What is content-cascade?

A tool that turns a YouTube video into a blog post, a Twitter/X thread, and a LinkedIn post. It reads the video's transcript and follows the creator's saved writing guidelines.

Use it to fetch a transcript, create the three written formats, and optionally save them as drafts in Supabase, a hosted database service.

It avoids rewriting the same video separately for several publishing platforms and helps keep the output aligned with the creator's usual voice.

content-cascade — Skill by AI-Answer

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/ai-answer/contentrepurposesystem/content-cascade

Any agent

npx skills add AI-Answer/ContentRepurposeSystem --skill content-cascade

Clone the repo

git clone --depth 1 https://github.com/AI-Answer/ContentRepurposeSystem

Made for: Claude Code, Codex.

Or install content-repurpose-system, the plugin that ships this one along with the rest of its 7 skills.

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,787 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00100	$0.03787
Opus 5	$0.00050	$0.01894
Sonnet 5	$0.00020	$0.00757
Haiku 4.5	$0.00010	$0.00379

Measured 3d ago against content hash ec5b49d68f6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content-cascade scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/fetch-transcript-apify.js, scripts/fetch-transcript.js, scripts/generate-flyer-hook.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s "YOUR_SUPABASE_URL/rest/v1/posts?youtube_video_id=eq.VIDEO_ID_HERE&select=id" \

skills/content-cascade/SKILL.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Cascade

Turn a YouTube video into a full content cascade: blog post + Twitter thread + LinkedIn post. Fetches the transcript, generates all three pieces following your voice guidelines, and optionally saves everything as drafts to Supabase.

Setup Required

Run /onboard first. It configures everything below in one pass (channel, Voice DNA, optional keys). If onboarding hasn't been run yet and no channel is configured, suggest running /onboard before proceeding. The items below are what onboarding sets up — only do them manually if the user is configuring by hand:

Voice prompts — Your blog/social voice guidelines live in ${CLAUDE_PLUGIN_ROOT}/skills/content-cascade/prompts/. /onboard writes a Voice DNA block into each; otherwise edit the template files directly.
YouTube channel — YOUR_CHANNEL_ID below is replaced with your real channel ID by /onboard.
Supabase (optional) — If you want auto-saving to a database, set up your Supabase project and update the config section at the bottom.
Apify (optional) — For reliable transcript fetching, get a free API token at https://apify.com and set APIFY_API_TOKEN env var.
Twitter/X (optional) — For auto-posting threads, set Twitter API credentials in ${CLAUDE_PLUGIN_ROOT}/skills/content-cascade/.env.

When This Skill Activates

Activate when the user wants to:

Generate blog/social content from a YouTube video
Create a content cascade from a video they just published
Write a blog post, Twitter thread, or LinkedIn post from a video transcript
Run the content pipeline for a new video

Example triggers:

"Run the content cascade on my latest video"
"Content cascade for my latest video"
"Generate content for https://youtube.com/watch?v=XYZ"
"Create blog + twitter + linkedin for [URL]"
/content-cascade
/content-cascade [URL]

Pipeline Steps

Step 1 — Get the Video

If the user provided a YouTube URL, use it.

If the user said "latest video" or didn't provide a URL, auto-detect the most recent upload:

Read the full file on GitHub · 316 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago First seen · 316 lines · 100 tokens per session scan A ec5b49d68f6e

Subscribe to this mod's changes

content-cascade is a skill published in the GitHub repository AI-Answer/ContentRepurposeSystem (12 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 3,787 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Marketing and SEO Writing and docs claude-code claude-plugin content-repurposing creator-tools short-form skills

feature-state-keeper

Use when starting, advancing, finishing, or blocking a feature. Manages featurelist.json + progress.md + session-handoff.md. Default-FAIL enforced.

Redtropig/harness-anchor · 37 tokens

anti-hallucination-gates

Use before claiming done/fixed/passing — or before asserting something is absent: not installed, not available, no such function, couldn't find it. Default-FAIL runs both ways — every claim needs an evidence path. A negative claim must carry its search scope and observation date; state calibrated uncertainty when…

Redtropig/harness-anchor · 72 tokens

cpp-static-analysis

Use in C/C++ projects when reviewing changes or hunting bugs. Runs clang-tidy/cppcheck/IWYU. Needs compilecommands.json. Changed lines only.

Redtropig/harness-anchor · 37 tokens

capturing-golden-rules

Use when the same mistake or bad pattern recurs, when a code-review comment is really a convention worth enforcing, or when you catch AI-generated drift/slop and want it to never happen again. Encodes the lesson as a durable rule in golden-rules.md — the feedback-flywheel / harness-layer-learning ratchet — instead of…

Redtropig/harness-anchor · 87 tokens

cpp-sanitizers

Use in C/C++ projects for crashes, hangs, UB, data races, memory errors. ASan/UBSan/TSan runtime checks. Build sanitizer config separately.

Redtropig/harness-anchor · 40 tokens

docs-lookup

Use when looking up unfamiliar tools, APIs, errors, library behavior. Context7 → WebSearch → calibrated uncertainty fallback chain. Don't guess.

Redtropig/harness-anchor · 32 tokens

content-cascade