Skip to content This library is free, offered as dana. If it helps your work, donate here →
penguin tree ai
← back to libraryDonate here

This is one of 3,622 free prompts in the penguin tree ai library. Sign up once and the whole library opens, with new prompts by email.

open the library →

Host talent scout

Produces a category-and-platform-specific host evaluation framework with weighted scoring criteria, a structured candidate profile template, and a comparative shortlist ranking for assessing potential on-camera or…

download .md

Purpose

Generate a rigorous, category-and-platform-tuned evaluation framework and a repeatable candidate profile template for assessing potential hosts — so talent decisions rest on weighted, comparable criteria rather than gut feel. Solves the problem of inconsistent, subjective host evaluations across a production team.

When to Use

Invoke this skill when the user asks to:

  • Evaluate or score one or more host candidates for a show, channel, or franchise
  • Build a standardized host assessment rubric for a talent pipeline
  • Compare a slate of potential hosts and produce a ranked shortlist
  • Define what "good on-camera talent" means for a specific category and platform
  • Onboard a new casting or development team member with a repeatable evaluation process
  • Decide between a proven-but-generic host and a category-native newcomer

Inputs Required

Before starting, collect:

  • Category: The content vertical — sports, lifestyle, culture, news, gaming, food, etc.
  • Platform: Primary distribution — YouTube, TikTok, podcast, broadcast/linear TV, streaming, live
  • Show/format context: 2–3 sentence description of the show, its length, and its tone
  • Target audience: Who this host must connect with (demographic, fandom, or psychographic)
  • Candidate list: Names or descriptions of hosts to evaluate (or "framework only" if none yet)
  • Non-negotiables: Any hard requirements — language, credential, availability, exclusivity
  • Existing talent benchmarks: A current host or comp the team considers the bar (optional)

If no candidate list is provided, produce the framework and blank template only. If platform is missing, default to the dominant platform for the given category and note the assumption.

Instructions

Step 1: Establish the Category + Platform Profile

Before scoring anything, define what this specific context demands. State in 3–5 sentences:

  • The hosting archetype this category/platform rewards (e.g., sports-YouTube rewards fast-take conviction and fandom fluency; lifestyle-TikTok rewards intimacy and relatability; culture-podcast rewards curiosity and interview restraint)
  • The failure mode most common in this context (e.g., broadcast polish that reads as robotic on social; over-scripted energy that kills authenticity)
  • The platform-specific delivery demands (pacing, eye contact, hook speed, run length, editing dependence)

Step 2: Build the Weighted Evaluation Criteria (8 criteria, weights sum to 100)

Score each candidate 1–10 on each criterion, then apply the weight. Tune the weights to the category/platform from Step 1 — do not use equal weights.

Use these eight criteria as the base set, adjusting weight emphasis:

  1. On-camera/on-mic presence — magnetism, watchability, comfort in the medium
  2. Category authority & fluency — genuine credibility and vocabulary in the vertical
  3. Audience connection & relatability — ability to make the target audience feel spoken to
  4. Communication clarity & pacing — articulation, structure, platform-appropriate rhythm
  5. Improvisation & live recovery — handling unscripted moments, guests, or failures
  6. Range & versatility — ability to flex format, tone, or segment type
  7. Growth trajectory & coachability — how much better they get with direction
  8. Brand safety & reliability — history, consistency, professional risk profile

For each criterion, write one sentence on what a 9–10 looks like vs. what a 3–4 looks like in this specific category/platform.

Step 3: Define the Candidate Profile Template

Produce a reusable template with these fields:

  • Candidate name / handle
  • Category-fit snapshot (2 sentences)
  • Weighted score table (criterion | raw 1–10 | weight | weighted points)
  • Total weighted score / 100
  • Signature strength (their single most bankable trait)
  • Development gap (the one thing to coach or cast around)
  • Sample-content assessment (what to watch/listen to and what to look for)
  • Green flags (3 bullets) and Red flags (3 bullets)
  • Verdict: Cast / Develop / Pass — with one sentence of reasoning

Step 4: Apply the Template to Each Candidate

If candidates were provided, complete a full profile per candidate using the template. Score honestly and differentiate — avoid clustering all candidates in the 7–8 range.

Step 5: Comparative Shortlist & Recommendation

Rank all evaluated candidates by total weighted score in a single comparison table (name | total score | verdict | one-line differentiator). Then make one clear recommendation for the lead role and name the strongest developmental pick. Be decisive.

Output Format

  • Structure: Category+platform profile → weighted criteria with scoring anchors → blank profile template → completed candidate profiles → comparative shortlist table → recommendation
  • Length: 1,000–1,400 words (framework + template only: 600–800 words)
  • Format: Structured document with tables for scoring and the comparative shortlist; prose for profiles and profiles' verdicts
  • Sections: Category/Platform Profile → Weighted Evaluation Criteria → Candidate Profile Template → Candidate Profiles → Comparative Shortlist → Final Recommendation
  • Tone: Casting director meets talent-development lead — sharp, opinionated, evidence-based, never flattering for its own sake

Quality Checklist

Before delivering output, verify:

  • [ ] All 8 criteria are present and their weights sum to exactly 100
  • [ ] Weights are tuned to the specific category/platform — not equal across the board
  • [ ] Each criterion includes both a 9–10 and a 3–4 scoring anchor
  • [ ] The profile template contains every listed field
  • [ ] Every provided candidate has a completed profile with a Cast/Develop/Pass verdict
  • [ ] The comparative shortlist ranks candidates by total score and ends with a single decisive lead recommendation

Notes

  • Category authority and audience relatability are almost always the two heaviest weights on social platforms; presence and reliability often outweigh them on broadcast — weight accordingly.
  • Coachability matters more than a high current score for developmental picks — a 6 who takes direction beats an 8 who doesn't.
  • Push the team to score from actual sample content, not reputation or reel highlights; a "sample-content assessment" field exists to force this.
  • When a candidate has one elite trait and one fatal flaw, name it plainly and route them to "Develop" only if the flaw is coachable, not structural.

How to use this skill

This file is a Claude Code skill in Anthropic's standard format — markdown with YAML frontmatter at the top.

Installing in Claude Code:

  • ~/.claude/skills/<folder-name>/SKILL.md — auto-loads in every session anywhere on your machine (recommended for skills you'll use across multiple projects)
  • <your-project>/.claude/skills/<folder-name>/SKILL.md — auto-loads only when working in that project (recommended for project-specific skills)

Restart Claude Code or open a new session to register.

Using in Claude.ai, ChatGPT, Gemini, or other AI tools:

  1. Drag this file into a new chat, or copy and paste its contents
  2. Send your task or request as your next message — the AI will apply the skill where it fits

For Claude Code skill details: https://docs.anthropic.com/en/docs/claude-code/skills