메뉴
이 저장소의 skills
SkillsMP는 Kayforkind/skill-slice에서 495개의 skill을 수집했습니다. skill을 열어 소스와 세부 정보를 확인하세요.
Kayforkind/skill-slice수집된 skill 495개 중 40개를 표시합니다.
Deploys and manages Vercel projects via CLI authenticated by VERCEL_TOKEN in the environment (never --token on the command line): preview deploy, env vars, inspect, domains. Use when CI or an agent must deploy without vercel login. Not for interactive vercel…
원문 언어: 영어
Guides Vercel Functions compute covering Node serverless, Edge isolates, Fluid Compute, streaming, Cron, waitUntil/after, and vercel.json runtime config. Use when editing api routes, App Router route handlers, or debugging FUNCTION_INVOCATION_FAILED and…
원문 언어: 영어
Selects and configures Vercel storage: Blob, Edge Config, and Marketplace Neon/Upstash/Supabase/Prisma/Mongo/Convex/Turso, including sunset @vercel/postgres and @vercel/kv migrations. Use when choosing or debugging data stores on Vercel. Not for Neon branch…
원문 언어: 영어
Assembles a final video from existing clips, audio, and subs with FFmpeg concat/amix/xfade/subtitles/loudnorm (Remotion only for complex motion). Use when combining production outputs, concatenating clips, or mixing/burning audio and captions. Not for…
원문 언어: 영어
Directs 2026 T2V/I2V models (Veo 3, Sora, Kling, Runway Gen-4, Vidu, Hailuo, Luma, Pika) with shot recipes: subject/action/setting/camera/style channels, motion budget, negatives, and model-specific grammar. Use when writing or debugging generative video…
원문 언어: 영어
Serves LLMs with vLLM PagedAttention and continuous batching: OpenAI-compatible /v1/chat/completions, GPTQ/AWQ/FP8 quantization, tensor parallelism, and offline LLM.generate. Use when deploying high-throughput GPU inference endpoints or fitting 30B-70B…
원문 언어: 영어
Designs low-latency voice agents with OpenAI Realtime, Vapi, Deepgram STT, ElevenLabs TTS, and LiveKit. Use when the user mentions voice AI, speech-to-text, text-to-speech, or realtime voice. Not for text-only chat UIs (vercel-ai-sdk-expert) or local ComfyUI…
원문 언어: 영어
Scrapes JS-rendered pages with Hermes browser_* + CDP: navigate, snapshot, interact, extract JSON from the live DOM after static fetch fails. Use when a SPA, login wall, infinite scroll, or click-to-reveal hides data from HTTP fetch. Not for Playwright E2E…
원문 언어: 영어
Profiles and tunes runtime FPS of canvas WebGL/WebGPU games via draw-call batching, instancing, KTX2, object pools, GC pauses, and engine knobs for Three.js, Phaser, PixiJS, Babylon.js, and Godot 4 Web. Use when FPS drops, jank, leaks, or context-lost appear.…
원문 언어: 영어
Logs ML training with wandb.init/log, hyperparameter sweeps, artifact lineage, and the model registry. Use when tracking experiments, comparing runs, or sweeping hyperparameters in PyTorch, TensorFlow, or HuggingFace. Not for LLM app tracing and prompts…
원문 언어: 영어
Reviews and authors Cloudflare Workers against current best practices (streaming, floating promises, global state, secrets, wrangler.jsonc, bindings). Use when writing or reviewing Workers or wrangler config. Not for Durable Objects details (durable-objects),…
원문 언어: 영어
Runs Cloudflare Wrangler v4+: wrangler.jsonc, deploy/dev, KV/R2/D1/Vectorize/Hyperdrive/Queues/Workflows/Pages, secrets, types, and tail. Use when editing wrangler config, bindings, or any wrangler command. Not for Cloudflare Agents SDK application code…
원문 언어: 영어
Ingests Microsoft Excel .xlsx workbooks with openpyxl (or pandas) into list-of-dict rows, handling multi-sheet books, sparse rows, merged cells, and composite list or JSON cells. Use when a task input is .xlsx rather than a database. Not for .csv, .json, or…
원문 언어: 영어
Calls the 2slides hosted API for Fast PPT, image-matched Nano Banana decks, document-to-slides, AI voiceover, and PNG/WAV zip export. Use when the user wants 2slides themes, create-like-this, or billed narration. Not for local PowerPoint COM/Open XML…
원문 언어: 영어
Builds fully linked income-statement, balance-sheet, and cash-flow workbooks in openpyxl with working-capital, D&A, debt, and NOL schedules plus cash/RE tie-outs. Use for filling 3-statement templates or debugging a BS that will not balance. Do not use for…
원문 언어: 영어
Engineers FDM print-in-place mechanisms (ball joints, knuckle hinges, flexi walls, gears) with per-side clearances and Bambu P1S slicer knobs. Trigger on PiP toys, living hinges, or fused/broken joint diagnosis. Never treat this folder as a Blender…
원문 언어: 영어
Create 3D-printed miniatures and figurines from concept to painted tabletop-ready piece using AI image-to-3D tools, digital sculpting, FDM print settings, support strategies, and post-processing. Trigger when user asks about 3D miniatures, figurines, tabletop…
원문 언어: 영어
Assembles interactive browser 3D with Three.js, React Three Fiber, Spline, Draco GLB, and WebGL fallbacks. Use when the user wants a product configurator, 3D portfolio, or scroll-scrubbed WebGL scene. Not a native Unity/Unreal game skill and not a Blender…
원문 언어: 영어
Redact author-identifying text from academic PDFs for double-blind peer review anonymization — trigger when preparing manuscripts for blind review, anonymizing submissions, or stripping names/affiliations/emails/DOIs from PDFs. Not for scanned image-only…
원문 언어: 영어
Deep-reviews a GitHub repo, local project, CLI, docs, or product for high-leverage bugs, features, UX gaps, and inspiring upgrades—not typo farms. Use when the user says /addvalue, add value, find improvements, or what to build next. Do not use for a /better…
원문 언어: 영어
Load when writing prompts for sub-agents, generation CLIs (jules, agy, claude-code, opencode, codex), or any model emitting structured artifacts (SVG, JSON specs/ops, code files). Turns vague instructions into machine-checkable contracts with mandatory…
원문 언어: 영어
Specifies production agent tools: JSON Schema input_schema, MCP tools/list and tools/call, is_error envelopes, and batched parallel tool_result. Use for function-calling schemas or SDK tool runners. Never substitute this for prompt-only persona design or…
원문 언어: 영어
Build, run, deploy, and evaluate OpenAI Agents SDK apps. Use when the user asks to create or adapt an Agents SDK app, build from a prompt or Codex thread, prepare a runnable agent prototype, add a focused eval harness, or deploy locally through the Agents SDK…
원문 언어: 영어
Designs cross-service flows: signed webhooks, API chaining, CloudEvents, choreography sagas, and transactional outbox publishing. Trigger on Kafka/Pub/Sub, ETL pipelines, or compensating transactions. Do not use for a single-API CRUD wrapper with no…
원문 언어: 영어
Creates Apify Actors with the apify CLI, Crawlee Cheerio/Playwright crawlers, .actor schemas, local apify run, and apify push. Use when the user is bootstrapping or deploying an Actor on the Apify platform. Never confuse this with generic Playwright test…
원문 언어: 영어
Instrument browser/web apps with @microsoft/applicationinsights-web for Real User Monitoring (RUM), page views, clicks, AJAX/fetch dependencies, exceptions, custom events, and browser-side GenAI agent traces. Use when adding App Insights to React, Angular,…
원문 언어: 영어
Runs the astropy Python stack for SkyCoord frame transforms, FITS read/write, unit Quantities, Planck18 distances, and Time scale conversions. Use for ICRS/Galactic/AltAz, WCS pixel-world, or FITS catalog work. Not a general NumPy/SciPy notebook skill without…
원문 언어: 영어
Pulls a video soundtrack into mono 16 kHz 16-bit PCM WAV through the bundled FFmpeg wrapper. Trigger on extract-audio, ASR/VAD prep, or normalizing mixed containers to analysis WAV. Not for stereo music mastering, archival hi-fi, or keeping the picture track.
원문 언어: 영어
Triage Monte Carlo alerts interactively or build an automated workflow. Fetch, score, and troubleshoot alerts using MCP tools now, or design a reusable workflow that runs on a schedule. Activate when the user wants to investigate alerts, set up automated…
원문 언어: 영어
Transcribes speech with Whisper or faster-whisper and overlaps segments onto diarization turns for speaker-labeled text and SRT. Use when the user needs transcripts, captions, or post-diarization word alignment. Do not use for speaker diarization itself or…
원문 언어: 영어
Lays out Apple-style bento grids: mixed-span rounded compartments (1x1, 2x1, 1x2, 2x2) with CSS Grid, Flutter staggered tiles, SwiftUI LazyVGrid, or RN/Compose row stacks. Use when the request is a bento grid, bento-box dashboard, or modular compartment…
원문 언어: 영어
Scaffolds Manifest V3 Chrome, Firefox, and cross-browser extensions: content scripts, service workers, popups, chrome.storage, monetization, and Web Store/AMO publishing. Trigger on browser extension, chrome extension, firefox addon, MV3, or extension popup…
원문 언어: 영어
Compares bounded-cache eviction in stdlib Python: LRU, LFU, FIFO, S3FIFO classes plus a same-trace replay harness for hit rate and residency. Use when picking a policy for a buffer pool, page cache, CDN edge, or LLM KV cache, or when lining up policies on one…
원문 언어: 영어
Manages freight carrier portfolios: lane RFPs, linehaul/accessorial/FSC negotiation, 3-deep routing guides, five-metric scorecards, FMCSA SAFER vetting, and spot-versus-contract mix. Trigger when awarding lanes, scorecarding carriers, or deciding contract vs…
원문 언어: 영어
Automates GitHub Actions quality gates (lint, tsc, test, build, audit), preview deploys, staged rollouts, rollback workflows, and Dependabot. Use when adding or repairing CI pipelines, required PR checks, or deployment automation. Never treat workflow YAML as…
원문 언어: 영어
Embeds Zoom Meeting SDK Web Client View through the ZoomMtg singleton: system check, WASM preload, init/join with passWord (capital W), and inMeetingServiceListener. Use for full-page Zoom meeting embeds or debugging blank-screen, black-overlay, and…
원문 언어: 영어
Applies Jest and Testing Library patterns for React and React Native: getMockX factories, jest.mock GraphQL hooks, renderWithTheme providers, and red-green-refactor TDD. Trigger when writing unit tests, test factories, or module mocks. Do not use for…
원문 언어: 영어
Interviews a vague image idea across 4-7 exchanges, then synthesizes a model-tuned positive prompt, negative prompt, settings table, and pipeline recommendation. Use when the user has a fragment vision and needs a ComfyUI prompt spec before generation. Not…
원문 언어: 영어
Tracks developer-tool rivals on features, pricing, GitHub traction, content, community sentiment, and six-section sales battlecards. Use for competitive intelligence, battlecards, pricing comparisons, or a response to a rival launch. Not a consumer-brand…
원문 언어: 영어
Maps Conductor track, phase, and task ids to commit SHAs, applies git revert newest-first, then realigns plan.md checkboxes, metadata.json counts, and tracks.md. Use when undoing a Conductor work unit on a branch others may already have pulled. Not for rebase…
원문 언어: 영어