Produce a structured daily brief with updates, metrics, charts, goal progress, KPI risks/opportunities, fleet activity, and prioritized action items from all connected data sources
Configure a newly-created KPI by picking the right measurement approach from connected platforms, recording a first value, and scheduling recurring refreshes
Onboard into a new workspace through an interactive interview — discover platforms, understand the user's priorities, then build the workspace blueprint
Execute a KPI's stored measurement plan, record the new value, and raise a risk/opportunity flag only when movement is actually meaningful
Delegate coding tasks to Claude Code (Anthropic's CLI agent). Use for building features, refactoring, PR reviews, and iterative coding. Requires the claude CLI installed.
Delegate coding tasks to OpenAI Codex CLI agent. Use for building features, refactoring, PR reviews, and batch issue fixing. Requires the codex CLI and a git repository.
Inspect and analyze codebases using pygount for LOC counting, language breakdown, and code-vs-comment ratios. Use when asked to check lines of code, repo size, language composition, or codebase stats.
Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.