Loading...
Loading...
Found 2,790 Skills
Drive terminal sessions, panes, and TUIs from an agent — spawn shells, send keystrokes, snapshot pixel-perfect PNGs of any pane, and extend shux itself with line-delimited JSON-RPC plugins in any language. Use when you need to multiplex terminal work, drive a TUI you'd otherwise control with tmux / screen / iTerm2 / expect / pexpect / asciinema / vhs / termshot, run scripted CLI/REPL interactions, do headless visual regression on a terminal UI, or write a process plugin that subscribes to the shux event bus and calls back through `window.rename`, `pane.send_keys`, `state.apply`, etc. Trigger phrases include "drive terminal", "spawn pty session", "send keys to a TUI", "screenshot a tui", "snapshot pane", "replace tmux", "iTerm2 automation", "expect script", "headless terminal test", "agent multiplexer", "asciinema record", "write a shux plugin", "extend shux", "shux plugin install".
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel folding, recompute strategy, dispatcher choice, and CUDA-graph bring-up.
Always-on ambient signal capture. Fires on every inbound message to detect original thinking and entity mentions. Spawn as a cheap sub-agent in parallel, never block the main response.
Read-only Storage Analysis Assistant for macOS / Windows (auto-detects system). Scans the entire disk usage to identify space hogs, categorizes each item into three levels: 🟢 Auto-cleanable / 🟡 Manual judgment required / 🔴 Clean with caution, and provides actionable disposal plans. Generates an interactive HTML report with beautiful formatting, collapsible sections, and one-click copy commands. Also supports starting a local service to delete files directly via the web (move to trash / delete immediately). The entire scanning process is read-only. Must be used in the following scenarios: When users mention "storage analysis", "disk full", "C drive/hard disk full", "insufficient space", "clean up space", "disk cleanup", "space occupied", "what's taking up space", "help me check storage", "check computer storage/space", "storage space", "computer space insufficient", "memory full/insufficient" (in Chinese colloquial, "memory" often refers to storage), "storage analysis", "disk cleanup", "clear cache", "disk cleanup"; or when users complain about insufficient computer space, want to know what's taking up hard disk space, or need cleanup suggestions. Note: If users explicitly refer to RAM (e.g., "which process is using memory", "high memory usage", want to see Activity Monitor), that's RAM, not storage, and does not belong to this skill.
Primarily the agent's internal-thinking skill — invoke it silently to model a problem, identify trade-offs, and decide what to do, BEFORE asking the user anything or dispatching another skill. Workflow skills call `/culture` as their step-1 reasoning pass; the agent does not surface the dialogue. Only treat this as a user-facing skill when the user has explicitly opted out of writes — phrases like "no writes", "just rubber-duck this", "let's only talk", "/culture". In the user-facing path the output is conversation; the only sanctioned artifact is an opt-in `.cheese/notes/<slug>.md` handoff slug at session end if the user asks for notes. Culture never writes to production code, never commits, never opens PRs. If the dialogue reveals real work, recommend `/mold` (fuzzy → spec) or `/cook` (clear ask → code) and stop. Before `/mold` or `/cook`.
Community skill for applying the Geist design system to Vercel-inspired UI across React, Next.js, Vite, Astro, Svelte, Vue, HTML/CSS, Tailwind, shadcn, and Radix surfaces. Use it for typography, spacing, color tokens, material treatment, component styling, app shells, dashboards, forms, tables, dialogs, empty/loading/error states, responsive layouts, and UI polish. This is a community-authored skill, not an official Vercel skill. Trigger on generic visual direction such as clean, modern, premium, beautiful, polished, SaaS, developer tool, product UI, app shell, navigation, data views, and marketing sections. Skip only when the user explicitly names a non-Geist final visual system/art direction as the final visual authority, supplies a non-Geist design artifact as the final visual authority, or asks for game/illustrative output where Geist UI is not the requested surface.
Build messaging agents and apps with Spectrum — Photon's unified messaging SDK. Write your handler logic once and ship it across iMessage, WhatsApp Business, the terminal, or a custom platform. Spectrum is multi-platform by design and is becoming multi-language; the current SDK is `spectrum-ts` (TypeScript), with additional language SDKs planned. Use this skill for any Spectrum question — quickstart, multi-platform setup, receiving messages, content builders, spaces and users, reactions and replies, platform narrowing, the built-in providers (iMessage cloud/local/dedicated with message effects, Terminal TUI test harness, WhatsApp Business 1:1), custom event streams, graceful shutdown, building your own provider with `definePlatform`, and the production architecture patterns Photon uses internally to ship agents that live natively inside IM apps (five-stage inbound pipeline with debounce → batch flush → mark as read → generate → send, in-flight cancellation with abort signals, drain-in-handler, carry-forward, idempotent retries via stable client GUIDs and a startIndex resume cursor, per-resource memory scope `resourceId` vs `threadId`, durable job-failure audit log). This is the entry point for the skill; consult the topic files in this directory for full reference. Keywords: spectrum, spectrum-ts, photon, unified messaging, multi-platform, multi-language, im agent, messaging agent, imessage, whatsapp, whatsapp business, terminal, tuichat, definePlatform, custom platform, platform provider, platform narrowing, app.messages, Spectrum(), space, send, reply, react, tapback, typing indicator, responding, startTyping, stopTyping, content builder, text, attachment, voice, contact, richlink, poll, group, custom content, message effects, bubble effect, screen effect, line model, dedicated line, shared pool, custom events, app.stop, lifecycle, SIGINT, graceful shutdown, message queue, debounce, batch, in-flight, cancellation, abort controller, carry forward, idempotent retry, client guid, dedup, deduplication, startIndex, resume cursor, working memory, resourceId, threadId, per-resource memory, job failure, audit log, race condition, worker crash, retry, pg-boss, queue worker, conversational agent, chat agent, native messaging, agent architecture, production agent, spectrum patterns, best practices.
This skill should be used when the user wants to bulk-build ArcKit artefacts in parallel rather than running individual /arckit:* commands one at a time. Load whenever the task sounds like 'kick off a build', 'build everything', 'generate all artefacts', 'run all the commands', 'rebuild this project from scratch', 'resume the build', 'pick up where we left off', 'refresh the artefacts', 'run the recipe', 'build the whole project end-to-end', or 'parallel build', or mentions `--plan`, `--resume`, `--target`, `--refresh`, `--recipe`, or `.arckit/state.json`. The skill orchestrates parallel /arckit:* generation using subagent isolation: reads project state, computes the artefact dependency DAG, dispatches one subagent per target per wave (each subagent invokes a /arckit:* skill in its own context), validates outputs, commits the wave, and persists progress to .arckit/state.json for resumability.
亚马逊店铺商品定价（与 linkfox-amazon-store-auth / linkfox-amazon-store-report / linkfox-amazon-store-listings 同系列），经 /spApi/developerProxy 调用 SP-API Product Pricing：v0 的 getPricing、getCompetitivePricing、getListingOffers、getItemOffers、getItemOffersBatch、getListingOffersBatch；2022-05-01 的 getFeaturedOfferExpectedPriceBatch、getCompetitiveSummary。含 ASIN/SKU 单条与批量、FOEP、竞争摘要。当用户提到亚马逊定价、比价、低价报价、listing/item offers、batch pricing、FOEP、featured offer、competitive summary、Product Pricing、SP-API 价格 时触发。
End-to-end retail ETL pipeline using Medallion Architecture (Bronze/Silver/Gold) with TSQL, PySpark, and Airflow for inventory, sales, and supplier data processing
Decision guide for delegating to hui-style subagents. Tells the main thread WHEN to spawn `huicrew-investigator` (locate code), `huicrew-builder` (1-2 file edit), or `huicrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is hui-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use huicrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
Transform research questions into constructs, design, samples, measurement, analysis, falsification, and execution plans. Use when the user asks for "design research", "can this method answer the question?", "help me create a research proposal", or requests the rw-research-design workflow. Runs without a private local workspace or preset research-lab; use user-provided material and bundled public-source methods.