Koleen Paunon

@GithubProjects Sure! The Braille translates to: Use the weekend to build the life you want instead of trying to escape the life you have.

Prompt engineering is dead. Anthropic recently released the real playbook for building AI agents that actually work. It’s a 30+ page deep dive called The Complete Guide to Building Skills for Claude and it quietly shifts the conversation from “prompt engineering” to real execution design. Here’s the big idea: A Skill isn’t just a prompt. It’s a structured system. You package instructions inside a SKILL .md file, optionally add scripts, references, and assets, and teach Claude a repeatable workflow once instead of re-explaining it every chat. But the real unlock is something they call progressive disclosure. Instead of dumping everything into context: • A lightweight YAML frontmatter tells Claude when to use the skill • Full instructions load only when relevant • Extra files are accessed only if needed Less context bloat. More precision. They also introduce a powerful analogy: MCP gives Claude the kitchen. Skills give it the recipe. Without skills: users connect tools and don’t know what to do next. With skills: workflows trigger automatically, best practices are embedded, API calls become consistent. They outline 3 major patterns: 1) Document & asset creation 2) Workflow automation 3) MCP enhancement And they emphasize something most builders ignore: testing. Trigger accuracy. Tool call efficiency. Failure rate. Token usage. This isn’t about clever wording. It’s about designing an execution layer on top of LLMs. Skills work across Claude, Claude Code, and the API. Build once, deploy everywhere. The era of “just write a better prompt” is ending. Anthropic just handed everyone a blueprint for turning chat into infrastructure. Download the guide here: resources.anthropic.com/hubfs/The-Comp…

We recently conducted the Bitskwela–DICT Blockchain Readiness Program. 🚀 Over two days, DICT personnel explored computational thinking, rule-based system design, and policy-to-logic translation as preparation for smart contract development. Because smart contracts are not just code. They are policies that execute exactly as written. Proud to contribute to strengthening institutional capability for responsible blockchain adoption in the Philippines.

Counter-terrorism efforts in the Philippines (2016-2026) I made it #LLM ready too for security agents: raw.githubusercontent.com/KBPsystem777/p…

🦞Here is a noob's guide to setting up @openclaw 📝 I took notes of each step setting up a mac mini 🤖 @clawdbotatg turned it into an article: x.com/clawdbotatg/st…

Hot take: AI is pushing SWEs up the stack. Writing code is becoming table stakes. Direction, product judgment, and system design are the real leverage. Engineers who don’t evolve will get stuck reviewing PRs from bots. 🐳⚡️

Only a year ago people would argue between using TypeScript vs Python vs Rust vs Go. Today everyone I know is just coding in English and markdown.

There's an ongoing debate in the PH about the recent statement of the ICT secretary about blockchain being 101% free from hacks. Here's my thoughts:

3. risk containment (security, compliance, scalability) 4. speed with correctness 5. Authority to say NO The edge will be your judgement!💥

WHAT COMPANIES WILL ACTUALLY PAY FOR IN 2026 Sometime in 2-26, nobody pays big money for code anymore. AI will kill that. Companies will pay for: 1. correct decisions under uncertainty 2. avoiding irreversible architectural mistakes

Sine Nov-Dec 2025, i no longer write code. Devs can’t compete with AI. But devs can out own fellow humans with the use of AI. 2026 outlook: Devs should be Operators, use ai as junior devs/intern and labor workforce ⚡️🤖

@WakaTime @github 365 :D

Bragging rights: wakatime.com/a-look-back-at… @WakaTime

Software engineering will be completely unrecognizable in 5 years. Likely less