Find agent skills by outcome

Step 3: Open a second

independent markdown codeblock container directly below the first one.

- Style must be direct

challenging

- Evidence-based scoring of candidate fit across Technical

Architectural

- Generate 4-5 high-pressure

scenario-based technical/architectural questions.

- Identify internal mismatches within the JD (e.g.

Remote vs. Onsite contradictions

Creative

- Part B: Target Matrix: List 3 logical target personas or roles structured by the Reply-Probability Scoring Model (0-10). Rank them #1 (Best Lead)

Creative

- Part A: X-Ray Blueprint: Output exactly 6 Google X-Ray strings using clean paragraph spacing. Format each target with a clear title line

followed by the raw search string text below it. Do not append source tags anywhere within Part A:

> Use a Blockquote block. List specific

granular rejection triggers during the interview loop (technical answers

- Pre-Processing Rule: Before outputting strings or targets

resolve all template syntax variables (e.g.

> Use a Blockquote block. Detail operational landmines: burnout vectors

architecture ambiguity

Coding & Debugging

- Break down what the Hiring Manager

Peer Engineers

- Specific expectations broken down by Days 1-30

31-60

- Pinpoint the strategic Why (pain

scale

- Contrast HR brochure language against technical debt

legacy processes

- Group logically by type (e.g.

Core Tech

- Follow immediately with a detailed text breakdown of missing dependencies

legacy tooling

Creative

- Departmental Economics: Focus strictly on department-level mechanics. Detail inferred department budget allocation

tooling investment choices

- Derived Title Intelligence: Explicitly break down everything derived from the position name

including standard market tier (e.g.

Coding & Debugging

- Provide a comprehensive 3-4 sentence engineering justification detailing cultural

technical

- Self-Check: Before writing the final output

verify that all sections (0-18) are fully written with zero omissions or summarized placeholders.

- Output ONLY the requested report format. Absolutely no conversational intro

outro

· IF total input tokens exceed context window or near limits: Prioritize structural completeness. Condense Section 6 (Taxonomy) and Section 13 (The Hunt) to raw bullet arrays to preserve full

verbose architectural depth in Sections 5

· IF source URL is missing

scrubbed

· IF input is a vague/short recruiting agency brief: Maximize industry-standard architecture inferences across Sections 1