SRS community robot is online now: https://t.co/9P3eMaGjS7 I trained this robot with skills and knowledge base. So it works very well much better than the common AI.

Opus 4.6 enables 1m context window. It also uses subagents when evaluating the skills, which consumes less tokens. As a result, when I evaluated 12 questions and answers, it only consumed 7% of the context window. Nice. 👍

Skill is very powerful, but how to test and assure you get a stable skill over time? Claude Code supports the evaluation for skills, which is very useful. It is just a evals.json, which describe the Q&A covering the skill. It is powerful, but only supported by Claude Code.

Finished the ST knowledge base with my two AI contributors: claude and codex. And, gh (github cli) is so powerful that almost AI can do everything you can do, be careful to grant access to gh. https://t.co/JdL32qnzUn

An very interesting discover: Knowledge-base enables AI to write utests with logic that can be understand by human developer. Without the KB, AI sometimes just output some garbage utest code, in order to improve the coverage rate. But this type of utest doesn't make sense.

It's a easy and fantastic experience to study the code with OpenClaw, which creates utest, setup the cmake, and enable debugging for utest.

3 Pitfalls of Using OpenClaw as Your Personal Assistant

I find agent skills very useful because they turn "you asking questions" into "the AI asking you questions." For example, when I need AI to review or correct a document, I have to tell it which document and which section. But with skills, the AI asks me instead — I just pick the

I found that AI agent skills behave very consistently, similar to a programmed workflow. For example, every time I use a skill to review a section of a knowledge base, it always works correctly and uses the right matching skill. This improved my workflow and made my work more

I'm writing a knowledge base for ST. About one-third of it is based on background knowledge from my own experience; the rest is code summaries generated by AI. I told AI to summarize specific modules and workflows — for example, the coroutine thread creation workflow. Then I

I'm building the knowledge base about coroutines in ST with OpenClaw, and I found a comment regarding the aarch64 register SP: Register '31' is one of two registers depending on the instruction context: For instructions dealing with the stack, it is the stack pointer, named rsp.

I'm working on the knowledge base for ST (state threads), the coroutine library used in the SRS media server. It's been a long time since I last worked on this coroutine library, so I only have a general idea of it — not much detail. Still, I managed to write a brief overview of

🧠 Key insight from building AI-assisted open source: kills ≠ Knowledge Base. Skills LOAD the knowledge base. Published an SRS skill to @ClawHub — when you ask about SRS, it automatically loads the codebase, docs, and design decisions into context. The result? Not a generic AI

Claude Opus 4.6 has a 1M token context window. SRS (our open source media server) is ~300K tokens — code + docs combined. That means the entire project fits in one shot. No RAG, no context engineering. The AI just... knows everything. But the real unlock: it can help the

Just spent an hour building the SRS knowledge base — and I didn't write a single word. I just talked (🤣practicing my spoken English😊) to my AI about the project: vision, ecosystem, limitations, performance. It organized everything into structured docs. For open source

When I was teaching my OpenClaw AI assistant about SRS, it says SRS supports converting RTMP(MP3) to WebRTC(Opus), but I didn't remember. Then AI showed me the code and the steps to verify it. Finally, I confirmed it's true! Imagine that — if we successfully build a