Conciseness

The body is dense but nearly every token carries real, non-inferable constraints (hook config precedence, 'external_id' UUID handling, the lifecycle-trace exclusion). It is not 5 because step 2 states the coding-session rules twice — once in the bullet list and again in prose ('Always query... include coding_session... Never run an unscoped...') — and the intro paragraph re-states the description, which could be trimmed.

Actionability

Concrete, executable guidance throughout: the exact tool call 'search_notes' with literal 'metadata_filters' JSON per query, the six config keys, and explicit precedence rules. It is not 5 because step 4 says 'read the highest-signal hits' without naming the read tool or the expected permalink format, leaving small execution gaps.

Workflow Clarity

A clear five-step sequence with explicit error paths — 'if the repository is missing, report that setup is incomplete', 'mention that setup has not been run', and surfacing 'any missing setup or ambiguous project mapping' in the output. It is not 5 because there is no validate→fix→retry analogue (e.g., re-checking the merged checkpoint list), and not 3 because checkpoints are explicit rather than implicit.

Progressive Disclosure

The skill is short (~40 lines of prose) with no bundle files and nothing that clearly belongs in a separate file; the title, intro, and '## Steps' sections are well-organized and self-contained. Per the simple-skill scoring note ('under 50 lines with no need for external references... can score 5 with just well-organized sections'), this fits the top anchor.

Specificity

The description lists multiple concrete actions — "reading active tasks, open decisions, recent checkpoints, and repo conventions" — comprehensively covering what the orientation does, matching the anchor 'lists multiple specific concrete actions; comprehensive coverage'. It is not 4 because coverage shows no minor gaps.

Completeness

Both halves are explicit: what — "Orient Claude from Basic Memory... by reading active tasks, open decisions, recent checkpoints, and repo conventions"; when — "Use when resuming old work or when the user asks where things stand". This matches the anchor 'clearly and explicitly answers both what AND when with concrete trigger phrases'.

Trigger Term Quality

Natural phrases users would say are present — "resuming old work", "where things stand", "active tasks", "open decisions" — but common variations ("catch up", "get up to speed", "brief me on the project") are missing. It is not 3 because keyword coverage is genuinely good, not merely 'some relevant keywords'.

Distinctiveness Conflict Risk

The Basic Memory niche and its triggers ("resuming old work", "where things stand") are distinct, but "before substantial repo work" leaves minor overlap risk with generic session-start/context-recovery skills — matching 'mostly distinct; minor overlap risk with closely related skills' rather than the clear-niche anchor 5.