Conciseness

The body is lean with no padding or explanation of basic concepts; every section (When-to-delegate table, Invocation, Traps, Verify) earns its place and assumes Claude's competence, matching the lean-and-efficient anchor.

Actionability

It provides a copy-paste-ready shell command with model and flags plus a complete prompt-file template, giving fully executable guidance that covers the common case.

Workflow Clarity

The write-prompt, invoke, verify sequence is clear and includes an explicit "Verify before acting" checkpoint with a feedback path (read inline if the summary looks odd), but it is sectioned rather than numbered and lacks a formal validate-retry loop, placing it at 4 rather than 5.

Progressive Disclosure

No bundle files exist and the skill is self-contained; sections are well-organized and the Related section signals one-level-deep pointers to delegate-opencode2 and agents/delegations.json, matching the clear-overview anchor.

Specificity

"Delegate large-file reads to a cheap opencode2 worker and read only the summary" names the domain and one concrete action pair (delegate + receive summary), but lists no further capabilities, matching the anchor for 1-2 concrete actions rather than the several required for a 4.

Completeness

It states a clear what (delegate reads, receive summary) and an explicit when via the "Trigger:" clause, but the when is just keyword triggers rather than a fuller use-case scenario, so it sits at 4 rather than 5.

Trigger Term Quality

The explicit "Trigger: bulk read, leer archivo grande" plus "large-file reads" gives good natural keyword coverage including a Spanish variant, comparable to the 4-anchor example, though a few synonyms like "read large file" or "summarize big file" are absent.

Distinctiveness Conflict Risk

"bulk read" and the opencode2-specific framing give it a clear niche with minimal conflict risk, though there is minor overlap with the related general delegation skill mentioned in the body.