Conciseness

At ~20 lines with zero filler and no explanation of concepts Claude already knows, the body is highly efficient; the one trimmable spot is the near-duplicate governance statements "the **deepline-gtm governs the entire session**" and "The recipe only covers one part of the task. The meta-skill handles everything else the user asked for." This fits anchor 4 ('Efficient; minor instances of over-explanation that could be trimmed') — mostly earned tokens, but one repetition could be consolidated; it is well above anchor 3's 'some unnecessary explanation'.

Actionability

Everything is executable and copy-paste ready: 'npm install -g deepline', 'deepline -h', 'Invoke `deepline-gtm` using the Skill tool', and the exact recipe path '../deepline-gtm/recipes/find-qualified-titles.md' with explicit behavioral directives ('Do not skip docs just because a recipe is pre-selected', 'Conditional access and safety checks still apply'). As an instruction-only router skill its guidance is fully concrete with no pseudocode, matching anchor 5.

Workflow Clarity

The 'Execution order' is a clear numbered 3-step sequence with conditional checkpoints ('only when that gate routes you to it', 'Conditional access and safety checks still apply') and an explicit guard against the main failure mode ('Do not skip docs just because a recipe is pre-selected'). No error-recovery guidance exists for the case where the meta-skill or recipe file is unavailable, which fits anchor 4 ('Clear sequence with most checkpoints present; minor validation gaps') rather than 5's explicit validation and feedback loops — though this read-only search task is not destructive/batch, so no cap applies.

Progressive Disclosure

SKILL.md is a concise router overview with a single well-signaled, one-level-deep reference (the recipe file), loaded conditionally via the meta-skill's routing gate, and the body has well-organized sections (Quick Start / Execution order) with all detail appropriately split out. No bundle files exist in this skill's directory, and the referenced sibling deepline-gtm bundle is not present in this review sandbox, so the path is unverifiable here — but the disclosure structure itself matches anchor 5 ('Clear overview with well-signaled one-level-deep references; content appropriately split; easy navigation').

Specificity

The only capability stated is "finding real role-holders at known company domains from an ICP" — one concrete action with its domain, with no further actions or outputs described (no tool, no search/validation steps, no mention of what is returned). This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' (3); it is above a 2 because the action is concrete rather than generic like 'Processes PDF files', and below a 4 because there is no list of several specific actions.

Completeness

The 'when' is explicit and detailed ("Use when... especially prompts like ... or when exact title discovery should precede paid people search"), while the 'what' exists only embedded inside that when-clause ("finding real role-holders at known company domains from an ICP") with no standalone statement of what the skill does or produces. Both are present but the 'what' could be more explicit — the mirror image of anchor 4 ('Has both what and when; when could be more explicit or specific'), and clearly above anchor 3 where 'when' is missing or only weakly implied.

Trigger Term Quality

Natural quoted user phrasings are strong: "find all job titles at these companies", "find qualified titles", "find RevOps or marketing-ops buyers", plus "paid people search" and "ICP" as domain vocabulary with synonyms (job titles / qualified titles / role-holders / buyers). A few plausible natural variations are missing (e.g., "find contacts at these companies", "identify decision-makers", "title discovery"), so this fits anchor 4 ('Good keyword coverage; a few natural terms missing') rather than 5's comprehensive coverage.

Distinctiveness Conflict Risk

The niche is sharply drawn and the sequencing cue "when exact title discovery should precede paid people search" explicitly separates it from a paid people-search skill, and triggers like "find qualified titles" are distinctive. Minor overlap risk remains with closely related prospecting skills (e.g., "find RevOps or marketing-ops buyers" could plausibly fire a contact-finding or buyer-identification skill), which fits anchor 4 ('Mostly distinct; minor overlap risk with closely related skills') rather than 5's minimal conflict risk.