A daily pipeline that finds AI and technology topics across YouTube, X/Twitter, TikTok, and Anthropic’s changelogs, then stores and reviews them.

It helps build a content backlog, rank ideas by recency and engagement, collect video transcripts, and create a dated review file.

It removes the need to search several platforms manually and helps avoid duplicate ideas.

How robinsadeghpour/content-workflow configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to robinsadeghpour/content-workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/robinsadeghpour/content-workflow/main/.claude/skills/pulse/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/robinsadeghpour/content-workflow

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/robinsadeghpour/content-workflow/pulse/github.svg)](https://agentmods.dev/skills/robinsadeghpour/content-workflow/pulse)

Your own site

<a href="https://agentmods.dev/skills/robinsadeghpour/content-workflow/pulse"><img src="https://agentmods.dev/badge/skills/robinsadeghpour/content-workflow/pulse/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/robinsadeghpour/content-workflow/pulse"><img src="https://agentmods.dev/badge/skills/robinsadeghpour/content-workflow/pulse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,255 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.00114	$0.01255
Opus 5.5	$0.00046	$0.00502
Sonnet 5.5	$0.00023	$0.00251
Haiku 4.5	$0.00011	$0.00126

Measured 2mo ago against content hash 62d894152d55, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pulse scanned grade A with 0 findings 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 2mo ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/pulse/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pulse -- Content Discovery Pipeline

Automated daily discovery that keeps Robin's content backlog stocked with trending AI/tech ideas -- no manual searching required.

Prerequisites

Ensure .env contains:

APIFY_TOKEN -- required for TikTok and X scrapers
SUPADATA_API_KEY -- required for transcript extraction
ANTHROPIC_API_KEY -- required for content generation phases (not used by pulse itself)

Running the Pulse

Step 1: Ensure DB is initialized with transcript column

node scripts/init-db.js

Step 2: Run the full pulse

node scripts/pulse.js

This will:

Scrape YouTube (via yt-search), TikTok (via Apify clockworks/tiktok-scraper), X/Twitter (via Apify apidojo/tweet-scraper), and Anthropic changelogs (via Cheerio)
Score each idea by recency + engagement (no Claude API calls -- pure numeric formula)
Deduplicate against existing data/content.db entries using SHA-256 URL hashes
Eagerly fetch transcripts for all YouTube and TikTok ideas via Supadata
Insert new ideas into data/content.db (ideas table, status='new')
Generate a dated markdown review file at data/review/YYYY-MM-DD.md

Source failures are logged and skipped -- the pulse continues even if one source is down.

Step 3: Read and display the review file

After the pulse completes, read the review file to present a summary:

cat data/review/$(date +%Y-%m-%d).md

Present the top ideas from the review file to Robin with their scores, sources, and content angle suggestions.

Expected Output

[PULSE] 2026-04-09T06:00:00.000Z -- pulse started
[PULSE] youtube: 12 ideas found
[PULSE] tiktok: 8 ideas found
[PULSE] x: 15 ideas found
[PULSE] changelog: 3 ideas found
[PULSE] 18 new ideas (20 duplicates filtered)
[TRANSCRIPT] Fetching transcripts for 10 video ideas...
[TRANSCRIPT] 8/10 transcripts fetched
[PULSE] Inserted 18 ideas into data/content.db
[REVIEW] Review file written: data/review/2026-04-09.md
[PULSE] Done. 18 ideas written to DB. Review file generated.

Read the full file on GitHub · 153 lines

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.

2mo ago First seen · 153 lines · 114 tokens per session scan A 62d894152d55

Subscribe to this mod's changes

pulse is a skill published in the GitHub repository robinsadeghpour/content-workflow (54 stars, last pushed 6mo ago), licensed MIT. It adds 114 tokens to every session and 1,255 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Marketing and SEO Research

pulse next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pulserobinsadeghpour/content-workflow	Skill	54	6mo ago	MIT	A	114	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex

content-workflow: Skill for Claude Code