en

New ideaFintech

Hosted "day-trader skills" desk

A web app that runs the open-source day-trader skills for you — scan charts, track news, time entries and replay outcomes before you risk a dollar — no terminal needed.

2 weeks ago · Scored 26 Oct 2026 · ID HBV-261026-02

Working title: Hosted "day-trader skills" desk: chart scanning, news, entry/exit timing and replay for retail day traders without Claude Code (working name "Replay Desk")

Summary

BriefingVerifiedHypothesis

Benchmark: Jakeschincariol/day-trader-skill — Total: 1.8k (github.com page text, read 26 Oct 2026 07:06 BRT; page shows no exact count); API 1,816 (OSS Insight/gh meta 06:57 BRT) and 1,824 (second gh read) — live growth. Created 2026-10-20 (gh API cross-check only; not visible on the repo page), MIT (browser).…

Read the rest

24h (last full UTC day, 25 Oct): +519 stars. 7d (19–25 Oct): +1,674 = 239/day over 7 days (repo is 6 days old, so ≈279/day over its real life). Since creation: ~1.8k in 6 days ≈ 303/day. Acceleration: 7v7 n/a (repo younger than 7 days; prior 7 days = 0, not computable); 3v3 (23–25 Oct 1,136 vs 20–22 Oct 538) = +111% (accelerating); peak day 25 Oct (+519, the last full day) → not past peak. Daily series: 20 Oct 37 · 21 Oct 216 · 22 Oct 285 · 23 Oct 347 · 24 Oct 270 · 25 Oct 519 · 26 Oct partial 223 (OSS Insight analyze-recent-stars, fetched 26 Oct 06:57 BRT). Not on github.com/trending daily, weekly, python weekly or typescript weekly at 07:06 BRT (weekly #5 cutoff ≈2,790 stars/week). All star numbers Verified (browser total; API/OSS Insight series). Existence check: No maintainer-hosted version (maintainer site opusjake.ai offers a PDF only); web search found only directory listings (conduits.dev, skills.sh, skillsllm) and 0 hosted wrappers (Verified by search, 26 Oct; Hypothesis that none exist unseen). Free TradingView screeners overlap part of the job (scanning), not the replay/timing workflow. the pain query "day trading + AI" has 434 posts/7d and fell −55% 3v3 (weekend market closure on 24–25 Oct is the likely cause — Hypothesis). Stars: Total: 1.8k (github.com page text, read 26 Oct 2026 07:06 BRT; page shows no exact count); API 1,816 (OSS Insight/gh meta 06:57 BRT) and 1,824 (second gh read) — live growth. Created 2026-10-20 (gh API cross-check only; not visible on the repo page), MIT (browser). 24h (last full UTC day, 25 Oct): +519 stars. 7d (19–25 Oct): +1,674 = 239/day over 7 days (repo is 6 days old, so ≈279/day over its real life). Since creation: ~1.8k in 6 days ≈ 303/day. Acceleration: 7v7 n/a (repo younger than 7 days; prior 7 days = 0, not computable); 3v3 (23–25 Oct 1,136 vs 20–22 Oct 538) = +111% (accelerating); peak day 25 Oct (+519, the last full day) → not past peak. Daily series: 20 Oct 37 · 21 Oct 216 · 22 Oct 285 · 23 Oct 347 · 24 Oct 270 · 25 Oct 519 · 26 Oct partial 223 (OSS Insight analyze-recent-stars, fetched 26 Oct 06:57 BRT). Not on github.com/trending daily, weekly, python weekly or typescript weekly at 07:06 BRT (weekly #5 cutoff ≈2,790 stars/week). All star numbers Verified (browser total; API/OSS Insight series). X: 28 posts/7d (Rising (16 of 28 posts on 25 Oct; daily split not pulled); window 2026-10-19 10:30 UTC → 2026-10-26 09:50 UTC (X API recent counts, granularity day, pulled 26 Oct 2026 ~06:55–07:15 BRT; Sun 19 and Mon 26 are partial UTC days; full days Mon 20 → Sun 25; 3v3 = (23+24+25) vs (20+21+22))). Revenue hypothesis: ~$3K–$20K/month at month 6 (HYPOTHESIS).

DescriptionHypothesis

A web app that runs the open-source day-trader skills for you — scan charts, track news, time entries and replay outcomes before you risk a dollar — no terminal needed. Who: Retail day traders and swing traders (US first, then Brazil/LatAm) who want AI chart scanning and news timing but will not install Claude Code skills.…

Read the rest

Pain: The 11 skills that 1.8k GitHub users starred in 6 days need a terminal, Claude Code and API keys; non-developer traders cannot use them, and existing screeners do not replay outcomes before risking money. Monetization: Subscription (prosumer) with usage caps on scans/replays; optional broker affiliate links (Hypothesis). Build: ~3–5 agent-weeks (hosted skill runner, delayed/free market data, news feed, replay UI, Stripe); stack: Next.js on Vercel; Claude API running the MIT skills; free/delayed market data (Yahoo, Alpaca free tier) or user's own broker keys; Stripe. GTM: SEO/GEO pages per setup ("replay a day-trade setup"), shareable replay cards (PLG loop), faceless X/TikTok clips of replays.

Target customer

Retail day traders and swing traders (US first, then Brazil/LatAm) who want AI chart scanning and news timing but will not install Claude Code skills.

Pain

The 11 skills that 1.8k GitHub users starred in 6 days need a terminal, Claude Code and API keys; non-developer traders cannot use them, and existing screeners do not replay outcomes before risking money.

Why this score

Why it scored lower: Financial-advice/regulatory exposure and market-data licensing cost; the MIT code lets anyone host the same thing.

MoatHypothesis

Weak (MIT code) — speed and distribution: First hosted version of a fast-rising skill pack; replay cards create a sharing loop. Saved replays, user setups history and SEO pages per setup. Status: Hypothesis.

Demand signals

X posts (7 days)

28

Signal trend

Rising (16 of 28 posts on 25 Oct; daily split not pulled)

Web demandVerified

Repo mentions on X 28/7d, rising (16 on 25 Oct, Verified). Sister repo Jakeschincariol/trader-skill (same author) 650 stars in 12 days (browser), but decelerating 3v3 −24%, peak 21 Oct (OSS Insight). Weekly trending top 5 (07:06 BRT): cloudflare/security-audit-skill 15,072/wk, stablyai/orca 9,622, anomalyco/opencode 5,921, ruvnet/ruflo 2,987, anthropics/knowledge-work-plugins 2,790 — day-trader-skill not listed.…

Read the rest

Other X counts (same window, Verified X API): 434 posts (Falling -55% 3v3 (23–25 Oct 108 vs 20–22 Oct 239; daily full UTC days 73, 81, 85, 61, 28, 19); peak 22 Oct 85; 25 Oct is 78% below peak — ≥50% below peak: POP 5.3 window-closed signal): ("day trading" OR daytrading) (AI OR Claude OR ChatGPT) -is:retweet

Market and competitors

TAM

Not sized this run — Scope: Global. Method: No third-party report fetched. (Basis: n/a)

SAMHypothesis

Not sized — Scope: Target markets above. Method: HBV assumption. (Basis: Hypothesis)

SOMHypothesis

~$36K–$240K ARR (Hypothesis) — Scope: Month-6 run-rate. Method: From revenue hypothesis ×12. (Basis: Hypothesis)

Competitors

TradingView (screeners, alerts), Trade Ideas, Benzinga Pro (news), TrendSpider, Finviz; ChatGPT/Claude used directly with screenshots; free directories listing the skills.

Business model

MonetizationHypothesis

Subscription (prosumer) with usage caps on scans/replays; optional broker affiliate links (Hypothesis).

Revenue hypothesis (monthly)Hypothesis

~$3K–$20K/month at month 6 (HYPOTHESIS).

Jobs to be done

When I prepare for the market open, I want to scan charts, catch the news and replay how a setup played out, so I can enter fewer bad trades without learning to code.

HXC

Mike, 34, part-time day trader in Phoenix (illustrative) · Trades the first hour before work; pays for a screener. Buying signal: Saw the repo on X but has never used a terminal.

Build and go-to-market

Tech stack

Next.js on Vercel; Claude API running the MIT skills; free/delayed market data (Yahoo, Alpaca free tier) or user's own broker keys; Stripe

GTM channels

SEO/GEO pages per setup ("replay a day-trade setup"), shareable replay cards (PLG loop), faceless X/TikTok clips of replays

Risks

Main risk

Financial-advice/regulatory exposure and market-data licensing cost; the MIT code lets anyone host the same thing.

All risksVerified

Value: Supported — 1.8k stars, 3v3 +111%, peak 25 Oct (Verified) | Usability: Attention — Traders may not trust AI timing | Feasibility: Attention — Market-data cost/licensing | Business Viability: High — Investment-advice rules; MIT copies

Next validation step

Cesar decides which wrapper rule applies; if GO, re-read stars on github.com on 27 Oct and check the 7v7 window on 27–28 Oct (first full prior week).

Sources

  1. github.com (browser 26 Oct 07:06 BRT)
  2. github.com
  3. OSS Insight analyze-recent-stars (06:57 BRT)
  4. gh API repo meta
  5. github.com/trending (daily, weekly, python weekly, typescript weekly, 07:06 BRT)
  6. web search (conduits.dev, skills.sh, skillsllm, opusjake.ai)
  7. X API counts (window above)

ideagithub-wrapperfintechtradingai-agentsprosumerglobalusbrazillatam

Want the next one the day it is scored?

The score, the sources, the risks and the next step, by email.

Free. Sent with beehiiv. One click to unsubscribe.

  • New ideaFintech· 2 weeks ago

    Open-source "trader skills" pack

    Free PT/ES skill pack that lets Claude or Codex scan B3 and BMV charts, read CVM filings and local news, and replay setups — the day-trader-skill pattern for LatAm.

    Why it scored lower: Small, noisy LatAm demand signal and Hypothesis-only monetization; CVM rules on recommendations.

    Open ProductBots.ai →

  • New ideaFintech· 1 week ago

    Agent-native checkout

    Drop-in agent checkout and prepaid credits wallet for solo SaaS: MCP tool + embed so coding agents can buy credits or unlock features; merchant dashboard with card and LatAm PIX.

    Why it scored lower: Incumbent rails ship the same wedge; regulated payments support load.

    Open ProductBots.ai →

  • Existing businessFintech· 3 weeks ago

    AgentaOS

    AgentaOS (Aristokrates OU, Estonia) becomes the official seller for its users' digital products and services, handling card checkout, subscriptions, VAT/sales tax in 135+ jurisdictions, invoices and chargebacks, and paying out twice a month in EUR or USD to the seller's own bank in ~85 countries, Brazil included.

    Why it scored lower: Regulatory and partner dependency (licenses, acquiring, Pix requires licensed partner); thin per-sale margins; crowded fee war (Creem 3.9%, Dodo 4%, Paddle 5%); large sellers churn to cheaper rails; Paddle already sup…

    Open ProductBots.ai →

Research, not investment advice. Numbers keep the label they were published with.