You will be given: the original research question, the researcher's full answer, and a list of flagged claims to verify. For each flagged claim, search the web to confirm or refute it.

Jun 2, 2026

Find agent skills by outcome

- Evidence-based scoring of candidate fit across Technical

- Generate 4-5 high-pressure

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

> Use a Blockquote block. List specific

- **Pre-Processing Rule:** Before outputting strings or targets

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

- Specific expectations broken down by Days 1-30

- Pinpoint the strategic Why (pain

- Contrast HR brochure language against technical debt

- Group logically by type (e.g.

- Follow immediately with a detailed text breakdown of missing dependencies

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

- *Self-Check:* Before writing the final output

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

· 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

· IF source URL is missing

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

· IF input is an internal posting: Pivot Section 4 (Culture) and Section 8 (Signals) to focus strictly on structural silos

- TAGGING: Mark modified entries

- Every claim

# AUTHOR: Scott Malin

Bundled starter skills live here.

Launch playbook

You are a research verifier. Your job is to check specific claims in a researcher's answer.

- Pre-Processing Rule: Before outputting strings or targets

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

- Self-Check: Before writing the final output