Lists multiple specific concrete actions: converting scope into a structured matter plan, phases, workstreams, milestones, dependencies, owner assignments, and matter setup decisions. These are concrete, domain-specific deliverables.

Clearly answers both 'what' (convert scope into structured matter plan with phases, workstreams, milestones, dependencies, owner assignments, matter setup decisions) and 'when' (explicit 'Use when...' clause plus a detailed 'Trigger on:' list with specific phrases).

Excellent coverage of natural trigger terms including 'build a plan', 'project plan', 'what are the phases', 'who owns what', 'kickoff agenda', 'how do we sequence this', and domain-specific terms like 'task codes', 'rolling wave', 'matter setup'. These reflect how users would naturally phrase requests.

Highly distinctive with a clear niche in legal/professional services matter planning. Terms like 'matter plan', 'task codes', 'matter setup', and 'workstream plan' are domain-specific and unlikely to conflict with generic project management or other skills.

Extremely verbose at ~400+ lines. Contains extensive explanations of why things matter ('A plan that exists only in the partner's head is not a plan — it is an intention'), lengthy descriptions of common failures that read as essays rather than instructions, and repeated justifications for design decisions (e.g., the multi-paragraph explanation of why lawyers don't update plans in Mode 5 and again in Common Planning Failures). Much of the domain knowledge and failure mode content explains concepts an LLM can reason about without being told.

Highly actionable with specific field schemas for every plan component (workstream headers, task entries, milestone entries, dependency entries), exact column orders for workstream plan tables, concrete naming conventions (e.g., [MatterCode]-T-[sequential number]), explicit field mappings from intake to plan, and precise output requirements. The guidance is specific enough to produce consistent, structured outputs.

Clear 6-step sequential process with explicit validation checkpoints: Step 1 requires confirming scope baseline and owner names before proceeding (with a hard stop), Step 5 builds setup recommendations before finalizing, and Step 6 produces outputs in a defined sequence. The skill includes explicit gates ('Do not proceed to plan output until the user has responded'), feedback loops for Mode 5 (propose → confirm → produce), and phase gate decision points throughout.

Monolithic wall of text with no references to external files. The domain knowledge sections (matter type phase patterns, common planning failures), standard plan fields, and communication rhythm content could easily be split into separate reference files. Everything is inline, making the skill extremely long and difficult to navigate. No external file references or clear navigation structure beyond section headers.