…
Sets up CurseForge/Modrinth NeoForge or Forge Minecraft server packs: Java match, server.properties, JVM args, backups, firewall. Use when hosting a modded Minecraft server or troubleshooting start/kick issues. Not for vanilla-only servers without a pack,…
Writes Baseline 2026 native CSS: Flexbox/Grid/subgrid, logical properties, container queries, @layer/@scope, :has, oklch, nesting, anchor positioning, and fluid type. Use when writing or reviewing stylesheets, layout, dark mode, or cascade without a…
Authors and reviews 2026 Baseline HTML: document head, semantic landmarks, native dialog/popover/invoker commands, web components, forms, WCAG 2.2, JSON-LD, loading/CLS, and HTML security (CSP/SRI). Use when writing or auditing markup rather than CSS or…
Implements a strict single-hue UI: HSL tints/shades, tinted mono900 shadows, texture and weight instead of a second hue, including error and success states. Use when the user wants monochromatic, one-color palette, or tint/shade discipline on web or mobile.…
Produces numbered system-design blueprints, audits, and scale roadmaps (RPS math, Mermaid, trade-offs, SPOF tags) for backend architecture interviews and reviews. Use when asked to design, review, or scale a service, or to simulate a system-design interview.…
Investigates Monte Carlo data incidents (freshness, volume, schema, field drift, ETL) via MCP lineage/alerts and optional Troubleshooting Agent. Use when a table is stale, row counts drop, a pipeline fails, or the user has an MC alert/incident UUID. Not for…
Diagnoses data-pipeline slowness with Monte Carlo observability across Airflow, dbt, Databricks, and warehouse engines (slow jobs, costly queries, compute regressions). Use when the user asks why a pipeline is slow or what burns compute. Not for data-quality…
Implements React UI animation with Motion (motion/react, formerly Framer Motion): layout, AnimatePresence exits, layoutId, gestures, useScroll, and reduced-motion. Use when animating React components, shared-element transitions, or scroll-linked effects. Not…
Automates music- and curve-driven video edits: librosa beat-sync, MoviePy 2.x time_transform ramps, FFmpeg zoompan easing, camera shake, and word-highlight .ass. Use when beats, easing math, or time-remap drive the cut. Not for plain trim/concat…
Offloads CPU-heavy Godot work via WorkerThreadPool, Thread/Mutex/Semaphore, call_deferred, and threaded resource load so the main thread keeps the ~16 ms frame. Use when Godot pathfinding, procedural generation, or background loads hitch rendering. Not for…
Defines the smallest product slice and cheapest experiment to test a startup's core value hypothesis before heavy engineering. Use when a founder is scoping an MVP, validating demand, designing a smoke/concierge/Wizard-of-Oz test, or fighting…
Writes JavaScript in n8n Code nodes: $input.all/$json/$node, $helpers.httpRequest, DateTime/Luxon, $jmespath, and All Items vs Each Item modes. Use when transforming items, calling HTTP from a Code node, or troubleshooting Code node errors. Not for {{ }}…
Writes Python inside n8n Code nodes using _input/_json/_node helpers, the standard library only, and a return of list-of-json dicts. Use when the Code node language is Python, or when choosing Python vs JavaScript for n8n. Not for JavaScript Code nodes…
Writes and debugs n8n node-parameter expressions in {{ }} with $json, $node, $now, and $env. Use when fixing n8n expression errors, webhook field mapping, or Luxon date formatting in parameters. Not for n8n Code-node JavaScript (n8n-code-javascript) or Python…
Provisions Neon S3-compatible object storage that copy-on-write branches with a Neon Postgres project for uploads, images, documents, and avatars. Use when files must stay in sync with rows across preview and dev branches via SigV4 path-style S3. Not for…
Chooses and creates Neon Postgres branches (normal vs schema-only) via Neon CLI, MCP, or REST, including reset-from-parent and ephemeral expiry. Use when testing migrations against production-like data or isolating PR/dev databases. Not for picking Neon vs…
Finds and fixes application query patterns that inflate Postgres/Neon egress (SELECT *, missing LIMIT, JOIN duplication, in-app aggregation) plus cheap non-prod compute via neon.ts. Use when Neon bills spike, data-transfer costs jump, or list endpoints lack…
Operates the Netlify CLI: install, login or NETLIFY_AUTH_TOKEN, site link, Git or manual deploy, netlify dev / Vite plugin, and context-scoped env vars. Use when the user runs netlify, deploys to Netlify, or needs netlify env import/export. Not for Vercel env…
Writes Netlify serverless functions with the default-export plus Config pattern (Web Request/Response): API paths, background (15 min), scheduled, and streaming handlers. Use when adding server-side logic beside a Netlify site without a framework adapter. Not…
Localizes a failed API or network call to DNS, TCP, TLS, HTTP, or the app from the exact status, timeout, or errno (ENOTFOUND, ECONNREFUSED, 429, 502/503). Use when curl/fetch fails, the API looks down, or errors are intermittent. Not for Spark shuffle…
Implements Godot 4.x multiplayer: ENet, WebSocket, or WebRTC peers, @rpc, MultiplayerSpawner and MultiplayerSynchronizer, dedicated --headless servers, lobbies, and client-side prediction. Use when adding online or LAN play, RPCs, or Steam relay NAT…
Generates CI pipeline YAML/Groovy that installs Newman, runs Postman collections with JUnit/HTML reporters, and publishes artifacts on GitHub Actions, GitLab CI, Jenkins, Azure DevOps, or CircleCI. Use when moving Newman/Postman API tests into CI. Not for…
Wires Supabase Auth to Next.js App Router with @supabase/ssr: browser/server clients, middleware refresh, OAuth callbacks, and getUser() session checks. Use when adding login, signup, OAuth, or route protection. Not for RLS/schema design, generic App Router…
Aligns Python interpreter and pinned deps before installing NLP research repos from requirements.txt or environment.yml. Use when cloning or reproducing NLP papers, debugging torch/transformers conflicts, or setting up research envs. Not for greenfield app…
Downloads and parses NWS flood-stage thresholds (action/minor/moderate/major) for USGS gauges, then matches station IDs for labeling historical observations or a bulk snapshot. Use when asking at what stage flooding begins at a gauge, not how high the water…
Instruments production features with structured event logs, RED/USE metrics, OpenTelemetry traces, and page-vs-ticket alerts written beside the code. Use when adding logging, metrics, tracing, or alerting, or when incidents lacked evidence. Not for debugging…
Authors Obsidian Bases .base YAML: global filters, formulas, summaries, and table/cards/list/map views over note properties. Use when creating database-like views of notes, embedding ![[MyBase.base]], or editing Bases filters/formulas. Not for ordinary…
Reads, searches, creates, and edits markdown notes in an Obsidian vault via resolved filesystem paths (OBSIDIAN_VAULT_PATH, else ~/Documents/Obsidian Vault). Use when the user asks to manage vault notes, wikilinks, or Obsidian markdown files. Not for Google…
Parses seismological formats (MiniSEED, SAC, QuakeML, StationXML) into ObsPy Stream/Trace, Catalog/Event, and Inventory objects. Use when ingesting waveforms, event catalogs, or station metadata for processing or SeisBench. Not for generic non-seismic time…
Embeds alibaba/page-agent as an in-page GUI agent (DOM-as-text, OpenAI-compatible LLM) so end users drive a site with natural language. Use when adding an NL copilot inside a SaaS/admin app or evaluating page-agent against Ollama, Qwen, OpenAI, or OpenRouter.…
Fetches Hugging Face paper pages as markdown and the papers API for authors, linked models/datasets/spaces, GitHub, and project URLs. Use when the user shares an hf.co/papers or arXiv URL/ID or asks to summarize an AI research paper indexed there. Not for…
Debugs numerical parity between two ML pipeline implementations (research vs Diffusers, standard vs modular) with CPU/float32 component tests, encode/decode/denoise stage checkpoints, and tensor injection. Use when outputs look washed out, pixelated, or…