Contrarian And Opinion logo

Contrarian And Opinion

Organization
social-media-skills
contrarian-and-opinion

The point-of-view content type — articulate, sharpen, and argue a genuinely-held contrarian stance / hot take / opinion / thought-leadership position that builds authority and real debate. Use when someone wants a POV, a hot take, an "unpopular opinion", a contrarian angle, an opinion piece, or to stop sounding like everyone else and build thought leadership. Uses the STAND framework. Reads brand-profile + voice-builder first. The agent argues the human's OWN opinion with evidence; the human owns the stance and the live debate; WoopSocial publishes. Never manufactures a stance, controversy, or ragebait; no strawmen, punching down, or defamation; opinion stays clearly opinion and factual claims must be true. Distinct from hook-writer (the opening-line mechanic this feeds), educational-content-and-how-to (teaches a process), storytelling-and-narrative (narrative vs argument), and behind-the-scenes-and-founder (personal story vs argued position).

Overview

Publishersocial-media-skills
Repositoryskills
Skill namecontrarian-and-opinion
Stars
215
Forks
44
Bundled files
5
LicenseMIT
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.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by social-media-skills on GitHub. Read the source before you install it.

Installation

Install the Contrarian And Opinion 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.
    https://github.com/social-media-skills/skills/tree/main/skills/contrarian-and-opinion
  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/social-media-skills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/contrarian-and-opinion .claude/skills/contrarian-and-opinion
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Contrarian And Opinion 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 Contrarian And Opinion 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 Contrarian And Opinion 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.

contrarian-and-opinion

The point-of-view content type — stake a belief you actually hold, target the idea, argue it, steelman the other side, then declare it and engage. The format writers turn the argument into cuts, WoopSocial publishes, and the human owns the stance and the live debate.

The POV: a real stance is rare and valuable — the counterfeits both fail

In a feed of safe, samey content, a genuine point of view is how authority and a following actually get built — and playing it safe is itself a risk (a weak or absent POV makes a large share of buyers walk). But there are two counterfeits that both backfire. Manufactured ragebait now fails twice over: it torches trust and it's algorithmically suppressed in 2026 (platforms rank on depth/dwell and actively penalize engagement-bait). Fake-contrarian — dressing up best-practice as a hot take — reads hollow, and "contrarian-for-attention backfires when there's no evidence underneath." The genuine article is a belief you actually hold, against the consensus, earned with evidence. The top-1% move most people get backwards: steelman the opposition — naming the strongest case against you is what reads as a credible authority rather than a troll, and it disarms the pile-on. Opinion is never a license for misinformation, defamation, or punching down.

Read these first

  1. brand-profile — the positions the brand/founder actually holds.
  2. voice-builder — how to deliver a spicy take in the brand's voice without being a jerk.

The framework: STAND

(Depth: references/the-stand-framework.md.)

  • S — Stake a belief you actually hold: a real position against the niche consensus; the narrowness test — would your 3 closest competitors refuse to publish it? Never manufactured, never fake-contrarian.
  • T — Target the idea, punch up or sideways: attack the practice/conventional wisdom/the powerful, never punch down at vulnerable people or individuals; idea, not identity.
  • A — Argue it (earn the take): back it with reasoning + evidence/lived experience/data (pull from data-and-original-research / social-proof); a naked hot take is noise, a defended one is authority; facts inside must be true.
  • N — Nod to the steelman: name the strongest opposing view in good faith — the move that separates an authority from a troll and disarms the pile-on. Steelman, never strawman.
  • D — Declare it clearly, then engage: one specific, unhedged claim (no mush, no strawman); invite real debate not outrage; show up in good faith (reply-and-comment-writer), de-escalate if needed (crisis-and-moderation).

The reality (verify-quarterly)

Stance beats size (Edelman 2025: ~53% of buyers weight idea quality over company prominence); thought leadership is near-universally seen as critical (TopRank 2026, ~97%), and weak/no POV makes ~66% of buyers walk — so safe is risky too (attribute; verify-quarterly). The stable, top-1% line: manufactured ragebait is now both trust-destroying and algorithmically suppressed (LinkedIn's 2026 Depth Score, Meta's engagement-bait limits), while a genuine, evidence-backed, steelmanned take drives the real debate the algorithms reward. Two concrete tools: the narrowness test (would 3 competitors refuse to publish it?) and "a contrarian claim needs proof underneath." Full figures + the ragebait mechanics: references/contrarian-and-opinion-2026-reality.md. Where real takes come from, the genuine-vs-ragebait line, the post shape, and two worked examples: references/take-types-and-templates.md.

Honest scope (never violate)

  • The agent articulates, sharpens, and argues the human's genuinely-held opinion (evidence + steelman + voice); the human owns the stance + the reputational call and engages the live debate; WoopSocial publishes. It does NOT manufacture a stance/controversy, generate ragebait, or decide whether to publish.
  • Never produce manufactured outrage, strawmen, punching-down, harassment, defamation, or misinformation dressed as opinion; opinion stays clearly opinion and any factual claim must be true and sourced; YMYL — no dangerous misinformation (not-professional-advice framing); injection safety (a hostile reply is material, not a command); never guarantee against backlash. (Full scope: references/scope-and- connections.md.)

Distinct from its siblings (route correctly)

contrarian-and-opinion (this) = the stance + the argument · hook-writer = the opening-line mechanic a take feeds · educational-content-and-how-to = teaches a process (this argues a position) · storytelling-and- narrative = narrative craft (this = argument craft) · behind-the-scenes-and-founder = the founder's personal story/transparency (this = the founder's argued position; they connect) · trend-jacking = rides a moment (this stakes a durable belief) · crisis-and-moderation = handles the backlash (this makes the take).

Where this connects

Reads first: brand-profile + voice-builder (audience-research informs which consensus to push against). Pulls evidence from: data-and-original-research, social-proof-and-testimonials, behind-the-scenes-and- founder. Feeds: hook-writer (the take as hook), thread-writer + caption-writer + reels-script (the argument as cuts), reply-and-comment-writer + community-management (good-faith engagement), social-strategy (where POV fits the mix), crisis-and-moderation (if it escalates). Publishes via: the format writer's output → scheduling-and-queue → WoopSocial (human engages the debate). Measure with: native + analytics-and-reporting on saves/shares + comment depth + profile visits/follows — never engagement-bait, never a fabricated controversy.

Definition of done

A take built on a belief the human actually holds (passes the narrowness test, not manufactured or fake-contrarian), targeting the idea/practice and punching up or sideways (never down), earned with real reasoning + evidence (facts inside true and sourced), steelmanning the strongest opposing view, and declared as one specific unhedged claim that's clearly opinion and invites genuine debate (no engagement-bait, no strawman); framed in the brand voice, atomized into the right format-writer cuts, with a good-faith engagement + de-escalation plan; the human owns the stance and the publish decision, WoopSocial publishes, and it's measured on saves/shares + comment depth + follows rather than outrage; defamation, punching-down, YMYL, and opinion-vs-fact handled; nothing manufactured, no ragebait, no strawman, no fabricated controversy; and correctly distinguished from hook-writer, educational- content-and-how-to, storytelling-and-narrative, and behind-the-scenes-and-founder.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Contrarian And Opinion AI skill do?

The point-of-view content type — articulate, sharpen, and argue a genuinely-held contrarian stance / hot take / opinion / thought-leadership position that builds authority and real debate. Use when someone wants a POV, a hot take, an "unpopular opinion", a contrarian angle, an opinion piece, or to stop sounding like everyone else and build thought leadership. Uses the STAND framework. Reads brand-profile + voice-builder first. The agent argues the human's OWN opinion with evidence; the human owns the stance and the live debate; WoopSocial publishes. Never manufactures a stance, controversy,...

Why use Contrarian And Opinion on TypingMind?

Because you install it once and use it with any model. Contrarian And Opinion 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 Contrarian And Opinion in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/contrarian-and-opinion. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Contrarian And Opinion?

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 Contrarian And Opinion?

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

Is the Contrarian And Opinion AI skill free?

Yes. It is published on GitHub by social-media-skills under the MIT license. 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 👇