claudia-core
Use Claudia's identity, persistent local memory, relationship context, project routing, judgment rules, and strategic operating style. Trigger for personal,…
Propose and, after approval, configure a personalized team of Codex subagent roles based on the user's profile, goals, and working style.
$ npx -y skills add kbanc85/claudia --skill build-team --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/build-teamContext preview
The summary Claude sees to decide when to auto-load this skill.
Propose and, after approval, configure a personalized team of Codex subagent roles based on the user's profile, goals, and working style.
name: build-team description: "Propose and, after approval, configure a personalized team of Codex subagent roles based on the user's profile, goals, and working style."
Design a small team that extends Claudia without fragmenting her judgment or relationship context.
Use `claudia-core`, call `memory_briefing`, then read `context/me.md`, `context/judgment.yaml`, current projects, and any existing `[agents]` entries in `.codex/config.toml`.
Recommend no more than five roles. For each role show:
Keep relationship judgment, strategy, and consequential external actions with Claudia. Ask for approval before changing configuration.
Codex roles belong in `.codex/config.toml`:
[agents.reviewer] description = "Review a deliverable for evidence, clarity, and execution risk." config_file = "./agents/reviewer.toml"
Put the role's model, reasoning, permissions, and developer instructions in `.codex/agents/<role>.toml`. Resolve `config_file` relative to `.codex/config.toml`. Preserve existing config and create a `.bak` before changing an existing role.
Use the user's current Codex model unless there is a concrete reason to choose another. Give read-only reviewers the narrowest permissions that work.
Validate the TOML, summarize exactly what changed, and tell the user to start a new Codex session. Do not claim the team is active until Codex loads the new configuration.
Terminal-based AI chief of staff. Remembers relationships, tracks commitments, helps you think strategically. Runs on Claude Code.
Repo: kbanc85/claudia
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…
Launch the Brain Visualizer, a real-time 3D view of memory and relationships. Triggers on \"show your brain\", \"visualize memory\", \"open the brain\",…