Grad Cultivation

What it does

When your agent uses it

• The user needs to study cumulative media effects on audience beliefs
• Evaluate mainstreaming and resonance phenomena
• How does media shape worldview
• Mean world syndrome

Example prompts

• “does watching news make people more fearful”
• “how does media shape worldview”
• “mean world syndrome”
• “/grad-cultivation”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

1. 1Content Analysis
2. 2Measure Exposure
3. 3Survey Beliefs
4. 4Calculate Cultivation Differential

What it can do on your machine

Read from SKILL.md and the folder at commit 4e7f4f8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Grad Cultivation loads about 1.2k tokens when it runs, and up to ~8.2k if it reads all its reference files. Until then it costs about 115 tokens; SKILL.md has 328 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~115

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~8.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from asgard-ai-platform/skills at commit 4e7f4f8, republished under its MIT licence (© asgard-ai-platform). 328 words, ~1,160 tokens.

name

grad-cultivation

description

Apply cultivation theory (Gerbner) to analyze how long-term media exposure shapes worldviews. Use this skill when the user needs to study cumulative media effects on audience beliefs, evaluate mainstreaming and resonance phenomena, or assess how media consumption patterns correlate with perceptions of social reality — even if they say 'does watching news make people more fearful', 'how does media shape worldview', or 'mean world syndrome'.

metadata.category

WP-33 傳播/教育/公共行政

metadata.tags

communication, cultivation, media-effects, television

IRON LAW: Cultivation Is a LONG-TERM, Cumulative Effect

Single exposures do NOT cultivate. It is the PATTERN across thousands
of consistent messages over months and years that gradually shapes
worldviews. Key mechanisms:
1. MAINSTREAMING: Heavy viewing overrides demographic differences,
   creating a homogeneous worldview
2. RESONANCE: When TV messages match a viewer's lived experience,
   the cultivation effect is amplified (double dose)

# Cultivation Analysis: {Topic/Context}

## Media World
- Content analyzed: {media type, sample, period}
- Key portrayal patterns: {recurring themes, over/under-representations}
- "Television answer": {what media suggests is true}

## Real World
- Actual statistics: {objective data on the topic}
- Gap: {difference between media portrayal and reality}

## Cultivation Differential
- Heavy viewers: {beliefs/perceptions}
- Light viewers: {beliefs/perceptions}
- Differential: {magnitude, controlling for demographics}

## Mainstreaming/Resonance
- Mainstreaming: {evidence of worldview convergence among heavy viewers}
- Resonance: {subgroups where lived experience amplifies effect}

## Limitations
{Confounders, third variables, directionality concerns}

© asgard-ai-platform, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in grad-cultivation of asgard-ai-platform/skills.

• SKILL.md
• examples/sample_scenario.md
• references/cultural-indicators.md
• references/digital-cultivation.md

Open the folder on GitHubat commit 4e7f4f8