Total 58,387 skills
Showing 12 of 58387 skills
Rewrite text to remove AI tells. Use when editing or reviewing writing that sounds like a chatbot wrote it. Detects and replaces inflated significance, rule-of-three, em dash overuse, AI vocabulary, condescending openers, reader-lecturing, signposting, and other tells.
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for motivation.
TinyLaunch platform help — weekly product launch platform for indie makers (Product Hunt alternative). Covers free submission (DR60-71 dofollow backlink for Top 3), $39 premium launch (skip queue, guaranteed dofollow backlink), weekly badge system, newsletter sponsorship ($50/issue to ~11,000 subscribers), featured spot placement ($15-$30/week), submission service (50-100 directories), and feedback/review services. Use when your product isn't getting noticed by indie makers, you want a high-DR backlink but aren't sure if TinyLaunch is worth it, you're torn between free and premium launch on TinyLaunch, or you're wondering how TinyLaunch stacks up against other directories. Do NOT use for multi-directory launch strategy (use /sales-launch-directory). Do NOT use for Product Hunt launches (use /product-hunt-launch).
AI-powered browser extension that filters unwanted posts from Twitter/X feeds using natural language rules and multiple AI backends
Create custom QA agent personalities for project-specific testing needs. Guided builder that asks about the specialty, tools, and test scenarios, then generates a personality file and registers it in the QA config. Trigger on "create a QA personality", "add a custom test agent", "build a webhook tester", or when the user needs a project-specific QA agent. Also triggered by /qa-create-personality.
Help Portaly creators run follower-email campaigns end-to-end — create a draft, send it via Vibe MCP, read post-send analytics — and wire up where the invitation email's CTA redirects (Portaly-hosted waitlist, or a self-hosted /waitlist/[slug] page). Trigger when the user mentions invitation emails, follower outreach campaigns, sending an email blast to followers, drafting an email campaign, waitlist signup landing page, app base URL, embedding a waitlist CTA, or asks how the registration email link works / where it lands.
Reads a user's Link financial data — transactions, balances, and wallet sources — so agents can answer questions about spending and available source capabilities. Use when the user says "check my balance", "how much did I spend", "show my transactions", "what accounts are connected", "summarize my spending", "recent purchases", or asks about their financial activity, account balances, or linked sources.
Use when building custom agent backends, implementing the AG-UI protocol, debugging streaming issues, or understanding how agents communicate with frontends. Covers event types, SSE transport, AbstractAgent/HttpAgent patterns, state synchronization, tool calls, and human-in-the-loop flows.
Programmatically create and manipulate Obsidian Canvas (.canvas) files using JSON Canvas Spec 1.0. Enables agents to generate visual flowcharts, architecture diagrams, and planning boards. Use when creating or editing visual canvas files.
Full personal Telegram control over MTProto (Telethon) with the user's own account — list/search chats, read & summarize history, see unread, look up contacts & chat info, download media, and send / reply / forward / edit / delete / react / send files / mark read. Use when the user mentions Telegram, a Telegram chat/group/contact, "我的 Telegram", reading/replying/forwarding/summarizing Telegram messages, their unread Telegram, or sending a file/message on Telegram.
Use when you need durable, repo-specific context (architecture, domain model, how a flow works, standards, gotchas, decisions) before engineering or reviewing, or when you have learned something worth recording. Reads and writes an in-repo Obsidian knowledge base (docs/<repo>-vault/), synced by git.
Audit any eval, metric, experiment, or benchmark for leakage — does external ground-truth enter independently, or are the model, scorer, and designer just confirming a result no outside truth ever produced? Use before trusting any 'how we'll know it worked' — an A/B, a holdout, a score, a validation — and whenever a result feels too clean or self-confirming. Walks an 8-pattern leakage taxonomy and returns only the patterns that fire, each with an independence fix. Read-only.