Building Agent Skills from Scratch: A Retrospective on 8 Open-Source Projects
— § 01 —- COLOPHON
- Source Serif 4 · JetBrains Mono · Forge Codex
- TOOLS
- Next 15 · MDX · framer-motion
An independent developer's journey building 8 AI Agent tools — from idea to release
Building Agent Skills from Scratch: A Retrospective on 8 Open-Source Projects
Over the past few months, I built 8 open-source projects: 3 Agent Skills + 5 CLI tools. This post is a retrospective on what worked, what didn't, and what I learned.
§Why Build These Tools
One word: necessity.
I'm a tech blogger who publishes weekly on WeChat Official Account. The publishing workflow used to take 30-60 minutes of manual formatting. So I built md2wechat — one command to convert Markdown to WeChat-formatted HTML and push it as a draft.
That started a chain reaction.
§The 8 Projects
- ·md2wechat — WeChat formatting toolkit (Skill + Go CLI)
- ·agora — Multi-perspective deliberation system with 31 thinkers
- ·gcli — Gmail read-only CLI with OAuth PKCE
- ·imgcli — Zero-CGO image processing CLI
- ·any2card — Text-to-shareable HTML card converter
- ·interactive-learning — Socratic learning path generator
- ·jina-cli — Web-to-Markdown reader for AI agents
- ·md2wechat-lite — Lightweight Go CLI version of md2wechat
§What Went Right
1. One-line install is non-negotiable
If installation takes more than 3 steps, most users give up. My standard: the first code block in README is the install command.
2. Build for yourself first
7 out of 8 projects solved my own problems first. Tools you don't use yourself are hard to maintain.
3. Go's distribution advantage is real
Single binary, no runtime needed. curl | bash and you're done.
§What Went Wrong
1. Documentation is never enough
The most common issue after launch wasn't bugs — it was "how do I use this?"
2. Too many themes too early
md2wechat has 38+ themes. 30 of them are rarely used. Should have started with 3 great ones.
3. No automated testing for Skills
Agent Skill output is AI-generated and varies each time. But parsing logic and output format should still be tested.
§What's Next
- ·Commercialization — Turning mature Skills into paid services
- ·Community-driven — Let users vote on feature priorities
- ·Tutorials — Helping more developers build their own Agent Skills
Follow me on X or subscribe to my WeChat Official Account "极客杰尼" for weekly AI practice sharing.
I'm GeekJourney, an independent developer building tools for AI agents.
○