From phobos
Analyzes user requests by extracting explicit asks, implicit needs, constraints, and unknowns; resolves ambiguity in batch; orders work by dependency and risk. Use for multi-part, vague, or large requests.
How this skill is triggered — by the user, by Claude, or both
Slash command
/phobos:phobos-planThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Wrong order and misread intent are the two most expensive mistakes — each one costs a full redo. Spend 30 seconds parsing before spending 30 minutes building.
Wrong order and misread intent are the two most expensive mistakes — each one costs a full redo. Spend 30 seconds parsing before spending 30 minutes building.
Extract into four buckets (mentally for small tasks, written for large ones):
The user describing a problem or thinking out loud ≠ requesting a change. Deliverable there is your assessment — report, don't fix.
Priority, first match wins:
Tie-breaker: shortest task first — it unblocks feedback soonest.
Controls: "stop phobos-plan" / "normal mode" → off until re-invoked.
npx claudepluginhub broisnischal/phobosParses a request into a verified understanding and ordered execution plan before writing code. Useful for multi-file tasks, vague requirements, or when the next step is unclear.
Decomposes complex work into structured, verifiable tasks before implementation. Useful for features, epics, or redesigns requiring explicit planning.
Strategic planning with auto-calibrated detail, decision rationale, and dependency ordering. Use when starting a new feature, bug fix, refactor, or any non-trivial work. Produces a plan document with tasks, reasoning, and acceptance criteria. Triggers: plan, planning, create plan, implementation plan, feature plan, work plan.