compare-candidates

Book a meeting into the team's calendar files under the booking policy.

Build benchmarks of realistic, hard agent tasks, researched from real work, admitting only verified, shortcut-resistant, calibrated tasks and reporting how…

Iteratively improve any artifact and its improvement harness, inventing evaluation when needed; supports bounded runs, tournaments and continuous resumable…

Develop a project endgoal through N bounded cycles of brainstorm and research, design, implementation, comparison testing and analysis.

Review Orchflows against its purpose and design principles (architecture, workflow design, wording and bugs) and apply reviewed improvements on unmerged…

Build a complete Three.js game or bounded production phase through mechanics experiments, Blender assets, QA and independent playtests.

Drive an ambitious goal past a real-world quality bar by splitting it into pieces, each looped through a builder and a fresh, harsh, blind critic until ours…

Independently review an existing candidate, revise it at most once, and return the original review separately from the delivered result and checks.

Export an Orchflows workflow as a standalone native skill with a portability report and bounded trial.

Collect what people say across public communities and the web in parallel, then return one independently written, cited brief.

Plan and complete ordinary top-level tasks with core guidance and proportionate independent review, unless the user selects a workflow or primitive.

Implement one approved-scope design in an isolated candidate and return its exact reproducible state.