claudia

Iteratively improve a local artifact (draft, document, page) by running a hill-climbing loop. The user names the artifact, the evaluator, and the budget. Claudia edits the artifact, scores it, keeps it if better or reverts if worse, repeats. Use when user says "iterate on this", "loop on this until it's better", "run experiments on this draft", "auto-research this", "make this better and don't stop until it's good". Workspace-scoped, never touches live files, no external actions during the loop.

Propose a personalized team of specialized agents based on the user's profile, goals, and how they actually work. Runs the proposal through an independent Checker, gates on the user's approval, and applies with rollback. Use when the user says "build my team", "set up my agents", "what agents should I have", "design my team", "/build-team", or asks Claudia to tailor her team to their work. See also: `hire-agent` for proactive single-agent suggestions; `structure-generator` for folder scaffolding; `capability-suggester` for command-level additions.

End-of-session reflection generating persistent learnings about user preferences, communication patterns, and cross-session insights. Activates when wrapping up a session, or when user says "let's wrap up", "end the session", "time to reflect", or "meditate". Also extracts judgment rules from decisions made during the session. See also: `weekly-review` and `growth-check` for time-based reflection cadences.

Launch the Brain Monitor TUI, a real-time terminal dashboard for watching Claudia's memory system. Triggers on "brain monitor", "show dashboard", "memory dashboard", "terminal brain". See also: `brain` for a 3D graph view in the browser.

Launch the Brain Visualizer, a real-time 3D view of memory and relationships. Triggers on "show your brain", "visualize memory", "open the brain", "memory graph". See also: `brain-monitor` for a terminal dashboard alternative.

Process meeting notes or transcript to extract decisions, commitments, and insights. Use when user shares transcript or says "capture this meeting", "here are my notes from the call". See also: `meeting-prep` for pre-call briefings; `follow-up-draft` for post-meeting emails.

Check memory system health and troubleshoot connectivity issues. Use when memory commands aren't working, at session start if something seems wrong, or when user asks about memory status. See also: `memory-health` for the data-quality dashboard once connectivity is confirmed.

Draft an email response with tone matching the relationship context. Shows draft for approval before sending. Use when user says "draft a reply", "respond to this email", "write a response to [person]", or shares an email and asks for help replying. See also: `follow-up-draft` for post-meeting thank-yous with meeting context.

Store a document, email, or text for future reference with entity linking and provenance. See also: `ingest-sources` for multiple files; `capture-meeting` if it's meeting notes; `summarize-doc` to get a summary without filing.

Create a post-meeting thank-you or follow-up email with key points and next steps. Use when user says "follow-up email", "thank you note", "post-meeting email", "send a follow-up to [person]", or after a meeting capture when next steps need communicating. See also: `draft-reply` for general email responses unrelated to a meeting.

Periodic reflection on development, skills, learning, and progress toward goals. Triggers on "am I growing?", "development check", "personal growth review". See also: `weekly-review` for tactical week recap; `meditate` for session-level reflection.

Lightweight inbox triage across all configured email accounts. Dispatches fast subagent to fetch, then reviews with judgment. Use when user says "check my inbox", "any new emails?", "check email". See also: `draft-reply` once you pick an email to respond to.

Process multiple source documents with Extract-Then-Aggregate discipline. Use when user shares multiple transcripts, emails, or documents for batch processing. See also: `capture-meeting` for a single meeting transcript; `file-document` for a single document; `summarize-doc` when you only need a summary.

Scan context files to extract entities and relationships into the memory system. Triggers on "who knows who?", "network graph", "map my connections", "extract relationships". See also: `brain` for graph visualization once relationships are extracted.

One-page briefing before a call or meeting with person context, open items, and talking points. Use when user says "prep me for my call with [person]", "meeting prep", "brief me before my meeting", "get ready for my call", or mentions an upcoming meeting where context would help. See also: `capture-meeting` for processing notes after the call; `follow-up-draft` for thank-yous.

Show everything Claudia knows with provenance tracing and entity counts. Triggers on "what do you know?", "show memories", "memory audit", "what do you remember about". See also: `memory-health` for system-level stats and data quality; `diagnose` for connectivity troubleshooting.

Check memory system health and data quality. Use when user asks "how's my memory?", "system health", "memory stats", "data quality", "how's my brain?", or for periodic self-diagnostics. See also: `memory-audit` for content-level provenance; `diagnose` for daemon connectivity issues.

Daily digest of commitments, warnings, and relationship health. Use when starting your day or asking "what's on my plate". See also: `weekly-review` (end of week), `growth-check` (monthly+), `meditate` (end of session).

Create a relationship tracking file for a person with contact info, history, and communication preferences. Use when user says "new person", "add [name]", "create a file for [name]", "track this person", or mentions someone important who doesn't have a file yet. See also: `relationship-tracker` for ongoing health; `meeting-prep` when you have a call coming up.

Create an executive summary of any document at the appropriate level of detail. Triggers on "summarize this", "main points", "give me the gist". See also: `file-document` if you also want to save it; `capture-meeting` if it's meeting notes.

Guided weekly reflection across all relationships, commitments, and projects with pattern analysis. Use at end of week, or when user says "weekly review", "end of week", "reflect on this week", "weekly check-in", or "how did my week go". See also: `morning-brief` (daily), `growth-check` (zoom out), `meditate` (session reflection).

Surface risks, blind spots, overlooked items, and accountability across commitments and relationships. Triggers on "what am I overlooking?", "blind spots", "what's falling through the cracks", "what do I owe?", "am I overdue?", "check my commitments". See also: `risk-surfacer` for the proactive auto-firing version on overdue items and cooling relationships.

Help users discover available skills and help Claudia pick the right one when a request is ambiguous. Two surfaces: discovery (user says "what can you do?", "/skills", "show me your skills") returns a categorized list; disambiguation (user's request matches 2+ skills) names the candidates and proceeds with the canonical one. Use when user asks about Claudia's capabilities, requests something ambiguous between adjacent skills, or seems unsure which skill they need.

Maintain Claudia's wiki, a directory of synthesized Markdown pages about your active entities (people, projects, organizations, topics). Each page is written by Claudia from raw memories, cites its sources, flags contradictions, and grows over time. Use when user says "write a wiki page for [entity]", "what do you know about [entity]" (returns the wiki page if it exists), "update the wiki on [entity]", or after ingesting substantial new content about an active entity. Replaces PARA as the default vault structure for new installs.

Full-context deep analysis for meeting prep, relationship analysis, or strategic planning. Pulls up to 180 memories across multiple dimensions for comprehensive synthesis. Use when "deep dive", "full context", "everything about", "strategic analysis", or when preparing for important meetings.

Deep research on a topic with web sources, memory integration, and stored findings. Also handles quick context-aware lookups when current information would improve the conversation. Triggers on "research this", "look into", "find out about", "dig into", "look up", "what's new with", "check current", "any updates on", "latest info".

Send feedback, ideas, or bug reports about Claudia. Opens a pre-filled GitHub Discussion with system context. Use when user says "feedback", "suggestion", "report a bug", "feature request", or "I have an idea".

Create a workspace skeleton for a new project, client, or venture. Gathers details, creates directory with populated templates, validates generated files, populates dashboard, and updates main dashboard. Use when user says "new workspace", "new project", "new client setup".

View all Claudia memory databases, switch between them, manage isolation. Triggers on "which database?", "switch workspace", "show databases", "list databases".

Find and merge duplicate entities. Use when user says "clean up duplicates", "merge these people", "fix duplicate entities", "dedupe my contacts", or when you notice potential duplicates during conversation.

Health check across active client engagements showing status, deliverables, and concerns. Triggers on "how are my clients?", "client status", "client health check".

Quick view of revenue, expenses, invoicing, and cash flow with key metrics. Triggers on "cash position", "revenue check", "financial overview", "money status".

Review active pipeline, opportunities, capacity, and stalled items needing attention. Triggers on "pipeline status", "capacity check", "what's in the pipeline".