Loading...
Loading...
Found 3,448 Skills
Capture each agent failure, bucket and count it deterministically, and when a failure class recurs past a threshold, scaffold a candidate rule/skill stub into the propose->gate flow so the same mistake becomes a guardrail instead of repeating. Hamel's create->label->fix->repeat flywheel, self-evolving. Trigger when the user says "log this failure", "record the mistake", "why does this keep happening", "turn failures into rules", "failure taxonomy", "what keeps breaking", or invokes /failure-flywheel. Also run --report periodically to see the top recurring failure classes.
Build a beautiful macOS-inspired documentation site (single HTML file) with a liquid-glass surface system (tiered glassmorphism: opacity ladder, blur scale, edge highlights), animated SVG diagrams, traffic-light window chrome, and a light-blue + white liquid-glass palette (white glass surfaces over a soft blue gradient field, per-section blue-tone theming). Also trigger on "liquid glass", "frosted glass", or "translucent UI" requests for docs/showcase pages. Trigger when the user wants to create a docs site, landing page, showcase, portfolio, guide, tutorial site, feature overview, or product documentation — especially when they mention wanting it to look "clean", "modern", "Apple-like", "macOS style", "glass", "frosted", "animated diagrams", or "single HTML file". Also use when the user has multiple markdown files and wants them rendered into a cohesive visual HTML page with sections. If the user says "6 file" or wants separate pages per topic, generate one HTML file per wiki file (index.html as overview + N topic files), NOT a single combined page.
Deep codebase analysis — populate wiki with architecture, concepts, entities
Mở rộng một draft SPEC ĐÃ ĐƯỢC DUYỆT thành kế hoạch thi hành được — file `DDMMYY-<tên>-PLAN.md` mà một agent KHÔNG có context nào (CLI rẻ chạy headless, không hỏi lại được) vẫn làm đúng: đường dẫn file chính xác, khối Interfaces (Consumes/Produces) khai chữ ký cho task hàng xóm, ràng buộc bao trùm chép nguyên văn, và từng bước 2-5 phút kiểu TDD có code thật + lệnh chạy + output mong đợi. Gọi SAU `/propose` và SAU khi user duyệt ở cổng, TRƯỚC khi dispatch task cho agent. Trigger - "viết plan", "mở rộng proposal thành plan", "plan thi hành", "chuẩn bị brief cho agent", "/plan". KHÔNG dùng để thiết kế hay để hỏi yêu cầu (đó là `/propose`), KHÔNG dùng khi chưa có SPEC duyệt.
README-first AI repo reproduction orchestrator. Use when the user wants an end-to-end minimal trustworthy reproduction flow that reads the repo, selects the smallest documented inference or evaluation target, coordinates the intake, setup, execution, and optional paper-gap sub-skills, enforces conservative patch rules, and writes the standardized `repro_outputs/` bundle. Do not use for paper summary, generic environment setup, isolated repo scanning, standalone command execution, or broad research assistance outside repository-grounded reproduction.
Creative Intelligence Suite for AI-driven ideation, design thinking, innovation strategy, problem-solving, and storytelling. 5 named specialist agents with distinct methodologies — no setup required, all workflows available immediately.
Discovers how analytics tracking calls are actually written in this codebase — the concrete SDK calls, function signatures, and import patterns used to send events. Use this skill whenever you need to understand the existing analytics instrumentation patterns before adding new tracking, when someone asks "how do we track events here?", "show me the analytics setup", "what's the analytics pattern in this codebase?", or any time the instrument-events or discover-event-surfaces skills are about to run and you need to know the correct coding style to follow. Outputs a deduplicated list of patterns with generalized examples and the file paths where each pattern appears, plus the dominant event and property naming conventions inferred from those call sites. Always use this skill before writing any analytics instrumentation code.
Build, migrate, and deploy Next.js apps on Cloudflare Workers with vinext. Use when starting a Next.js project on Cloudflare, moving an existing app to Workers, choosing between vinext and OpenNext, or setting up vinext for Workers. For setup, migration, or deployment, install vinext's upstream skills with `npx skills add cloudflare/vinext` if missing, then read and follow the applicable skill and docs.
Build and troubleshoot Cloudflare K2 or K2 Streams durable logs. Use for stream setup, producing from Workers or HTTP, configuring retention and inputs, and consuming through subscriptions.
Get a Cloudflare Workers app to a working local request by connecting its bindings, secrets, and initial data, then verifying real application behavior. Use for app setup or onboarding after the project exists; use frameworks-on-cloudflare or cf-cli to create or configure the project, and wrangler or cf-cli for isolated commands.
When the user wants to figure out which marketing actually drives conversions and revenue, choose or interpret an attribution model, or reconcile conflicting numbers across tools. Also use when the user mentions "attribution," "attribution model," "first-touch vs last-touch," "multi-touch," "which channel drives revenue," "what's my real CAC," "my dashboards disagree," "Google/Meta says X but GA says Y," "media mix model," "MMM," "incrementality," "geo lift," "holdout test," "how did you hear about us," "self-reported attribution," "dark social," or wants to instrument attribution themselves — "stitch my bookings to their source," "SavvyCal/Calendly attribution," "close the identify gap," "track conversions on a third-party domain," "first-party / self-hosted attribution." For event tracking setup and UTMs, see analytics. For ad-platform pixels/CAPI, see ads. For pipeline and CRM revenue reporting, see revops. For the AI-search attribution blind spot, see ai-seo.
Use Agent Pulse to inspect AI agent activity, token usage, tool calls, model usage, cost, budgets, forecasts, reports, local log sources, health checks, and MCP tools. Use when the user asks to check how much AI agents have been used, what sessions ran, what models cost, whether spending is high, generate Agent Pulse reports, diagnose Agent Pulse setup, or expose Agent Pulse data to other agents.