find-qualified-titles

Use when finding real role-holders at known company domains from an ICP, especially prompts like 'find all job titles at these companies', 'find qualified titles', 'find RevOps or marketing-ops buyers', or when exact title discovery should precede paid people search.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean router skill that does exactly what a recipe shortcut should: minimal executable setup, an unambiguous delegation order, and tight conditional references into the governing meta-skill. The only real weaknesses are the cross-bundle dependency on `../deepline-gtm/recipes/find-qualified-titles.md`, which does not resolve from this skill's directory, and the absence of any recovery guidance if the routing gate or referenced recipe is unavailable.

Suggestions

Add a fallback line for the missing recipe (e.g., 'If the gate does not route to the recipe or the path is unavailable, follow the meta-skill's default routing for ICP/title discovery') to close the recovery gap.

Verify or pin the recipe path — `../deepline-gtm/recipes/find-qualified-titles.md` does not exist relative to this SKILL.md in the current layout; either ship the recipe in this bundle's references/ or state the expected deployment layout explicitly.

Consider one line on what to do if `deepline auth status` reports not connected after the wait timeout, since that is the only failure mode the Quick Start can hit.

Dimension	Reasoning	Score
Conciseness	The body is ~28 lines with zero padding: an install block with a one-line sandbox fallback, three auth commands annotated only where the annotation changes behavior ("# completes Cowork/browser approval; no-op if already connected"), and a three-step routing list. It assumes Claude's competence and explains nothing the model already knows, matching the lean-and-efficient top anchor.	5 / 5
Actionability	The Quick Start is copy-paste executable and the execution steps give concrete directives with an exact relative path ("Read the find-qualified-titles recipe at `../deepline-gtm/recipes/find-qualified-titles.md`"). It falls short of anchor 5 because the core task content is delegated to a meta-skill and recipe file that live outside this bundle — the referenced recipe path does not resolve from this skill's location, so the executable guidance has a minor unresolved dependency rather than fully covering the common case in-skill.	4 / 5
Workflow Clarity	The execution order is a clear, well-sequenced 1-2-3 list with explicit guards ("Read the recipe... only when that gate routes you to it", "Do not skip docs"), and the Quick Start includes checkpoint commands (`deepline auth wait`, `deepline auth status`). It is not a destructive or batch operation so no validation cap applies, but the only feedback loop is the auth-wait step; recovery guidance if the gate or recipe path fails is absent, placing it at anchor 4 rather than 5.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), and for a sub-50-line single-purpose skill that structure is appropriate — the SKILL.md is a clean overview with well-signaled sections. The single external reference is one level deep, explicitly pathed, and access-conditional, but it points into another skill's bundle (`../deepline-gtm/`) rather than this skill's own files, a minor organization gap versus the clean one-level-deep anchor 5.	4 / 5
	Total	17 / 20 Passed

Description

86%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with an explicit what, an explicit 'Use when' clause, and verbatim natural-language trigger phrases that clearly match how users would phrase the request. The what-side is a single composite action rather than a list of capabilities, and there is modest overlap risk with neighboring people-search skills, but nothing vague or over-claimed.

Suggestions

Sharpen the what-side by naming one or two concrete operations (e.g., 'resolves each ICP persona to exact job titles held at the target company domains') so it lists specific capabilities rather than one composite action.

Add a distinguishing qualifier to the buyer-discovery trigger (e.g., 'find RevOps or marketing-ops buyers by title before running a contacts search') to further separate it from general people-search skills.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain and a single concrete action — "finding real role-holders at known company domains from an ICP" — but does not enumerate multiple specific actions (e.g., how the search, filtering, or ICP matching is performed). It sits at anchor 3 (domain plus 1-2 concrete actions) rather than 4, which requires several specific listed actions.	3 / 5
Completeness	Both what ("finding real role-holders at known company domains from an ICP") and when ("Use when finding... especially prompts like...") are explicit, with concrete trigger phrases. This mirrors the top anchor's what-plus-when structure.	5 / 5
Trigger Term Quality	It quotes natural user phrasings verbatim — "'find all job titles at these companies', 'find qualified titles', 'find RevOps or marketing-ops buyers'" — plus the situational trigger "when exact title discovery should precede paid people search", giving comprehensive coverage of the terms a user would actually say. The only minor gap is the absence of closely related synonyms, but the quoted prompt variants cover the common cases, matching the top anchor.	5 / 5
Distinctiveness Conflict Risk	The ICP/company-domain/title-discovery framing carves out a clear niche and the quoted triggers are distinctive. Minor overlap risk remains with adjacent people-search or contact-enrichment skills ("find RevOps or marketing-ops buyers" could plausibly route to a general buyer-search skill), keeping it below the minimal-conflict anchor 5.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: getaero-io/gtm-eng-skills
Path: skills/find-qualified-titles/SKILL.md
Commit: a9b9731

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.