Consensus

Find out what YouTube actually agrees on about a topic, and what it has quietly stopped saying. Searches YouTube for a topic, pulls ~100 transcripts across both the top-ranking and the most recent videos, extracts every specific claim, clusters claims that say the same thing, then weights them by age to separate settled advice from current advice from expired advice. Produces a self-contained HTML report where every position is traceable to a timestamped source. Use when the user types /consensus, or asks what the consensus is on a topic, what most people/creators say about something, whether

8 stars 2 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add GoodLadTom/consensus --skill consensus

Manual install

git clone --depth 1 https://github.com/GoodLadTom/consensus.git /tmp/consensus
mkdir -p ~/.claude/skills
cp -r /tmp/consensus/. ~/.claude/skills/consensus

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# consensus

**v0.2.0**

Give it a topic. It reads about a hundred YouTube videos on that topic and
tells you what the field agrees on — separating advice that has held up from
advice that has quietly died.

The output answers one question: **when you strip out the outliers, what does
YouTube actually agree on about this, and what has it stopped saying?**

## Why the age split is the whole point

Any tool can summarise videos. The reason this one gathers old videos as well
as recent ones is that you cannot notice advice has died if you only ever
looked at current videos. On a topic like YouTube growth, 2022 advice is often
actively wrong — the platform changed underneath it. Reporting a consensus
that averages 2022 and 2026 together produces confident nonsense.

So every position lands in one of these:

| Status | Means |
|---|---|
| **Settled** | Backed in both older and recent videos. Has survived a changing field. |
| **Expired** | Well backed in older videos, absent from recent ones by more than chance explains. Dead advice. |
| **Current** | Backed recently, absent from older videos. Something changed. |
| **Emerging / Fading** | Leaning one way, but not enough backing to separate from chance. No claim made. |
| **Thin** | Too few independent channels to call. |

`expired` and `current` are assertions about *absence*, so they are tested
rather than eyeballed — see `scripts/analyse.py`. Where an absence could

Read the full skill on GitHub

Details

Skill name: consensus
Repository: GoodLadTom/consensus
License: MIT
Repo updated: 9 September 2026

FAQ

What does the Consensus skill do?

How do I install the Consensus skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add GoodLadTom/consensus --skill consensus. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Consensus popular?

It lives in GoodLadTom/consensus, which has 8 GitHub stars and 2 forks.

Related skills

Framecraft

vaddisrinivas/framecraft

Create polished demo videos from screenshots and scene descriptions. Think like a video producer — story arc, pacing, emotion, visual hierarchy. Orchestrates playwright, ffmpeg, and edge-tts MCPs or falls back to an atomic pipeline.

Images, Video & Audio

Vsdx Trace

ZJUZhiyuCai/vsdx-trace

Reconstruct raster references as high-fidelity, independently editable Microsoft Visio VSDX files. Use when a user asks to 复刻、临摹、重绘 a screenshot, paper figure, flowchart, system diagram, or model architecture as editable Visio, especially when iterative visual matching matters. Do not use for ordinary image generation or flat image embedding.

Images, Video & Audio

Riffkit

riffkit/skill

Riff winning short videos — give one source (a TikTok link, an uploaded video, or an analyzed template) and the backend riffs its emotion formula into your own AI video (post-ready short-form or UGC-style ad creative), with optional digital character, product placement, and language. You riff the formula, not the video.

Images, Video & Audio

Notebook Video

hyt315/notebook-video

Turn a topic into a Chinese 16:9 teaching video (flat / cel component themes, or the journal / papercut / archive hand-made skins driven by a metaphor-first director layer) with React, TypeScript and Remotion. Every shot is a code-drawn component scene — consoles, diffs, checklists, stat rows, funnels, progress rings, kinetic numbers, stamp seals, verdict bars, or a real screenshot / screen recording in a MediaFrame — moved by an engine-level virtual camera that pushes in on whatever the narration names. Weak-model friendly: five teaching blueprints with per-shot component picks, golden exampl

Images, Video & Audio

Video to Skill

brenoepics/video-to-skill

Convert a video (local file or YouTube/URL) into structured, evidence-grounded knowledge — and ultimately into an installable agent skill. Use when the user provides a video file or video URL and wants it analyzed, summarized into steps, or turned into a skill; triggers include "watch this video", "learn from this tutorial", "video to skill", or a path/URL to .mp4/.mkv/.webm/.mov or youtube.com/youtu.be.

Images, Video & Audio

3d Brain Animations

SamedVossberg/3d-brain-animations

Render 3D still images and rotating turntable animations of brain regions from ANY BrainGlobe atlas (mouse, rat, human, zebrafish, etc.), with optional glow/bloom highlighting and a semi-transparent whole-brain shell for context. Use this WHENEVER the user wants to visualize, render, picture, or animate brain anatomy: any species, any region (hippocampus, CA1, dentate gyrus, cortex, thalamus, amygdala, ...), any color, a glowing/highlighted region, a rotating brain video, or a neuroanatomy figure for a paper/thesis/slide — even if they don't mention Blender or BrainGlobe. Handles requests like

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.