Conciseness

Every section carries non-obvious operational constraints — exact URIs, per-runtime tool names, retry-once semantics, limit and threshold guidance — with no padding and no explanations of concepts Claude already knows. Not 4: there is no substantive trimming opportunity; the body is dense and self-contained.

Actionability

Fully concrete and executable: the exact root URI `viking://~/memories/experiences`, a per-runtime tool-name table (`find`/`search`/`read`, `openviking_find`, `ov_search`), parameters (`target_uri`, `limit=5`, `context_type`), the exact error signature (`INVALID_URI`, HTTP 400) with a retry-once recovery procedure, and a worked example query. Not 4: common cases including legacy servers are covered and nothing is pseudocode.

Workflow Clarity

The eight-step retrieval workflow is clearly sequenced with explicit decision and validation points (step 1 executable-task gate; step 4 relevance judgment by "task, environment, preconditions, and likely effect"; step 8 one failure-driven follow-up search) plus a dedicated error-recovery loop for `INVALID_URI` rejection. Not 4: checkpoints and feedback loops are explicit, not implied.

Progressive Disclosure

Well-organized sections with headers, and the legacy-alias fallback is clearly signaled from step 3 ("as described in *Servers Without the Home Alias*"), but the skill is a single ~130-line file with no bundle — the niche v0.4.16 fallback procedure is inline edge-case detail that could live in a separate reference file. Not 5: over 50 lines with edge-case material inlined; not 3: structure and navigation are good.

Specificity

"Retrieve and apply OpenViking Experience memories through the Agent runtime's generic OpenViking search and read tools" names the domain and concrete actions tied to specific tools, but the action list is not comprehensive ("apply" is generic and result selection/judgment is only implied). Not 5: only two core actions and one is abstract; not 3: more than 1-2 actions with tool-level specifics are stated.

Completeness

"Retrieve and apply OpenViking Experience memories through the Agent runtime's generic OpenViking search and read tools" clearly answers what, and "Use before or during executable, multi-step, or tool-based work such as ... when prior operational guidance could improve reliability. Do not use for casual chat or simple factual questions" answers when explicitly with concrete triggers and a negative boundary. Not 4: the when-clause is explicit and specific, not merely present.

Trigger Term Quality

Good coverage of natural task-context keywords users would say — "coding, file or data changes, configuration, deployment, workflow execution, and failure recovery" — plus an explicit negative boundary ("Do not use for casual chat or simple factual questions"). Not 5: natural phrases like "prior attempts", "lessons learned", or "we hit this before" are missing; not 3: coverage is good rather than merely some relevant keywords.

Distinctiveness Conflict Risk

"OpenViking Experience memories" is a clear, niche capability unlikely to be confused with other skills, but the trigger scope "before or during executable, multi-step, or tool-based work such as coding, file or data changes, configuration, deployment" is broad and would co-trigger alongside most coding/deployment skills. Not 5: broad trigger conditions create minor overlap; not 3: the domain and tooling are clearly distinct.