Media Literacy logo

Media Literacy

Community
Tibsfox
media-literacy

Media literacy and critical analysis of media messages across platforms and formats. Covers media ecology (McLuhan), encoding/decoding (Hall), news literacy, digital media analysis, propaganda techniques, algorithmic curation, visual rhetoric, and ethical media consumption. Use when analyzing media messages, evaluating news sources, understanding how media technology shapes communication, detecting propaganda, or studying the relationship between medium and message.

Overview

PublisherTibsfox
Repositorygsd-skill-creator
Skill namemedia-literacy
Stars
70
Forks
9
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Tibsfox on GitHub. Read the source before you install it.

Installation

Install the Media Literacy AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Tibsfox/gsd-skill-creator.git /tmp/gsd-skill-creator
mkdir -p .claude/skills
cp -r /tmp/gsd-skill-creator/examples/skills/communication/media-literacy .claude/skills/media-literacy
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Media Literacy in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Media Literacy on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Media Literacy is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Media Literacy

Media literacy is the ability to access, analyze, evaluate, create, and act using all forms of communication. It goes beyond the ability to read and write -- it is the ability to navigate a media environment where messages are constructed, distributed, and consumed through technologies that shape their meaning. Marshall McLuhan's dictum "the medium is the message" is the founding insight: the channel through which a message travels is not a neutral pipe but an active force that alters what is communicated.

Agent affinity: mcluhan (media ecology, the medium is the message, technological determinism), tannen (linguistic analysis of media messages), aristotle-c (rhetorical analysis of media persuasion)

Concept IDs: comm-digital-communication, comm-intercultural-communication, comm-audience-adaptation, comm-register-formality

Media Ecology (McLuhan, 1964)

The Medium Is the Message

McLuhan's central claim is that the significant thing about any medium is not the content it carries but the ways it changes human perception, social organization, and cognition. Television did not merely deliver programs into living rooms -- it reorganized family life, created a shared national experience, and trained people to think in images rather than text. The internet did not merely give people access to information -- it restructured attention, eroded the distinction between producer and consumer, and made geographic community optional.

Implications for media literacy:

  • You cannot understand a media message by analyzing only its content. You must also analyze the medium.
  • When a new medium appears, the important question is not "What will people do with it?" but "What will it do to people?"
  • Every medium amplifies some human capacities and amputates others. Print amplified linear reasoning and individual thought; it amputated oral memory and communal storytelling.

Hot and Cool Media

McLuhan classified media along a spectrum:

Hot mediaCool media
High definition -- filled with dataLow definition -- leaves gaps for the audience to fill
Low participation requiredHigh participation required
Examples: print, radio, film, lectureExamples: telephone, television, seminar, social media

This classification is debatable (McLuhan himself revised it), but the underlying principle is robust: media that demand more audience participation create different cognitive and social effects than media that deliver a complete experience.

The Tetrad of Media Effects

For any medium, ask four questions:

  1. What does it enhance? (What human capacity does it amplify?)
  2. What does it obsolesce? (What does it push aside or make unnecessary?)
  3. What does it retrieve? (What previously obsolesced form does it bring back?)
  4. What does it reverse into? (When pushed to its limit, what does it become?)

Example -- Smartphone:

  1. Enhances: instant access to information and people
  2. Obsolesces: landlines, maps, alarm clocks, cameras as separate devices
  3. Retrieves: the nomadic lifestyle (you can work from anywhere)
  4. Reverses into: isolation (constant connectivity produces loneliness)

Encoding/Decoding (Hall, 1973)

Stuart Hall's model challenged the assumption that audiences passively receive media messages. Instead, Hall argued that media producers encode meaning into messages, and audiences decode them -- but the decoding does not necessarily match the encoding.

Three Decoding Positions

PositionDescriptionExample
Dominant/HegemonicThe audience decodes the message exactly as the producer intendedWatching a luxury car ad and wanting the car
NegotiatedThe audience accepts the general framework but modifies it based on their own experienceAccepting that luxury cars are desirable but noting the ad ignores climate impact
OppositionalThe audience understands the intended meaning but rejects it entirelyReading the ad as a symbol of inequality and consumerism

Implications for media literacy: Every media message has an intended meaning, but audiences are not obligated to accept it. Critical media literacy means being aware of the encoding and choosing your decoding position deliberately rather than defaultly.

News Literacy

Source Evaluation

The SIFT method (Caulfield, 2019):

  1. Stop. Before you react or share, pause. Do you know the source?
  2. Investigate the source. Who published this? What is their track record? What do others say about them?
  3. Find better coverage. If the claim is true, reputable outlets will also cover it. Look laterally, not just at the original source.
  4. Trace claims. Follow citations to their origin. Is the original source saying what this article claims?

Information Quality Spectrum

CategoryDescriptionExample
Verified journalismOriginal reporting, fact-checked, corrections publishedAssociated Press, Reuters, major newspapers' news sections
Analysis/opinionInterpretation based on facts, clearly labeledEditorial pages, opinion columns, policy analysis
AdvocacyArgues for a position using selective evidenceNGO reports, industry white papers, political communications
PropagandaDeliberately manipulates to serve a political or commercial agendaState media under authoritarian regimes, astroturfing
MisinformationFalse but not intentionally soHonest errors, outdated information, misunderstood statistics
DisinformationDeliberately false, designed to deceiveFabricated stories, manipulated images, coordinated inauthentic behavior

Propaganda Analysis

The Institute for Propaganda Analysis (1937) identified seven techniques that remain relevant:

TechniqueHow it worksModern example
Name callingAttach a negative label to dismiss"That policy is socialist" (used as epithet regardless of accuracy)
Glittering generalitiesAttach a virtue word to bypass analysis"Freedom," "innovation," "patriotism" used without specific content
TransferAssociate with something respected or reviledPolitician speaks in front of a flag or a factory
TestimonialEndorsed by a respected (or feared) figureCelebrity endorsement of a product or policy
Plain folks"I'm just like you" to build false identificationBillionaire in a pickup truck eating at a diner
Card stackingPresent only favorable evidenceCherry-picked statistics, cropped quotes
BandwagonEveryone's doing it, so should you"Join the millions who already..."

Algorithmic Curation

Modern media literacy must account for the fact that most people's media diet is curated by algorithms they do not control and often do not understand.

Key concepts:

  • Filter bubble (Pariser, 2011): Personalization algorithms show you content that matches your existing preferences, creating an information environment where you rarely encounter opposing views.
  • Engagement optimization: Platforms optimize for time-on-platform, not truth or well-being. Outrage, fear, and novelty drive engagement. The algorithm's incentive is to radicalize, not inform.
  • Algorithmic amplification: Content that generates strong reactions spreads faster, regardless of accuracy. Misinformation can outrun corrections because it is more emotionally engaging.

Media literacy response:

  • Actively seek sources outside your filter bubble
  • Follow the claim, not the algorithm
  • Recognize when your emotional reaction is the product, not a side effect

Cross-References

  • mcluhan agent: Deep analysis of how media technologies shape communication, perception, and social organization. The primary agent for media ecology questions.
  • tannen agent: Linguistic analysis of how media messages are constructed and how different audiences interpret them.
  • aristotle-c agent: Rhetorical analysis applied to media messages -- ethos, pathos, logos in advertising, news, and political communication.
  • freire agent: Critical media literacy as a liberatory practice -- understanding media as a site of power.
  • persuasion-rhetoric skill: Persuasive techniques as they appear in media messages.
  • public-speaking skill: Media appearances require adapted public speaking skills.

References

  • McLuhan, M. (1964). Understanding Media: The Extensions of Man. McGraw-Hill.
  • Hall, S. (1973). "Encoding and Decoding in the Television Discourse." Stencilled Occasional Paper 7. Centre for Contemporary Cultural Studies, University of Birmingham.
  • Postman, N. (1985). Amusing Ourselves to Death: Public Discourse in the Age of Show Business. Viking.
  • Caulfield, M. (2019). "SIFT (The Four Moves)." Hapgood. https://hapgood.us/2019/06/19/sift-the-four-moves/
  • Pariser, E. (2011). The Filter Bubble: What the Internet Is Hiding from You. Penguin.
  • Institute for Propaganda Analysis. (1937). "How to Detect Propaganda." Propaganda Analysis, 1(2).

Frequently asked questions

What does the Media Literacy AI skill do?

Media literacy and critical analysis of media messages across platforms and formats. Covers media ecology (McLuhan), encoding/decoding (Hall), news literacy, digital media analysis, propaganda techniques, algorithmic curation, visual rhetoric, and ethical media consumption. Use when analyzing media messages, evaluating news sources, understanding how media technology shapes communication, detecting propaganda, or studying the relationship between medium and message.

Why use Media Literacy on TypingMind?

Because you install it once and use it with any model. Media Literacy is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Media Literacy in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Tibsfox/gsd-skill-creator/tree/main/examples/skills/communication/media-literacy. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Media Literacy?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Media Literacy?

As many as you like. As long as a model supports skills, you can use Media Literacy with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Media Literacy AI skill free?

It is published on GitHub by Tibsfox. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇