
Personal planner for reminders, calendar events, and tasks. Use when the user wants to: be reminded of something, plan an event/appointment, or manage personal tasks.
Create and manage scheduled automations. Use when the user wants something to happen automatically on a schedule (e.g. 'send me a daily report at 16:00', 'check the weather every morning', 'remind me to stand up every hour').
Long-term memory — search everything from past conversations. ALWAYS use this skill when the user: asks what was said before, references earlier conversations, wants to know or remember something from the past, asks "what did I/we/you say about...", "do you remember...", "have we talked about...", "what was that thing about...", or any question that requires knowledge from previous days/sessions. Also use when YOU are unsure whether a topic was discussed before. Commands: "index" to reindex, "status" to check index state, "dream" to trigger wiki consolidation, "lint" for wiki health check.
Read and write pawlia configuration settings (interfaces, TTS, transcription, agents, skill-config), switch the active model at runtime, and toggle private mode. Use this to enable/disable features, change providers, adjust interface settings, configure skill parameters, change the model, or enable/disable private mode.
Create new PawLia skills from scratch, improve or audit existing ones. Also manages centralized credentials for skills — store, retrieve, check API keys and tokens that other skills need at runtime. Use when the user wants to: create a new skill, scaffold a skill directory, manage skill credentials, improve or review an existing skill, validate a SKILL.md against the spec, package a skill for distribution. Triggers on phrases like "create a skill", "new skill", "store api key", "add credentials", "improve this skill", "validate skill", "audit skill", "scaffold a skill".
Perform AI-powered web searches using a Perplexica instance. Returns a synthesized answer with cited sources. Use when the user asks for current information, research topics, news, or complex questions requiring web search with summarization.
Headless browser for visiting websites and interacting with them. IMPORTANT: The query MUST be a browser command in one of these exact formats: "open <url>" to visit a page, "click <ID>" to follow a link or button (e.g. "click L3", "click B1"), "fill <ID> <value>" to fill a field (e.g. "fill I1 Berlin"), "submit <FORM_ID>" to submit a form (e.g. "submit F1"), "show" to re-display the current page, "back" to navigate back. Do NOT pass natural language or search terms as the query — pass the command directly. Example: to open bahn.de use query="open https://bahn.de"
Read, write, list, and delete files in the user's personal workspace. Use for creating notes, saving text, reading previously saved files, writing workspace config files like identity.md, soul.md, user.md, and deleting files like bootstrap.md. All filenames are automatically lowercased.
Create and manage research projects with their own knowledge base. Each project has its own RAG instance for indexing and querying documents. Use when the user wants to research a topic, add URLs/documents to a project, or query an existing research project. The query MUST be a command: "create <name> <description>" to create a new project, "list" to list all projects, "add <project> <url> [depth]" to scrape and index a URL (depth for recursive, default 1), "query <project> <question>" to query the project's knowledge base, "delete <project>" to delete a project, "rename <old> <new>" to rename a project.
Perform web searches using a SearXNG instance. Use when the user asks for web search results, current information, news, or wants to find online resources.