tried-and-true-aiSAFE
AI resources I've actually used and found helpful, curated from a non-technical background. 非技术背景亲测好用的 AI 资源。
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
English | 中文
I come from a non-technical background. Everything here is a public resource I've actually used and found helpful while building projects with AI.
The list keeps growing. Star the repo to follow along, and feel free to recommend your favorites in Issues.
Contents
- People Worth Following
- Understanding AI
- Skills & Tools
- Communities
- Web Design Inspiration
- UI Components & Motion
People Worth Following
- Matt Pocock - A well-known TypeScript educator now focused on teaching AI coding. His skills are written for engineers, but the way he approaches projects is a great reference for non-developers too
- Zara Zhang - An AI tinkerer from a non-technical background, best known for frontend-slides (web-based slides made by AI). Her codebase-to-course turns any codebase into an interactive course for non-technical learners. Also active on Xiaohongshu
- Khazix - khazix-skills - An open-source skill collection by the author of the WeChat account "数字生命卡兹克" (Digital Life Khazix). Follow the account for the latest AI news (in Chinese)
Understanding AI
- Dictionary of AI Coding - AI coding jargon explained in plain English. One I keep coming back to
- VibeHub - An illustrated glossary of vibe coding terms across frontend, backend, Git and AI. Each entry goes from how you'd say it to what it's called: a button changing color when your mouse moves over it is a "Hover" state. Non
a8228c2a4cc2OBSERVED · 2026-10-13Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
Gates applied: no_behavioural_pass.
a8228c2a4cc2full audit observations/trust-audit/skill/zlgan-spec__tried-and-true-ai.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-13 | a8228c2a4cc2 | SAFE | B | 89 | first audit |
Questions
What does the tried-and-true-ai skill do?
AI resources I've actually used and found helpful, curated from a non-technical background. 非技术背景亲测好用的 AI 资源。
Is tried-and-true-ai safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can tried-and-true-ai access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (a8228c2a4cc2), read on 2026-10-13. The repository is watched, and a new audit runs when it changes — this is the first audit.