Conciseness

The ~24-line body is lean: a two-line install block and numbered directives with no concept explanations, no padding, and nothing Claude already knows. The repeated emphasis that "deepline-gtm governs the entire session" is deliberate reinforcement of the skill's single governing rule rather than fluff, so the 5 anchor fits; there is no unnecessary explanation that would drag it to 4.

Actionability

Concrete and executable: "npm install -g deepline", "deepline -h", "Invoke `deepline-gtm` using the Skill tool", and a specific relative path ("../deepline-gtm/recipes/account-orgchart.md") with an explicit access condition. It stops short of the 5 anchor because the purpose and success criteria of "deepline -h" are never stated, and there is no guidance for the case where the meta-skill or the referenced recipe path is unavailable; it clearly exceeds the 3 anchor (no pseudocode, no missing key details for the in-scope steps).

Workflow Clarity

The "Execution order" section gives a clearly sequenced 1-2-3 process with a conditional gate ("only when that gate routes you to it") as a checkpoint. It misses the 5 anchor because there is no validation or recovery step for failure modes (meta-skill not found, gate not routing as expected); the destructive/batch cap at 3 does not apply since this is a read/routing skill.

Progressive Disclosure

A clear router overview with well-organized sections and one clearly signaled, one-level-deep conditional reference to "../deepline-gtm/recipes/account-orgchart.md"; this skill's own bundle has no references/, scripts/, or assets/ directories. It falls below the 5 anchor because the one reference points into a sibling skill's bundle rather than this skill's own files — a hard external dependency (the path does not resolve in this environment) with no fallback, which is a minor organization gap.

Specificity

"Build an interactive account org chart, leadership map, buying committee, or manager/report neighborhood around a person" names the domain and several concrete deliverables. It sits below the 5 anchor because it rests on a single action verb ("build") with output variants rather than multiple distinct operations, and above the 3 anchor because coverage of outputs (org chart, leadership map, buying committee, manager/report neighborhood) goes well beyond 1-2 actions.

Completeness

Both questions are explicitly answered: "what" via "Build an interactive account org chart, leadership map, buying committee, or manager/report neighborhood around a person" and "when" via "Use for decision makers, reporting-line candidates, stakeholder mapping, and warm intro paths" with concrete trigger phrases. It also adds explicit skip guidance ("Skip standalone email lookup and unrelated cross-company prospecting"), matching the 5 anchor and exceeding the 4 anchor where the "when" is less specific.

Trigger Term Quality

Natural terms users would say are well covered: "org chart", "leadership map", "buying committee", "stakeholder mapping", "warm intro paths", "decision makers", "reporting-line candidates". It falls short of the 5 anchor because common phrasings like "who reports to whom", "org structure", or "account hierarchy" are absent; it clearly beats the 3 anchor, which requires missing common variations.

Distinctiveness Conflict Risk

A clear niche (person-centered organizational mapping within an account) with distinct triggers, plus an explicit skip clause ("Skip standalone email lookup and unrelated cross-company prospecting") that actively disambiguates from adjacent skills. Anti-drift check against the 4 anchor confirms the skip guidance pushes this firmly to minimal conflict risk.