Hakim.

[Matt Pocock @mattpocockuk]

/writing-great-skills is quickly becoming my most often-invoked skill

It's just really good at writing skills, guys.

npx skills add mattpocock/skills --skill writing-great-skills

[cesar.wtf @heycesr]

Most underrated data source in a company: your AI agent's conversations.

Your agent talks to more customers than any employee, but the data it generates goes nowhere.

@trylatitude changes that, see how:

[David Ondrej @DavidOndrej1]

Matt Pocock just shared his entire agentic engineering workflow

every tool, every trick, the exact setup he uses to ship

just copy him

[Matt Pocock @mattpocockuk]

Announcing mattpocock/skills v1

- Achieved a 63% reduction in token cost for skill descriptions
- Split skills into model-invocable and user-invocable skills, adding /codebase-design, /domain-modeling, and /grilling
- (UPDATED) /writing-great-skills - rewritten from the ground up, encoding my skill-writing best practices
- (UPDATED) /diagnose -> /diagnosing-bugs - now model-invocable, awesome for fixing hard bugs
- (NEW) /ask-matt: a router skill that teaches you how all the engineering skills work together

[Matt Pocock @mattpocockuk]

Here are my 7 phases of AI-powered development.

I've been thinking that the pre-PRD phase needs more structure. You need to figure out the shape of the design tree first, before then walking down it with higher-fidelity prototypes.

In other words, /grill-with-docs needs to change again IMO

[Alpha Batcher @alphabatcher]

Prompt engineering is where people go when they refuse to write files

Karpathy's LLM Wiki gist is painfully simple:

> raw sources stay untouched
> the agent writes the wiki
> `CLAUDE.md` or `AGENTS.md` tells it the rules
> `index.md` maps the pages
> `log.md` records what changed

That is why a good answer should not die in chat history

If the model gives you a useful comparison, summary, decision, bug explanation, or research thread, file it back into the project

Use:

> `wiki/topics/[topic].md`
> `wiki/entities/[person-or-company].md`
> `wiki/sources/[source-name].md`
> `wiki/analysis/[question].md`

Make the agent keep the wiki from rotting:

> backlinks
> summaries
> contradictions
> stale claims
> orphan pages
> missing source links

For coding projects, same idea:

> `CLAUDE.md`: who you are, project rules, files not to touch
> `index.md`: current files and features
> `log.md`: date, change, reason
> saved pages: decisions you do not want to re-explain

Start by saving one good answer today

[Tech with Mak @techNmak]

Let me tell you about a tool that turns any codebase into an interactive knowledge graph you can explore, search, and ask questions about.

It's called Understand Anything.

Here's what actually happens when you run it:
Six agents analyze your project in parallel. A knowledge graph gets built of every file, function, class, and dependency. An interactive dashboard opens, color-coded by architectural layer, fully searchable, every node clickable with plain-English explanations.

Then you get:
→ /understand-chat - ask anything about the codebase in plain English
→ /understand-diff - see what your changes affect before committing
→ /understand-explain - deep dive into any specific file or function
→ /understand-onboard - generate an onboarding guide for new team members
→ /understand-domain - extract business domain knowledge as a horizontal graph
→ /understand-knowledge - analyze a wiki and surface implicit relationships as a navigable idea graph

The persona-adaptive UI is a detail I hadn't seen before, the dashboard adjusts its detail level depending on whether you're a junior dev, PM, or power user.

It supports multilingual output too. Run /understand --language zh and the entire dashboard generates in Chinese.

It works with Claude Code, Cursor, Copilot, Gemini CLI, Codex, OpenCode, Vibe CLI, Cline, KIMI CLI.

Here's the GitHub Repo: https://t.co/J1cN92k7rj

[Adam @heyadam_ai]

Singapore’s Foreign Minister, Dr Balakrishnan casually explaining how he built his own AI agent (a 2nd brain for diplomacy) using Claude & WhatsApp integration etc. on a Raspberry Pi

“You cannot govern a technology you have only been briefed on.” 🇸🇬

[Jaynit @jaynitx]

https://t.co/67rAGZE7X3

[Suryansh Tiwari @Suryanshti777]

https://t.co/xfcqOGZXL0

[Etisha Garg @GargEtisha]

https://t.co/GrNUG5E8Ki

[m0h @exploraX_]

most people don’t know the difference between MCP and agentic skills.

this 20mins course teaches you everything you need to know.

it’s free on YT. bookmark. watch.

at the end of the video course, you’d have learnt what the differences and similarities between agents skill and MCP.

and the best part when to use which.

this is just the first 12mins, check the cs for link to the full video.

[Morgan @morganlinton]

Just published.

If you've been trying to figure out how to optimize OpenClaw now that things have gotten a bit complicated with Opus, this might help.

[aditya @adxtyahq]

everyone wants to build a startup
no one knows what to build

Sam Altman explains it

[Thevesh @Thevesh]

My Raya traffic bot is back!

This is the 3rd year it's running, giving you data on the ETA for various routes, across time.

In short, you can see how long your journey would have taken, depending on what time you left in the past 48 hours—this is something that even Waze, Google Maps, etc do not provide to users 😌

Free to join on Telegram—in addition to the ETA charts, there's a really nice community of 3.5k people which has built up over time.

Safe travels and Selamat Hari Raya in advance—hope it helps!

https://t.co/9eiFAG93oi

🧵I've also added an interesting feature this year based on LLM cameras—read on for explanation.

[Bitcoin Malaya @bitcoinmalaya]

If you pay tax monthly via PCB (Potongan Cukai Bulanan / Monthly Tax Deduction)

👉 Select “No (Refund payable to Employee)”

Any tax refund should go back to you, not your employer

Many first-time filers get confused by this

[hoeem @hooeem]

https://t.co/xhFqyYE7RD

[Mohini Shewale @s_mohinii]

Instead of watching 2 hours Netflix, learn claude in 1 hours for Free (Build & Automate Anything)

[Najib Fazail @najibfazail]

Aku pernah kaji pergerakan saham Bursa Malaysia 2023. Konklusi yang aku boleh buat :

'Nak cepat untung kena labur di small cap. Nak kurang rugi, labur di big cap.'

Small cap
Purata keuntungan : 134%
Purata kerugian : -55%

Big cap
Purata keuntungan : 44%
Purata kerugian : -12%

[The Futurizts @TheFuturizts]

Sports Relief: RM1,000

✅ Self, spouse, child, and parents
✅ Badminton String, Racket, etc.
✅ Anytime Fitness Membership
✅ Pickleball Court Rental
✅ Registered Marathons
✅ Swimming goggles

❌ Dri-Fit Shirt
❌ Pilates Class
❌ Running Shoes
❌ Swimming suit
❌ Motorized bicycles

Sources 👇