build-team
Propose and, after approval, configure a personalized team of Codex subagent roles based on the user's profile, goals, and working style.
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:
$ npx -y skills add kbanc85/claudia --skill what-am-i-missing --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/what-am-i-missingContext preview
The summary Claude sees to decide when to auto-load this skill.
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:
name: what-am-i-missing description: "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." argument-hint: "[person name or 'overdue']" effort-level: high
Surface risks, blind spots, overlooked items, and accountability across all areas.
From `context/commitments.md`:
From `people/` files:
From `context/waiting.md`:
From `context/patterns.md`:
Looking at the bigger picture:
Cross-reference memory DB against file state to catch divergence:
This step catches the scenario where an interview/task was processed but only some status sources were updated.
## What You Might Be Missing - [Date] ### Commitment Risks **Overdue:** - [Item] was due [date] - [impact] **At Risk:** - [Item] due [date] - [concern] ### Relationship Risks **Cooling:** - [Person] - last contact [X] days ago -> Was: [relationship context] -> Risk: [what could happen] **Open Loops:** - Promised [thing] to [person] - [status] ### Waiting Risks **Overdue from Others:** - [Item] from [person] - expected [date] -> Impact: [why this matters] -> Suggested action: [what to do] ### Pattern Risks - [Pattern] - seen [X] times recently -> Concern: [why it matters] -> Suggestion: [what to consider] ### Strategic Blind Spots - [Thing being neglected] -> Why it matters: [impact] -> Suggestion: [action] ### By Relationship #### [Person/Client Name] **I Owe:** - [Item] - due [Date] **They Owe:** - [Item] - since [Date] [Repeat for key relationships with open items] **Recovery Actions:** - [Overdue item]: [What to do now] ### Data Consistency - [Source A] says [X], but [Source B] says [Y] -> Authoritative source: [which one and why] -> Fix: Update [stale source] to match ### Summary Critical: [X items need immediate attention] Watch: [Y items to keep an eye on] Consider: [Z strategic things to think about] Consistency: [N data mismatches found across sources]
**Full analysis:** Comprehensive review across all risk categories and relationships.
**For specific person:** `/what-am-i-missing [person name]` Filters to only show commitments and risks involving that person.
**Quick overdue only:** `/what-am-i-missing overdue` Shows only overdue items and immediate recovery actions.
**Quick check:** Major risks only, no deep analysis.
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…