build-team
Propose and, after approval, configure a personalized team of Codex subagent roles based on the user's profile, goals, and working style.
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).
$ npx -y skills add kbanc85/claudia --skill morning-brief --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/morning-briefContext preview
The summary Claude sees to decide when to auto-load this skill.
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).
name: morning-brief description: "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)." effort-level: low
Provide a concise morning brief to start the day with clarity. Surface what matters, flag what's at risk, and set up the day for focus.
1. **Call the `memory_morning_context` MCP tool** to get a curated morning digest in a single call:
2. **Call `memory_multi_recall`** for follow-up queries (batches multiple searches in one call), or `memory_recall` for a single specific query
3. **Check `context/judgment.yaml`** for surfacing rules with `trigger: "morning_brief"`
Use `context/commitments.md`, `context/waiting.md`, and `people/` files.
Before reporting status for any active project, check if it has a workspace with source files.
**Step 1: Detect active workspaces**
Check if the `workspaces/` directory exists and has subdirectories. Each subdirectory is a project workspace.
**Step 2: For each active workspace, scan source files**
For each workspace subdirectory, check for directories that contain trackable items:
workspaces/[slug]/ interviews/ <- Count .md files for interview total meetings/ <- Count for meeting total deliverables/ <- Check status in each file agreements/ <- Check for signed/pending Dashboard.md <- Read for current phase/status
The file count in these directories IS the canonical status. Do not override it with counts from MEMORY.md, context files, or your own recollection.
**Step 3: Report from source, not summary**
When including project status in the brief, report from the file system:
Not from memory: "9 interviews completed (from notes)"
**Step 4: Flag discrepancies**
If a workspace file count contradicts what you have in notes or memory, report both:
> Note: I had 9 interviews in my notes, but found 19 files in the workspace. Using the file count.
This builds trust by showing the verification happened.
**Without workspaces:** If `workspaces/` doesn't exist, skip this step. Rely on database and context file data as before.
---
When enhanced memory is available, use urgency-driven ordering. Use the `memory_morning_context` MCP tool to organize the brief by time sensitivity:
1. **Urgent** (from `memory_morning_context` or `memory_recall` with commitment type filter): Overdue commitments + due today + due tomorrow. These lead the brief. 2. **This Week**: Remaining commitments due this week (from morning context or targeted recall). 3. **Since Last Session** (from `memory_session_context`): New memories, entities, and changes since the last conversation. 4. **Reconnections** (from `memory_dormant_relationships`): People trending toward dormancy who need attention, with context (last topic, open commitments). 5. **Cooling Relationships**: From pattern detection (existing behavior). 6. **Reflections**: Active high-importance reflections from `/meditate`.
The brief should be urgency-driven, not category-driven. The old approach said "here are your commitments." The new approach says "here's what needs your attention RIGHT NOW."
---
If the `memory_session_context` MCP tool returns predictions, lead with them:
Check for urgent items:
From the `memory_recall` MCP tool or `context/commitments.md`:
If workspaces exist with active projects:
This section only appears when workspace directories exist. It uses file-system truth, not summaries.
From the `memory_morning_context` MCP tool's relationship health section:
**Dormant relationships by severity:**
**Introduction opportunities:**
**Forming clusters:**
From predictions or checking `people
Terminal-based AI chief of staff. Remembers relationships, tracks commitments, helps you think strategically. Runs on Claude Code.
Repo: kbanc85/claudia
Propose and, after approval, configure a personalized team of Codex subagent roles based on the user's profile, goals, and working style.
Use Claudia's identity, persistent local memory, relationship context, project routing, judgment rules, and strategic operating style. Trigger for personal,…
Inspect Claudia's unified production memory database and backups. Use for database identity, health, counts, schema, WAL, backup inventory, or an explicitly…
Run Claudia's required first-conversation setup. Use automatically before substantive work whenever the current Claudia workspace has no context/me.md,…
Iteratively improve a local artifact (draft, document, page) by running a hill-climbing loop. The user names the artifact, the evaluator, and the budget.…
Launch the Brain Monitor TUI, a real-time terminal dashboard for watching Claudia's memory system. Triggers on \"brain monitor\", \"show dashboard\", \"memory…