When the Work Spans Days, Not Minutes

Manus-style planning skill that keeps task_plan.md, findings.md, and progress.md on disk so multi-step work survives context loss and /clear.

Dump your messy stream of thoughts, tasks and ideas and get back a clean four-section system (Projects/Ideas, Tasks, Connections, How I Can Help) with zero information loss.

An output-style skill that reshapes every answer around the next concrete action, numbered steps, and zero filler.

Turns Claude into an explore-first planning consultant that grounds in your codebase, asks only the decisions you must own, and — only after your explicit okay — writes one decision-complete work plan.

Compiles a goal into a verifiable task plan and drives a bounded agent loop with machine-run checks, retry caps, and human escalation.

Spawns five mutually hostile agents for a three-round cross-critique debate, then hands only the surviving insights to a dedicated plan agent for formalization.

Turns a project's full claude-mem timeline into a serial, chapter-per-ISO-week narrative built by a chained sequence of subagents.