Shape agent capabilities into your workflow.

Use maxym-ai-ads to build a paid-media plan from a website or review campaigns that are already running. Its Claude Code workflows cover audiences, budgets, funnels, copy, creative briefs, landing pages, and audits across Google, Meta, LinkedIn, TikTok, Microsoft, YouTube, and Apple Ads, then guide tracking setup, launch, and biweekly optimization. Most workflows need no ad-account connection; image generation requires a separate provider.

For landing pages, dashboards, SaaS interfaces, and component libraries, the skill starts from a design brief, defines color, typography, spacing, and motion tokens, then implements with concrete component and animation patterns. It self-scores design quality, originality, craft, and functionality, adds a WCAG 2.2 AA gate, and assumes a Next.js, Tailwind, and shadcn/ui-oriented stack by default.

Holocron adds role-specific agents and engineering commands to Claude Code for planning, implementation, testing, security review, debugging, and documentation. Its SQLite and FTS5 “crystal” stores corrections and recalls relevant lessons in later sessions, so repeated guidance can become durable project knowledge. The plugin requires Node 18 or newer and an npm install for its native database dependency.

Ask about AI regulation, policy, law, or governance to receive a cited conversational answer, a topic briefing, a recent-development update, or a one-question-at-a-time quiz. The skill prioritizes an editable list of regulators, standards bodies, legal analysis, research, and trackers, and uses live retrieval for time-sensitive topics. Outputs can be reshaped for Slack, Confluence, email, or social posts.

fumeng combines gpt-image-2 mockups, MCP-fetched components and assets, and a structured frontend design method. Its three playbooks help users explore a visual direction, translate an existing mockup into code, or audit a live interface against the intended design. It works with Claude Code, Cursor, and Windsurf; image-led exploration requires gpt-image-2 access, while the fuller workflows depend on relevant MCP tools.

Use this Claude Code skill for straightforward Word-document work on Windows, especially when Cyrillic or other non-ASCII text causes encoding failures. A Python script extracts paragraphs and tables as UTF-8, while a Node script builds DOCX files from a JSON specification with headings, lists, images, and tables. It deliberately omits tracked changes, comments, footnotes, and in-place find-and-replace, and requires Python plus the global docx package.

Search the JSONL conversation history stored under `~/.claude/projects/` and return matching user or assistant turns with surrounding context, timestamps, session IDs, and file paths. Filters can limit dates, context turns, snippet length, and result count, after which the selected session can be reopened with `/resume`. The Python tool runs locally without network calls or third-party dependencies.

Use eight agent skills to investigate wallets, tokens, transactions, market data, smart-money activity, and MEV across Dune, Solscan, Nansen, Solana RPC providers, pump.fun, Dexscreener, and CoinMarketCap. The workflows prefer parsed and batched endpoints, estimate or gate costly calls, and include resumable asynchronous Python examples for larger jobs. Most paid data providers require your own API keys.

Use this Claude Code skill to create the right robots.txt, ai.txt, llms.txt, or TDM opt-out file for a website's actual policy. Its audit mode checks existing files for outdated AI user agents, crawler inheritance traps, and mismatches between training and search access, while distinguishing unrelated specifications that share the ai.txt name.

imap-client lets an AI agent turn inbox questions into read-only myl commands for searching messages, viewing content, and downloading mail or attachments. Credentials stay in environment injection or a permission-restricted file rather than generated commands. It supports Gmail, Yandex, Mail.ru, and many discoverable IMAP providers, but it cannot send, move, delete, or label messages.

emoji-speak converts explanatory prose in Claude Code into emoji-heavy responses while leaving code blocks, inline code, file paths, URLs, error messages, version numbers, and proper nouns unchanged. It can reduce output tokens for naturally verbose explanations, but the project's own benchmark notes that wrapping already-short answers in emoji may use more tokens instead.

Use this skill when a Midnight wallet stalls, a deployment hangs, the wrong address is selected, an RPC endpoint is blocked, or a Groth16 verifier may not match its local key. It maps symptoms to focused runbooks and includes scripts for address derivation, reachability checks, hash parity, and post-deploy verification. It is intended for developers operating Midnight Network backends through Claude Code, Codex, Cursor, or another markdown-aware agent.

This Claude Code skill pulls design context through Figma MCP, produces a design-spec checkpoint, and then generates resources, styles, drawables, XML layouts, and minimal ViewBinding code in a controlled order. It validates the result with an Android build and can iterate from screenshot differences. The workflow is intended for Android View-system projects rather than Compose.

Have the agent emit semantic JSON instead of raw HTML, then render it as a self-contained file with styles, scripts, and fonts included. Reports, diagrams, or documents can be stacked into a persistent dashboard and restyled later without changing their content. The files open offline and can also be published through GitHub Pages or a custom deployment.

memory-map bundles three skills that preserve project progress, decisions, and pending work after a conversation ends, recall relevant context in later sessions, and propose cleanup when stored memory becomes stale or cluttered. It uses a local Markdown file in Claude Code, the persistent memory interface on claude.ai, and can be installed in other tools that support the Agent Skills format.

Convert Feishu Dou or Feishu Minutes transcripts into an eight-section note for meetings, interviews, courses, podcasts, and other dense recordings. The skill separates recap, business implications, reusable content, methods, and actions, attaches stable IDs with source, value, and timestamp labels, and can render a Mermaid relationship map or an HTML card version.

Provide a screenshot, PDF, HTML snippet, or form description in Claude Code, Cursor, or Windsurf, and the tool returns validated FormEngine JSON plus a runnable App.tsx. The schema can round-trip through the online visual builder and render with RSuite, Material UI, or Mantine, making it easier to edit and reuse than one-off JSX. It currently depends on an LLM host that can load the skill or rule; the standalone MCP server is still planned.

Use this skill to route marketing tasks across Google Ads, Google Analytics 4, and Google Tag Manager, combining them for campaign analysis and changes, funnel diagnosis, tag debugging, conversion reconciliation, and weekly reviews. Each service still requires its own SDK, MCP connection, and authentication. GA4 access is read-only, campaign creation is recommended through the Ads web interface, and conversion totals across the three systems should be reconciled rather than forced to match.