All authors
Claude Skills by tomw1808
github.com/tomw18083 skills0 installs0 views
- DelegateRun a goal through flash workers instead of Claude subagents: frame it, cut it into coherent slices, dispatch with flash_task/flash_batch, verify every result yourself, review with a read-only worker, fix in rounds until a review finds nothing real, then apply. Use whenever the user says "use flash-agents", "fan out", "delegate this", or when a task means reading or writing more code than fits a tight token budget. Not for design decisions; those stay with you.Votes: 0GitHub stars: 4
- GauntletOrchestrate cheap parallel builder and critic subagents toward a runnable quality bar. The orchestrating (frontier) model frames the task, filters findings, and judges finalists in a blind A/B duel; smaller models do the building, critiquing, and revising. Use for tasks whose result can be checked by running something. Do not use for design decisions or vague goals.Votes: 0GitHub stars: 4
- SetupCheck and finish the Flash Agents prerequisites — the harness, Ollama, the model, and the service profiles — then prove the pipeline with one real worker task.Votes: 0GitHub stars: 4