Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mohitagw15856/boolean-search-builder
Build boolean and X-ray search strings to source candidates.
Passed 20 of 22 test cases with the skill, and 15 of 22 without it.
and 8 more in the full report
6 fixed14 passed either way1 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need to source lead DevOps engineers based in Austin, Texas who have strong AWS and Terraform experience for a fintech client. Could you map out the core keywords and title variants, generate both precision and recall boolean search strings, provide web X-ray queries for developer networks and professional profiles, and outline a step-by-step refinement strategy along with sourcing notes?
| Checked | Without skill | With skill |
|---|---|---|
| The response explicitly lists exclusions under the keyword mapping section. | Missed | Passed |
| The response includes seniority signals as a separate category in the keyword map. | Missed | Passed |
| The response includes a non-discriminatory reminder regarding protected characteristics in the notes section. | Missed | Passed |
| The response includes concrete rules for both expanding too few results and narrowing too many noisy results. | Missed | Passed |
The instructions your model reads when the skill loads.
Great sourcing starts with a precise search. The skill is turning a role into the right combination of synonyms (titles and skills people actually use), must-haves, and exclusions — then refining as the results come back. This skill writes those strings, including X-ray searches that reach profiles via Google, and a plan to tune the funnel.
Given "find senior backend engineers in Berlin", build the strings anyway — infer the likely title and skill synonyms, seniority signals, and sensible exclusions, labelling assumptions. Provide both a tight and a broad version. Never hand back questions instead of usable strings.
Ask for these only if they aren't already provided (else infer and label):
1. Keyword map — the building blocks before the string:
2. Boolean strings — ready to paste:
AND / OR / NOT / quotes / parentheses correctly.3. X-ray variants — Google searches into specific sites:
site:linkedin.com/in ...), GitHub (site:github.com ...), and any relevant community/portfolio sites — with the same keyword logic.4. Refinement plan — what to change if results are too few (drop a must-have, add synonyms, broaden title) or too many/noisy (add exclusions, require more skills, tighten seniority).
5. Notes — platform quirks (LinkedIn boolean only on certain fields/tiers), and a reminder to keep sourcing criteria job-related and non-discriminatory (no filtering on protected characteristics).
test cases passed, vs 15 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.