Conciseness

The body never explains concepts Claude already knows and is densely task-specific, but it is noticeably repetitious: the reuse policy is stated in Instructions, Preflight 1, and Guardrails; the Windows-shells pointer appears in three sections; and the Instructions section summarizes the workflow twice. Anchor 3 ("mostly efficient but could be tightened") fits — well below anchor 4's "minor instances of over-explanation".

Actionability

Provides an executable Quick start with exact commands, an exact three-line query template, concrete search commands with flags, an explicit merge rule ("dedup by rule `id`", topic-first), and a severity enforcement table. Not anchor 5 because some guidance is conditional prose at point of use — `--args-file`/`--context-file` and provenance stamping are described without concrete syntax where mentioned.

Workflow Clarity

The sequence Preflight (reuse check, auth, scope) → write queries → search/merge → output/apply is clear, with explicit validation gates: unadorned `--version` probe, `isError` check, one catalog-refresh-and-retry, low-return broadened re-run, and empty-result-is-valid. Not anchor 5 because the canonical order is scattered across sections with forward references ("go directly to Output", "follow the detailed workflow below" before the steps it summarizes) and non-sequential section ordering. Read-only search, so the destructive/batch cap does not apply.

Progressive Disclosure

Three real one-level-deep references (skill-updates.md, windows-shells.md, windows-launcher.md), each clearly signaled with a load condition ("before the first call", "only if invocation fails"); Windows and update detail is appropriately split out. Not anchor 5 because substantial conditional policy (sandbox auth diagnostic, Git Bash scope caveat, enterprise update gates) remains inlined in a ~220-line body rather than moved to reference files.

Specificity

Names several concrete actions ("Retrieve and apply Qodo coding rules", "Reuse rules already retrieved", "refresh when that scope changes") tied to four task contexts (implementation, planning, refactoring, code review). It stays below anchor 5 because it never conveys how retrieval works (search, merge, scoping), but exceeds anchor 3's 1-2 action coverage.

Completeness

Explicitly answers both questions: what ("Retrieve and apply Qodo coding rules relevant to implementation, planning, refactoring, or code review") and when (three quoted trigger phrases plus the task-start condition). This matches the anchor-5 pattern of concrete trigger phrases for both what and when.

Trigger Term Quality

Includes natural quoted phrases users would say — "get rules", "load qodo rules", "relevant standards" — plus "when starting a concrete coding task". Good coverage, but misses common synonyms like "coding standards", "team standards", or "check the rules", so it falls short of anchor 5's comprehensive synonym coverage.

Distinctiveness Conflict Risk

A clear niche — Qodo-managed organization coding rules — with tool-named triggers that are unlikely to fire for unrelated skills. Minor overlap risk remains because the generic "relevant standards" trigger could also match style-guide or linting skills, keeping it below anchor 5.