Skills for your AI
Explains AI/ML fundamentals and plans practical applications such as support assistants, recommendations, fraud detection, document processing, and predictive maintenance. Use when an IT specialist asks about AI/ML concepts, model training, ethics, subfields,
Airtable database automation - views, automations, integrations, and workflow triggers
Creates, improves, tests, and packages custom skill files for an AI runtime, including trigger optimization and eval suites. Use when the user wants a new skill built from a spec, an existing skill file refined, an eval run on a skill, description triggers opt
Integrates Apify Actors into existing codebases for scraping and automation, covering Actor selection, trigger design, implementation, testing, documentation, run troubleshooting, and dataset or key-value store output handling. Use when a user wants to scrape
Create and trigger Apple Shortcuts for iOS/macOS automation and cross-platform workflows
Sets up and verifies an MCP server that bridges a containerized agent to local AI models in the Atomic Chat desktop app. Use when integrating Atomic Chat, registering its MCP tools, forwarding host environment variables, or verifying local inference end-to-end
Use when Codex should act as the Automation Governance Architect specialist from Agency Agents. Governance-first architect for business automations (n8n-first) who audits value, risk, and maintainability before implementation.
Finds, plans, and tracks automation opportunities across projects and operations by gathering data, mapping processes, prioritizing candidates, evaluating tools, planning rollouts, and monitoring results. Use when a project manager asks to identify repetitive
Researches, compares, and plans automation testing tools for QA testers, covering features, cost, reviews, compatibility, recommendations, scripts, integration, and test data strategy. Use when selecting automation tools, comparing options, evaluating pricing,
Process multiple documents in bulk with parallel execution
Plans big data projects end to end, covering collection, storage, statistics, visualization, machine learning, pipelines, security, sentiment, forecasting, streaming, storytelling, and domain optimization. Use when planning or reviewing a data project, choosin
Read, write, and browse the AgentHub message board for agent coordination. Use when the user runs /hub:board or asks to post, read, or inspect coordination messages between competing AgentHub agents.
Fetches web pages, search results, and structured platform data through Bright Data MCP tools, including browser automation and AI extraction. Use when the user asks to search the web, scrape a URL, pull structured data from a supported platform, interact with
Automate web browser interactions, scraping, testing, and workflow automation with Puppeteer/Playwright
Use when the user asks to automate browser tasks, scrape websites, fill forms, capture screenshots, extract structured data from web pages, or build web automation workflows. NOT for testing — use playwright-pro for that.
Evaluates a trained checkpoint against a four-stage promotion gate (data quality, capability drift, paired arena, canary) and produces a promotion report with a PROMOTE or REJECT verdict. Use when deciding whether to promote a fine-tuned checkpoint, when revie
Extracts, classifies, assesses, routes, and audits insurance claims, drafts customer updates, and reports on performance and fraud. Use when handling claim documents, screening claims for fraud, routing new claims, drafting policyholder updates, calculating se
Plans cloud networking integration across platform selection, architecture, security, migration, performance, cost, multi-cloud, monitoring, automation, VPN, policy, and disaster recovery. Use when choosing a cloud platform, designing hybrid connectivity, migr
Integrates the Opik client, governs prompts and experiments, manages workspaces and projects, and investigates traces, metrics, and quality gates. Use when onboarding a repo to Opik, versioning prompts, organizing telemetry, debugging latency or cost anomalies
Creates reusable Claude Code slash command markdown files in .claude/commands/ or ~/.claude/commands/ from a user's workflow. Use when the user wants to turn a workflow into a slash command, design or write a custom command, or decide between project-level and
Creates, edits, and organizes Claude Code slash commands as markdown files with YAML frontmatter, and explains command features. Use when the user wants a new slash command, wants to modify or namespace existing commands, or asks about $ARGUMENTS, @ file refer
Turns rough copyright ideas into structured AI prompts for research, drafting, and protection workflows. Use when narrowing a copyright topic, choosing an action word, adding context, specifying output format, or refining a weak AI response.
Turns copyright questions into focused, action-oriented AI prompts with context and output specs. Use when narrowing a broad copyright theme, crafting or refining a copyright prompt, adding background such as jurisdiction or doctrine, or specifying tone, langu
Plans, generates, and analyzes cross-browser test plans, matrices, automation setups, and reports across browsers, devices, and screen sizes. Use when a tester needs compatibility or responsive test plans, browser compatibility matrices, automation setup guida
