M
marketcalls/discord-roblox-child-safety
AI skills that help parents, teachers, counsellors and doctors check a child's Discord/Roblox messages for…
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
- Star count
- 0 ★ · marketcalls/discord-roblox-child-safety · read from the GitHub search API · (checked 2026-11-13 20:00:50)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-08 · last seen 2026-11-14 · seen 7× · listed by 1 sources
- Score
- score 103 · 1 sources · repo
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: 开源项目. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
marketcalls/discord-roblox-child-safety;first catalogued 2026-11-08;last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.# Discord & Roblox Child Safety Skills
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
An AI helper that reads your child's Discord messages — with your permission — and tells you in plain words whether anyone is putting them in danger.
It works with Claude Code, Claude Desktop, OpenAI Codex, Cursor and Google Antigravity, and even with AI tools that can't use a browser (you run one small script yourself, then the AI reads the file).
## Why this exists
Kids spend hours on Discord, often because of Roblox: trading game items, joining "servers", making friends they have never met. Most of it is harmless. Some of it is not.
These skills were built after a real family review. The parents were worried about "too much Discord". What the review actually found was:
the child had told online friends about self-harm and suicide attempts that the parents never knew about,
a contact with a cute display name was an 18-year-old man who talked about his sex life, asked the child to keep secrets, deleted his messages, and asked for a photo of the outside of the child's house,
several adults were mixed in with 13–15-year-olds in Roblox "trading" servers,
the child was online until 3–5 AM because of unpaid "staff" work in those servers.
None of this showed up as "danger" at first glance. It took reading tens of thousands of messages carefully. That is what this tool helps an AI do — safely, and without the parent having to read everything themselves.
## Who it's for
Parents and guardians worried about who their child is talking to.
Teachers and schools helping a family after a concern is raised.
School counsellors supporting a student and their parents.
Doctors, psychiatrists, psychologists and therapists — a parent can export the messages and share the file (and the report) with the child's clinician.
Professionals should always work with the parent's or guardian's consent. The parent logs in or exports the data; the professional never needs the child's password.
## What it checks
| It looks for | Examples |
| 🆘 Suicide and self-harm | "I want to die", goodbye letters, "I attempted", cutting, friends panicking at 3 AM |
| 🧑🦱➡️👧 Grooming by adults | age questions, "you're so mature", gifts, secrets, deleting messages, asking for photos or where you live |
| 🔞 Sexual talk | adults talking about sex with a child, "friends with benefits", "what are you wearing" |
| 💸 Sextortion | "send money or I'll post your pictures" — especially aimed at teenage boys |
| ⚠️ "764"-style groups | people pushing kids to hurt themselves on camera |
| 🎣 Scams | free Nitro links, QR-code "verification", fake Discord staff, Roblox trading and "middleman" scams |
| 🤖 "Join servers for you" bots | apps that keep adding your child to servers (even banned ones come back), Roblox "voice chat enabler" / "game copier" tools that steal accounts |
| 🎰 Gambling | casino servers using Robux, game currency or real money |
| 😡 Bullying and threats | insults, slurs, "kys", threats to share someone's address |
| 📍 Private details leaked | real name, school, city, photos that show home or uniform |
| 🌙 Healthy use | how many messages a day, how much happens between midnight and 5 AM |
## What you get
A private report (on your own computer) that says, in plain language:
It works with Claude Code, Claude Desktop, OpenAI Codex, Cursor and Google Antigravity, and even with AI tools that can't use a browser (you run one small script yourself, then the AI reads the file).
## Why this exists
Kids spend hours on Discord, often because of Roblox: trading game items, joining "servers", making friends they have never met. Most of it is harmless. Some of it is not.
These skills were built after a real family review. The parents were worried about "too much Discord". What the review actually found was:
the child had told online friends about self-harm and suicide attempts that the parents never knew about,
a contact with a cute display name was an 18-year-old man who talked about his sex life, asked the child to keep secrets, deleted his messages, and asked for a photo of the outside of the child's house,
several adults were mixed in with 13–15-year-olds in Roblox "trading" servers,
the child was online until 3–5 AM because of unpaid "staff" work in those servers.
None of this showed up as "danger" at first glance. It took reading tens of thousands of messages carefully. That is what this tool helps an AI do — safely, and without the parent having to read everything themselves.
## Who it's for
Parents and guardians worried about who their child is talking to.
Teachers and schools helping a family after a concern is raised.
School counsellors supporting a student and their parents.
Doctors, psychiatrists, psychologists and therapists — a parent can export the messages and share the file (and the report) with the child's clinician.
Professionals should always work with the parent's or guardian's consent. The parent logs in or exports the data; the professional never needs the child's password.
## What it checks
| It looks for | Examples |
| 🆘 Suicide and self-harm | "I want to die", goodbye letters, "I attempted", cutting, friends panicking at 3 AM |
| 🧑🦱➡️👧 Grooming by adults | age questions, "you're so mature", gifts, secrets, deleting messages, asking for photos or where you live |
| 🔞 Sexual talk | adults talking about sex with a child, "friends with benefits", "what are you wearing" |
| 💸 Sextortion | "send money or I'll post your pictures" — especially aimed at teenage boys |
| ⚠️ "764"-style groups | people pushing kids to hurt themselves on camera |
| 🎣 Scams | free Nitro links, QR-code "verification", fake Discord staff, Roblox trading and "middleman" scams |
| 🤖 "Join servers for you" bots | apps that keep adding your child to servers (even banned ones come back), Roblox "voice chat enabler" / "game copier" tools that steal accounts |
| 🎰 Gambling | casino servers using Robux, game currency or real money |
| 😡 Bullying and threats | insults, slurs, "kys", threats to share someone's address |
| 📍 Private details leaked | real name, school, city, photos that show home or uniform |
| 🌙 Healthy use | how many messages a day, how much happens between midnight and 5 AM |
## What you get
A private report (on your own computer) that says, in plain language:
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/marketcalls-discord-roblox-child-safety/)
- Source
- github · https://github.com/marketcalls/discord-roblox-child-safety
- Browse by field
- Open source
- added
- today
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.