Loading...
Loading...
Found 9,512 Skills
Use when an app uses @pierre/trees to render or control a file tree, including React, vanilla JavaScript, SSR, web components, selection, search, rename, drag and drop, icons, git status, and themes.
Agent-callable Telegram bot tools — send messages, media, locations, contacts, and polls; edit, delete, forward, copy, and pin messages; resolve chats, members, and files. Use when the user mentions Telegram or wants a bot to post, manage, or look up Telegram content — including requests that don't name Telegram explicitly, e.g. "message the team channel", "post this update to the group".
Create, migrate, or align frontend packages and monorepos on Vite+. Use for Vite+ scaffolding, migration, upgrades, `vp` commands, consolidated Vite/Oxlint/Oxfmt/Vitest configuration, hooks, packaging, or CI. Prefer the repository-pinned Vite+ surface and its packaged documentation; preserve existing stacks and proven exceptions.
Lightweight PRIMARY for multi-type orchestration of CTF / AWD / security labs. Hand over control to the sidecar CTF-Sandbox-Orchestrator. Use this when the user mentions CTF, AWD, security labs, or competition questions, and no more specific pwn/APK/IDA route has been activated.
Use hexagonal architecture for external systems; define ports (interfaces) and per-provider adapters; select adapter at composition edge
Fetch and analyze Linear issue with all related context. Use when starting work on a Linear ticket, analyzing issues, or gathering context about a Linear issue.
Copy-trade any Hyperliquid trader automatically. Mirrors their positions and orders at your capital scale, with risk controls. Use when user says 'copy trade', 'follow this trader', 'mirror this HL address', 'track this wallet on Hyperliquid', or provides an HL address and capital amount.
End-to-end testing and click-verification of web apps with Playwright — install, write specs, drive authenticated pages, take screenshots, and run in CI. Use when verifying a web change actually works in a real browser, testing user flows, debugging a UI bug live, or confirming an authed/gated page before shipping. Keywords Playwright, e2e, browser test, click test, screenshot, headless.
Extended `5dive` CLI recipes beyond the everyday core — see the `5dive-cli` skill first for spawning/messaging sibling agents and the basic task queue. Use THIS skill for hiring a ready-made persona off the agent market (`5dive market`, `hire --from-market`) or firing one (`5dive fire`), auth recovery (`error.class=auth_required`, `--defer-auth`, device-code login via `agent auth start/poll/submit`), BYO-provider agents (`--provider`), multi-account auth (`5dive account`), declarative fleets and company templates (`5dive up/down/ps/export`, `team import`), hosting a CrewAI crew (`5dive crew`), controlling agents on OTHER registered boxes (`5dive fleet`), recurring/scheduled work (`task add --recurring`, `5dive heartbeat`) and projects (`5dive project add`), building or editing multi-agent loops — a relay with optional human gates (`task loop start`) or a maker→verifier review loop (`task add --verifier`, `task reject`, `5dive loop` LOOP-7 verbs) — decomposing an outcome into a guardrailed task DAG (`5dive goal add`) or a self-steering objective bound to a live metric (`5dive objective`), compiling durable knowledge into the shared wiki (`5dive memory add`), org-chart writes (`5dive org set`), convening a governance vote (`5dive council`), reading fleet health / token burn / the daily standup (`5dive supervisor`, `5dive usage`, `5dive digest`), a machine-readable health check (`5dive doctor --json`, `5dive selfcheck --json`), a task's causal history (`5dive trace`), the current model id per alias (`5dive models`), Telegram/Discord pairing and shared team-bot setup, a delegated GitHub push-for-review (`5dive push`), or the onboarding wizard (`5dive company`).
Build, review, debug, configure, migrate, teach, or plan Permix type-safe permissions with current docs and a full usage guide. Use for permix, createPermix, setup, check, template, dehydrate, hydrate, isReady, isReadyAsync, ~all/~any, ValidateDefinition, Rules, ReBAC closures, permix/react, permix/vue, permix/solid, permix/svelte, permix/next, permix/tanstack-start, permix/express, permix/hono, permix/elysia, permix/fastify, permix/node, permix/server, permix/trpc, permix/orpc, permix/drizzle, permix/effect, and Permix v3 to v4 migration.
How to reach IntelliStory from any agent: the `intellistory` CLI (install, sign in, pick a project, call ANY tool with schema-checked options, upload/download media, connect Claude/Codex/Cursor/Gemini/Hermes) and the same tools over MCP. Load this first when a task mentions IntelliStory, a project code (HGRD, sq010_sh0020), shots, storyboards, looks, generation, or "put this render on the shot". Other intellistory-* skills assume this one: they name tools; this one says how to call them.
Skill Installation Manager — Automatically reads skill list files, compares them with currently globally installed skills, identifies uninstalled or updatable skills, and performs one-click installation/update. Supports three-level fallback: HTTPS → SSH → direct fetch via MCP/GitHub API. Install using the `npx skills` command as a Global installation, specifying the three Agents: Reasonix / Claude Code / OpenCode. Be sure to use this skill whenever users mention any requirements related to skill installation and management, such as "check skills", "sync skills", "install skills", "skill management", "skill update", "skill sync", "batch installation", "missing skills", etc.