ak-elementor-studio
A Claude skill that converts HTML, CSS, JS, screenshots, PDFs, Figma exports or design mockups into WordPress Elementor template kits. Built for designers and developers who build WordPress sites.
4,248 plugins. 79,851 skills, agents, commands and MCP servers. 99 get Auto-invokedWhat is this?This plugin ships a FLOW.md router the engine fires, so the matching skill runs itself. No slash command to remember.Learn how →.
A Claude skill that converts HTML, CSS, JS, screenshots, PDFs, Figma exports or design mockups into WordPress Elementor template kits. Built for designers and developers who build WordPress sites.
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause…
Remove the git worktrees review checked PR code out into. Each one is a full checkout on disk; nothing else is touched.
Inspects routing, rendering and build diagnostics for apps built with the Next.js framework.
Compresses large files and noisy tool outputs such as command results, diffs, logs and search results before they enter Claude Code's context, reducing token usage.
Draw an architecture, system, or flow diagram as a committable hand-drawn (sketch) image — SVG + PNG — in the Excalidraw /…
Verifies that this repo's agent-facing surface - skill-doc instructions, slash-command frontmatter, and plugin manifests -…
Public, source-cited Obsidian brain for Claude Fable 5, Claude Mythos 5, Project Glasswing, Claude Code, and current agent-operations practice. This is a public research repository.
企業 PRD Writer — 受監管 / 金流 / 風控 / 跨職能團隊等級的產品需求文件撰寫與強化工具, 用於產出可直接進入 Refinement、Engineering Design、Development、QA 與 UAT 的…
Renders multi-slide carousels from HTML/CSS templates using Playwright. Handles slide content injection, brand styling, and PDF…
Print the gitleaks release sha256 for a version, formatted for direct paste into a GitHub Actions workflow or `agent-guard setup…
Multi-agent code review for Claude Code in any language or stack. It runs the repo's own typecheck, lint and tests, has several review agents read the diff in parallel, then has a separate verifier re-check each finding before it reaches the report.
Used when the user asks to "create HTML slides", "generate an HTML presentation", "make animated slides", "build interactive…
Designs API contracts using OpenAPI in the contract component. Generates types consumed by server and webapp.
Agent skills for administering a real UniFi network over its local API: auth, zone firewall, Wi-Fi, clients, and the site map.
Manage Backblaze B2 cloud storage. List files, audit usage, estimate cost, clean up stale data, review security posture, and…
Compound V builder for one run. Starts from a clean context with the run id, the approved spec and the user's request; does the…
Show available THRUNT threat hunting commands and artifact layout
A Claude Code hook that checks the session record before dependent steps such as file edits, notebook edits, git commits and pushes, and session stops run. It helps users verify that an agent's actions are consistent with what it recorded.
Generate a complete handoff document of the current conversation so another LLM (ChatGPT, a fresh Claude, Gemini...) can pick up…
Activate for: chief of staff, orchestration agent, digital chief of staff, daily digest delivery, morning brief, executive…
Configure iterm2-tab-status plugin settings (emoji prefixes, colors, display target, subtitle activity, badge, notifications)
Processes online payments and payouts for merchants across the Middle East and North Africa.
Routes Snowflake-related prompts from Claude Code to Cortex Code CLI, covering SQL, data governance, dynamic tables and machine learning work. Includes setup skills to install the Snowflake and Cortex Code command-line tools.
Apply fable-ish verification discipline to Claude Code coding tasks with risk-proportional workflow, review, and final reporting.…
Evaluate whether a dependency should be kept or decomposed. Use during dependency decomposition (phase 3) to assess each library…
Edits Russian text using Maxim Ilyakhov's infostyle method. It removes filler words, clichés, bureaucratic phrasing and unsupported claims, replacing them with concrete facts and benefits, and adjusts strictness to the context.
Prevents premature execution on ambiguous requests. Analyzes request clarity using 5W1H decomposition, surfaces hidden…
Sole mutator role — applies and verifies code, test, doc, and infra changes.
Gives coding agents semantic code search and editing through language server integration, IDE style codebase navigation.
Extracts a Figma design system into a structured design.md file, turning design tokens into markdown that AI coding assistants such as Claude Code can use. Useful for teams that want their design tokens documented for AI-assisted development.
Use when: new features, component creation, major changes, adding functionality — triggers BEFORE Analyze phase. Do NOT use for:…
Provides RPC nodes, webhooks and enriched transaction data for building applications on the Solana blockchain.
A Claude Code skill for social media work: it builds monthly content calendars, audits a brand's social channels, and runs competitor audits. Useful for marketers and brand teams planning posts.
Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use…
This agent should be used when the user needs to design how a specific feature should be implemented within an existing codebase,…
Steerable code review that challenges the design and approach, not just implementation defects. Read-only; never edits files.
A coding-agent skill that applies SOLID principles and design patterns to backend code, with judgment and restraint. The goal is not to maximize the number of principles or patterns in the code.
Add support for a new AI tool with adapters, CLI, completion, and tests.
Run the fable-mode eval suite (probes → pairwise judge → report). Costs tokens — runs headless claude many times. Optional arg: a…
A collection of agent skills for embedded systems work, covering MCU debugging, C framework integration, charger and fuel gauge ICs, BLE GATT services, and bootloader debugging.
Use when the user wants to ignore, skip, or exclude specific topics from being archived. Triggers on "ignore topic", "don't…
Analyzes a Symfony project (6.4 LTS, 7.x, 8.x) for hexagonal architecture compliance, detects installed Symfony/PHP/Doctrine…
Generate or modify Metin2 client UI code via the m2ui skill (screenshots, descriptions, existing scripts, audits)
AI coding assistant skills for building CrowdStrike Falcon Foundry apps. Build Foundry apps from a natural language prompt, API integrations, workflows, UI pages, functions, collections, AI agents, and knowledge bases, all scaffolded with the Foundry CLI.
Orchestrate multiple LLMs as a council, generating collective intelligence through peer review and chairman synthesis
Forwards a coding/diagnosis/research/recording/scraping/conversion/design-review/code-review/one-shot-ask request to the Google…
Turn rolling-context off for this session (or --global for the whole machine) — full history goes upstream uncompressed, no…
A Claude Code hook that rewrites each user prompt so the AI first works out what is being asked before acting, keeping it aligned from the first message onward. Aimed at developers who want clearer, faster results from Claude Code.
Use when writing project instructions for a coding agent (CLAUDE.md, AGENTS.md, or equivalent). Covers what belongs in them, what…
Scores a codebase against the /assess 0-8 layered contract model, reading the deterministic run-context.json and assigning…
Mini spec-first development workflow for well-scoped implementation tasks with human in the loop.
Adds live web and X platform search results to a coding agent through an existing AI chatbot subscription.
Turn any material into a course that actually teaches. Built on learning science, not content dumps.
Run pre-trained AI models on geospatial imagery. Detect buildings, cars, ships, solar panels, agriculture fields, or use…
Compresses the project memory hot layer when it grows too large. Reads MEMORY.md and schema.yaml, archives older entries into…
Routes each prompt you type to the installed skill that fits it, with the process skill that goes with it, before Claude takes any action. You get fewer missed skills and less time spent on the skill listing every session.
Advanced surface, separate from Foreman's core roadmap job — a standalone prompt builder for work that has no roadmap entry…
Primary session agent for this project. Triages each request and routes it to the right skills; coordinates non-trivial work end…
Hardstop - Pre-execution safety layer for shell commands. Shows status and help.
Provides access to Cloudflare's REST API covering DNS, Workers, storage and security settings on an account.
Gives Claude Code tools to summarize, organize and extract insights from your SpecStory AI coding session history. It also scans for leaked secrets before commits and tracks URLs your sessions fetched.
Use when designing, choosing, or reviewing the rendering layer of any real-time 3D (or 2D-with-lighting) game — the rasterization…
Read-only deep-dive of ONE repository inside a workspace fan-out task. Receives the user task + project_path + seed chunks (with…
A Claude Code workspace for product managers and designers with skills for drafting communications, sourced competitive research, epic drafts, product decisions, and an interactive learning guide. Your vault notes serve as persistent context.
Checklist for adding a new AI provider (image, video, text, audio) that satisfies all 5 integration principles — ACL, bulkhead,…
驗證 Python Agent SDK 應用程式是否正確配置,遵循 SDK 最佳實踐和文檔建議,並準備好進行部署或測試。 使用時機範例: - "驗證我的 Python Agent SDK 應用程式配置" - "檢查 Python SDK…
Extract learnings from the current session and update wp-dev-skills skill files — captures corrections, new rules, edge cases,…
Monitors Claude Code and OpenCode sessions locally in real time, showing tokens, costs, tool calls, agents, MCP activity, sessions and quotas as they run.
Use when about to commit or push a diff that touches two or more locale variants of one file stem, adds catalog or listing…
Extract a full task specification up front (goal, constraints, definition of done), then execute — the primary documented lever…
Turns any text, web page or URL into a ready-to-publish HTML information card. Suited to turning articles, threads, papers and data summaries into shareable image cards for WeChat, Xiaohongshu and X.
Use when the user wants to improve a specific article under a fixed viral-scoring rubric, iterate on one article to raise its…
Deep technical work. Use for complex implementation, deep debugging, cross-module reasoning, architecture review, and risky or…
Install starter or full skill bundle into a target project
geo-score is an open-source AI visibility (GEO) scorer for websites, by Jianrun Tech (见润科技). Formerly geo-watch: geo-watch merged into geo-score in 1.2.0 and lives on as its levels 2 and 3. Website, docs and a free online check: geo-score.dev.
Use when making single-property CSS or Tailwind visual changes in Next.js App Router projects. Presents a floating control widget…
Long, context-heavy investigations that would pollute the main context - exploring a large slice of a codebase, grinding through…
Run a grounded repository-structure review. Usage: /lumin-repo-lens:audit [--root <repo>] [--output <dir>] [--profile…
Production-grade Claude Skills for building, debugging, and shipping n8n workflows, distilled from 100+ production workflows by an n8n Verified Creator. Give Claude Code the instincts of a senior n8n engineer.
Generate a Figma component set from a component contract. Use when the user wants to build or update a Figma component from a…
Use this agent when the user asks to "understand the application", "map the codebase", "analyze the architecture", "identify…
Cancel the active dev workflow loop (archives by default, --hard to wipe)
Quizzes you on the code Claude Code just wrote to confirm you understand it, and by default blocks the session from continuing until you pass.
生成"黑墨手绘涂鸦"风格的动画架构图/流程图:米色纸面、针管笔墨线、极淡水洗色块、简笔涂鸦图标、序号章、连线上的流动圆点动画、图标微动效。产出单文件自包含动画 HTML(SVG+CSS),可一键导出无缝循环…
Dispatched only by the audit-loop unit on a Light route. Never invoked directly.
Show guardrails status, switch modes, set token cap, or view the audit log. Usage: /guardrails…
Builds polished, interactive HTML presentation decks from a short brief, or rebuilds an existing PDF or PPTX as a single shareable file. Covers pitch, sales, launch, keynote and all-hands decks, and you can edit any element in the browser.
Analyzes the current coding task and picks appropriate background music. Use proactively when the user starts a new type of work,…
Pay down the frozen code-quality baseline and run a full QA sweep
Tells you who is favored, the live score, and what matches are worth watching for football and basketball, using Asian-market odds. A read-only lookup that needs no account or API key.
End-to-end assistant for filing Indian Income Tax Returns (ITR-1/2/3/4) for any assessment year. Takes a user from raw documents…
Lets an engineer describe a stormwater modelling task in plain language and have the work run as a checked SWMM workflow, covering building the drainage network, assembling the model, running calibration and validation, and recording where each input came from.
Local AI skills central library + scoped symlink enablement. One AISkills directory holds every skill source; symlink what you need into a project, the shared user-level Agents directory, or Hermes on demand.
Adds a new runbook to an existing doctor and registers it in the runbook index and mode config. Use when extending a doctor's…
A Claude Code skill that hands implementation work to Sol through the Codex CLI, while Claude plans, orchestrates and reviews the diff. The model that writes the code never grades it.