Conciseness

The body is lean: it provides commands and a routing table without explaining concepts Claude already knows, so every token earns its place rather than the padded score-1 style.

Actionability

Gives fully executable commands (e.g. 'python3 ./.trellis/scripts/get_context.py --mode phase --step <X.X> --platform kiro') plus a concrete status/artifact routing table, matching the copy-paste-ready score-3 anchor.

Workflow Clarity

A clear 4-step sequence with an explicit decision-tree checklist (status + artifact presence) and gating checkpoints ('only run task.py start after user confirms') exceeds the mere list-without-checkpoints score-2 anchor; the task is navigational, not destructive, so no validation cap applies.

Progressive Disclosure

The body is an entry point that keeps only routing logic inline and defers full detail to the one-level reference '.trellis/workflow.md', clearly signaled in a Reference section, rather than a monolithic wall or nested references.

Specificity

Lists multiple concrete actions ('Loads the workflow Phase Index', 'figures out which phase/step to pick up at', 'pulls the step-level detail via get_context.py --mode phase') in third person, matching the score-3 anchor rather than the domain-only score-2 example.

Completeness

Explicitly answers both what (load/figure/pull step detail) and when ('Use when coming back to an in-progress task and you need to know what to do next'), so it is not capped at 2 for a missing trigger clause.

Trigger Term Quality

Includes natural user phrasing ('Resume work on the current task', 'coming back to an in-progress task', 'need to know what to do next') that a user would plausibly say, giving good coverage rather than the partial keyword set of score 2.

Distinctiveness Conflict Risk

Targets a clear Trellis-specific niche (Phase Index, get_context.py) with distinct triggers unlikely to fire for unrelated skills, rather than the overlapping generic anchors at lower levels.