Loading...
Loading...
Found 770 Skills
Upgrade any Pulumi provider to a newer version and reconcile the resulting diff. Use when users want to upgrade or update a provider (including editing package.json, requirements.txt, pyproject.toml, go.mod, or Pulumi.yaml to bump a provider SDK), check for breaking changes before or during an upgrade, fix resources that broke after a provider upgrade, or resolve unexpected replacements, creates, or deletes in a post-upgrade preview. Applies to all providers (aws, azure-native, gcp, kubernetes, aws-native, cloudflare, datadog, etc.) — not just Tier 1. Do NOT use for querying which stacks use what package versions; use skill `package-usage` for cross-stack audits. Do NOT use for general infrastructure tasks.
This skill bridges the current host coding agent (Claude Code, Codex, or Gemini CLI) to IM platforms (Telegram, Discord, Feishu/Lark, QQ, or WeChat). Use for: setting up, starting, stopping, or diagnosing the IM bridge daemon; forwarding agent replies to a messaging app. Trigger on: "link-to-im", "start bridge", "stop bridge", "bridge status", "消息推送", "消息转发", "桥接", "连上飞书", "手机上看claude", "启动后台服务", "诊断", "查看日志", "启动桥接", "停止桥接", "配置", or any mention of IM bridge management. Subcommands: setup, start, stop, status, logs, reconfigure, doctor. Do NOT use for: building standalone bots, webhook integrations, or coding with IM platform SDKs — those are regular programming tasks.
Ban `as` type assertions in a package via the `@typescript-eslint/consistent-type-assertions` lint rule, replacing them with compiler-verified type-safe alternatives. Use when enabling the assertion ban in a new package or fixing violations in an existing one.
alfred_ (get-alfred.ai) platform help — AI executive assistant that autonomously triages email, drafts replies, extracts tasks, and manages calendar. Use when inbox is overwhelming and you need AI to triage email overnight, spending too much time on email replies and want AI drafting in your voice, need tasks auto-extracted from emails into a kanban board, want focus time protected on your calendar, need a daily brief of what matters today, or comparing alfred_ to Fyxer AI, Superhuman, Lindy, or Reclaim. Do NOT use for meeting recording or transcription (use /sales-note-taker) or meeting scheduling and booking pages (use /sales-meeting-scheduler).
BrandJet AI platform help — multi-channel outreach sequences, unified inbox, brand monitoring, AI visibility tracking, lead discovery, social listening, email warmup, Artemis AI agent, and integrations. Use when outreach sequences aren't getting replies, brand mentions going unnoticed, multi-channel sequences feel disjointed, unified inbox is overwhelming, or AI visibility scores are dropping. Do NOT use for designing cadence strategy (use /sales-cadence), cross-platform deliverability (use /sales-deliverability), social listening strategy (use /sales-social-listening), or enriching contacts (use /sales-enrich).
Daily protection and relapse prevention companion for people in recovery. Expert in identifying high-risk situations, managing triggers, maintaining accountability, encouraging therapy/couples counseling investment, and building sustainable recovery habits. Activate on "relapse prevention", "staying sober", "trigger management", "recovery daily", "sobriety check-in", "high risk situation", "couples therapy recovery", "protect sobriety". NOT for active crisis (call 988 or your sponsor), prescribing medications (consult doctors), or replacing counselors/therapists.
Remove, replace, or modify video backgrounds using each::sense AI. Create transparent backgrounds, virtual offices, green screen effects without green screens, blur effects, and professional video compositing.
Self-correcting outreach loop using Exa Websets, Notion, direct Gmail SMTP, and IMAP audit. Defaults to Oulang.ai VC pre-seed raise plus Spanish-Chinese diaspora partnerships, parameterizable for any campaign. Triggers on "next wave", "audit replies", "find more investors", "outreach wave", "follow up unreplied", "fix the previous batch".
Use this skill when working with Unreal Engine async operations, threading, parallel execution, or concurrency. Also use when the user mentions 'FRunnable', 'FAsyncTask', 'TaskGraph', 'UE::Tasks', 'ParallelFor', 'TFuture', 'TPromise', 'Async()', 'thread safety', 'FCriticalSection', 'FRWLock', 'background thread', 'game thread dispatch', or 'thread pool'. For networking async (RPCs, replication), see ue-networking-replication. For asset streaming, see ue-data-assets-tables.
Personal US-equity options trading knowledge base. Use for trade analysis, options strategy recommendations, earnings plays, post-mortems, or ticker mentions in a trading context (e.g., "analyze APP", "sell put on TSLA", "structure for NVDA earnings"). Triggers on multi-leg options (Jade Lizard, bull put spread, iron condor, diagonal, calendar), IV / IV crush, channel checks, earnings positioning, AH action, LEAPS / stock replacement, dealer GEX / gamma exposure / max pain / options chain analysis, or any single-stock options play. Provides concrete strikes, IV-aware structures, and probability -weighted scenarios drawn from 21 trading pitfalls, a gamma framework, and case studies (INTC, Mag-7, APP, NOK, CBRS). Market data via TradingView + Funda AI. Responds in Chinese with English technical terms. **Always sanity-check net vega sign before recommending a directional structure** — wrong vega (credit spread at low IVR, debit spread at high IVR) is a known failure mode; see pitfall 19.
Full Sentry SDK setup for Next.js. Use when asked to "add Sentry to Next.js", "install @sentry/nextjs", or configure error monitoring, tracing, session replay, logging, profiling, AI monitoring, or crons for Next.js applications. Supports Next.js 13+ with App Router and Pages Router.
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.