Install
$ agentstack add skill-social-media-skills-skills-contrarian-and-opinion ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
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
- brand-profile — the positions the brand/founder actually holds.
- 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.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: social-media-skills
- Source: social-media-skills/skills
- License: MIT
- Homepage: https://social-media-skills.com
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.