abtree fragment: run a BDD test spec against its target tree and write a markdown report embedding the mermaid trace.
Tiny jest-style TypeScript DSL for authoring abtree behaviour trees. Renders to the canonical tree-file shape (composite/action nodes with state, evaluate, and instruct steps).
Implement an approved plan with complexity-gated architectural review, following the clean-code rules in clean-code.md.
Greet a user based on time of day. Demonstrates sequence, selector, and action primitives.
Take a documentation goal, ground it in the repo's styleguide, find or build a home in the docs tree, write to it, and gate-check structure / flow / atomicity. Up to three write/review passes (one initial + two retries) before surfacing failure to the hum
Score the effectiveness of a tree using evidence from one of its sessions, find improvements in parallel, draft a plan in plans/, then commit and push.
Continuous code-improvement cycle. Confirms intent + green baseline, scores quality metrics in parallel, snapshots the baseline, hardens findings via a Senior-Principal critique, looks up best practices, triages with a human gate, then iterates through ea
Refine a change request into an approved plan: analyse intent, draft to a per-execution draft file, critique it in place, promote to plans/, then take it through codeowner approval (either in-session or via an assigned MR).
Score the codebase for Single Responsibility violations, snapshot the initial scoring, pause for the human to pick one to tackle, refactor it in a bounded loop (re-scoring after every pass), do a multi-agent code review, and finish with a before-vs-after
Sweep a docs site, classify every page into the MDN orientation / education / reference tiers, score each on clarity, impact, and single responsibility, and gather everything into a private documentation-sitemap.md. A senior-writer critique drives a bound