Conciseness

The body is lean and assumes Claude's competence: every sentence carries execution-critical detail (config precedence rules, UUID routing via `project_id`, frontmatter fields to add, example confirmation and output lines). There is no explanation of concepts Claude already knows and no padding. Matches the anchor "every token earns its place".

Actionability

Guidance is fully concrete and executable for an instruction-only skill: exact config keys (`teamProjects`, `primaryProject`, `promoteFolder`), the routing rule ("if the team ref is an `external_id` UUID, pass it as `project_id`; otherwise pass the workspace-qualified name as `project`"), exact frontmatter field (`shared_from: <source permalink>`) and observation format, plus a sample output line. Per the rubric's scoring note, absence of code is not penalized when guidance is this actionable.

Workflow Clarity

Six clearly sequenced steps with explicit validation checkpoints around the risky write: stop if `teamProjects` is empty ("Don't invent a target"), confirm with the user before writing ("wait for a yes. Never share silently"), don't overwrite an existing note, and confirm the outcome with the new permalink. This matches the anchor's validate-before-proceed pattern with error paths (missing config, ambiguous source note) handled.

Progressive Disclosure

The body is well-organized (Steps / Notes) with no dangling references, and there are no bundle files to score against. Not 5 because the rubric reserves a 5 for skills under 50 lines needing no external references; this body is ~60 lines, and the config-resolution detail in step 1 (environment-variable handling, settings precedence) is dense enough that it could live in a reference file if the skill grew.

Specificity

The description names the domain and a concrete action — "Promote a note from your personal Basic Memory project to a shared team project, with attribution" — which matches the anchor for 1-2 concrete actions without comprehensive coverage (no detail on how attribution works, what a team project is, or what the write does). Base specificity would be 4 given several implied actions (promote, attribute, write to team workspace), but the second-person possessive "your personal Basic Memory project" triggers the rubric's voice penalty, bringing it to 3. Not 2 because the action and domain are concrete, not generic like "Processes PDF files".

Completeness

Both parts are explicit: the "what" ("Promote a note from your personal Basic Memory project to a shared team project, with attribution") and the "when" ("Use when the user says 'share this with the team', 'publish this decision', or runs /basic-memory:bm-share"). This mirrors the anchor-5 example structure of what + concrete trigger phrases.

Trigger Term Quality

Quoted trigger phrases "share this with the team" and "publish this decision" are exactly what a user would naturally say, plus the explicit slash-command invocation "/basic-memory:bm-share". Not 5 because common variations like "share this note", "send this to the team", or "make this visible to teammates" are missing.

Distinctiveness Conflict Risk

It occupies a clear niche (Basic Memory note promotion to a configured team project) with distinct quoted triggers, and it actively disambiguates from adjacent behavior — "This is the deliberate way to write to a team workspace — auto-capture never does" — minimizing conflict risk with sibling skills.