All Skills

Generate Anki flashcard decks from PDF or Markdown study materials. Use only when "Anki flashcard" or "Anki deck" is explicitly mentioned. Do not trigger for generic flashcard requests. Outputs in Anki-importable format (Question | Answer).

Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.

Use when managing the pynchy service on the server — deploying changes, observing logs, checking service status, restarting the service, setting up GitHub auth, rebuilding the agent container, or running any commands on pynchy-server via SSH. Also use when interacting with the LiteLLM proxy — investigating failed requests, model routing errors, spend tracking, health checks, API gateway diagnostics, or modifying the LiteLLM configuration. Also use when the user mentions the LiteLLM UI, dashboard, proxy errors, or model availability.

Use when creating, scaffolding, or updating a pynchy plugin, including channels, MCP servers, skills, agent cores, workspace specs, and container runtime plugins. Also use when users ask how to register plugins via config.toml, add entry points, or validate plugin hook wiring.

Invoke AFTER successful feature implementation when 'that went well', 'save this pattern', 'document this approach', 'capture this solution' - captures reusable code patterns with context (before/after, steps, benefits, trade-offs) for future team knowledge sharing. Auto-triggers on multi-file refactors or complex problem solutions. Specific phrases: 'save pattern', 'document approach', 'capture solution'. (user)

Conducts structured requirements interviews for spec documents. Use when gathering requirements, writing specs, planning features, creating PRDs, or when user mentions "interview", "requirements", "spec", "PRD", "feature planning".

Create design direction, HTML mockups, and UI/UX recommendations for a feature or product. Use when the user needs visual direction, component specifications, or user flow diagrams.

Use when working with non-admin groups that have pynchy_repo_access, understanding git worktree isolation, diagnosing uncommitted work left in a worktree after a service restart, or understanding post-run merge behavior.

Build your MVP following the AGENTS.md plan. Use when the user wants to start building, implement features, or says "build my MVP", "start coding", or "implement the project".

Get oriented with the solopreneur plugin — see your AI team, check project status, and get suggestions for what to do next. Use when you're getting started or need a refresher.

Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

Review and validate pending predictions against current market data. Usage: /validate-predictions

Use this skill when you need to search Datadog logs, query metrics, tail logs in real-time, trace distributed requests, investigate errors, compare time periods, find log patterns, check service health, or export observability data.

Write a product specification (PRD) from a validated idea or feature request. Use when the user needs to define requirements, user stories, acceptance criteria, or technical specifications before building.

Use when working with any code, infrastructure-as-code, configuration files, dependencies, or before claiming security posture is adequate — covers OWASP Top 10, secrets detection, dependency vulnerabilities, IaC security, Docker hardening, and supply chain risks

Run initial NanoClaw setup. Use when user wants to install dependencies, authenticate WhatsApp, register their god channel, or start the background services. Triggers on "setup", "install", "configure nanoclaw", or first-time setup requests.

Generate API test suites from plain-English descriptions as cURL, Postman, or Playwright

Use this skill when the user asks to "create a finding", "record an insight", "what findings exist", "show findings", or wants to create or review evidence-backed analysis insights from crawl observations. Creates and queries curated findings with evidence chains.

Interactive setup for language coaching preferences

Post tweets, like, reply, retweet, and quote on X (Twitter) using browser automation. Use when the user asks you to interact with X/Twitter.

Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.

Managing GitHub notifications inbox. Use when listing, filtering, or triaging notifications (mark read, done, unsubscribe).

Connect to local Weaviate vector database and verify connection health

Create outbound phone calls, web calls, and batch calls using the Vapi API. Use when making automated calls, testing voice assistants, scheduling call campaigns, or initiating conversations programmatically.