Tag: #skills
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 21 posts
Writing as an Engineering Skill — What Design Docs, Postmortems, and Review Comments Actually Do
Everyone says writing matters for engineers, and the reason usually collapses into a story about promotion. This piece runs the order differently. Writing is first a device for verifying your own thinking, then a tool fo
2026-08-15 · 6 min read #career#skills#technical-writing#design-doc#postmortemDesigning Verification — Tests as Grounds for Trust, Not Pass or Fail
A green build tells you nothing on its own. Green acquires meaning only once it is settled what you no longer have to worry about. This piece covers treating tests as grounds for trust rather than as a pass-fail gate: at
2026-08-15 · 6 min read #career#skills#testing#verification#craftA Sense for Production — What Looks Different After You Have Been Through an Outage
Two people read the same design doc and one of them reads something else entirely: what logs exist when this breaks at three in the morning, how many minutes a rollback takes, and what happens to the data that already la
2026-08-15 · 7 min read #career#skills#sre#production#reliabilityWhat Stays Expensive — Four Things That Gain Value When Generation Gets Cheap
Answer the question "what should engineers prepare for" with a list of tools and the answer is stale in two years. This piece proposes a different axis: the skills that hold value are the ones that stay expensive to veri
2026-08-15 · 6 min read #career#skills#ai#craft#engineering-cultureWhy Debugging Resists Replacement — The Craft of Elimination
Debugging runs in the opposite direction from writing code. Writing produces one possible thing; debugging erases possible causes until one is left. This piece covers why debugging sits on the expensive-to-verify side, h
2026-08-15 · 6 min read #career#skills#debugging#craft#troubleshootingReading What Others Wrote — Entering a Codebase and Reverse-Engineering an Undocumented System
Writing gets practiced under compulsion; reading does not. That asymmetry made reading the skill everyone performs daily and nobody trains, and now that generation is cheap it is the capability whose price rose fastest.
2026-08-15 · 6 min read #career#skills#code-reading#craft#legacy-codeWhy Domain Knowledge Is a Defensible Line — The Engineer Who Knows the Business
Domain knowledge is not in the code and usually not in the docs; it lives in people and in organizational habit. That makes it the single largest contributor to the verification cost this series has been tracking, and th
2026-08-15 · 7 min read #career#skills#domain-knowledge#ddd#ontologyThe Fear of Growing Old With an Aging Stack
As the years accumulate, the shape of the anxiety changes. It moves from wondering whether there is a place to start toward wondering when the place you are standing on disappears. This post splits that fear in two: depr
2026-08-15 · 7 min read #career#senior-engineer#obsolescence#skills#agingWorking With AI Tools as a Skill — Where the Delegation Line Sits and How to Verify
Saying someone is good with AI tools carries no information until you know what they delegated and how they judged the result. This piece covers the criterion that draws the delegation line by verification cost rather th
2026-08-15 · 7 min read #career#skills#ai#verification#engineering-practiceFraming the Problem — How to Avoid Perfectly Solving the Wrong One
A perfect solution to the wrong problem is usually worse than a rough solution to the right one, because a rough answer signals that it is not finished and a perfect one signals that it is. This piece covers the three qu
2026-08-15 · 6 min read #career#skills#problem-framing#requirements#scopingLearning How to Learn — Telling Fundamentals From Fashion, and Choosing One Thing to Go Deep On
A learning strategy usually arrives as a list of things to learn, when what is actually needed is a criterion for what not to learn. This piece covers the single question that separates fundamentals from fashion, the rul
2026-08-15 · 7 min read #career#skills#learning#fundamentals#deliberate-practiceThe FDE Skill Map — Baselines, Working Levels, and Check Questions for 8 Domains
A map of the skills a Forward Deployed Engineer (FDE) actually needs, drawn across eight domains: Linux, networking, Kubernetes, databases, auth and security, observability, cloud and infrastructure, and customer communi
2026-08-12 · 6 min read #career#fde#forward-deployed-engineer#skills#roadmapWhy the Claim That Code Was Never the Hard Part Makes People So Angry
An essay that reached the top of Hacker News in August 2026 argues that saying code was never the hard part is an insult to every programmer. This post agrees with the rebuttal but locates the cause somewhere else. That
2026-08-09 · 8 min read #career#craft#ai#engineering-culture#skillsWhen Code Generation Gets Cheap, Which Skills Go Up in Value — What Depreciates and What Appreciates
When code generation becomes cheap and abundant, value does not vanish — it moves to whatever is still a bottleneck. Right now that bottleneck is verification, judgment, and integration. Building on Jason Wei's asymmetry
2026-07-12 · 14 min read #career#software-engineering#ai#skills#code-reviewThe Tech Interview Playbook — Coding, System Design, and Behavioral
A tech interview tests your skill — and is a separate skill of its own. Pattern-based coding prep, a 5-step system design frame, building a STAR story bank for behavioral rounds, the staple questions per role, and an 8-w
2026-07-06 · 7 min read #career#interview#skills#preparationA Knowledge Map for the Rising Tech Roles of 2026 — What to Actually Study
AI/LLM engineer, platform/DevOps/SRE, security engineer, data engineer, frontend — a checklist-style map of what the five most in-demand roles actually require. Includes the cross-cutting skills every role shares, plus t
2026-07-06 · 7 min read #career#roadmap#skills#learningBuilding a Career That Compounds — Don't Chase Passion, Build Skill
A good career is not built by "following your passion." It is built by compounding rare and valuable skills, reputation, and relationships over time. Career capital theory, deliberate practice, leverage, and a repeatable
2026-07-03 · 13 min read #career#growth#skills#productivityBuild Your Own Claude Code Skill — A Hands-On Deep Dive Into SKILL.md, Invocation, and Distribution (2026, english)
Agent Skills were introduced by Anthropic in October 2025 and opened as a standard in December 2025. As of May 2026 they are the default way to extend Claude Code. The mechanism is small — a SKILL.md with YAML frontmatte
2026-05-14 · 23 min read #claude-code#skills#anthropic#ai-tooling#hands-onAI Coding Workflow Best Practices in 2026 — CLAUDE.md, AGENTS.md, .cursorrules, Skills, Subagents, MCP Deep Dive
The standards AI coding tools are converging on in 2026 — CLAUDE.md, AGENTS.md, .cursorrules, .github/copilot-instructions.md, plus Claude Code Skills, subagents, hooks, MCP, and permission modes. What goes in each file,
2026-05-14 · 20 min read #ai-coding#claude-md#agents-md#cursorrules#claude-codeWhat is an AI Harness: Skills, Context, Hooks, and Permissions — The Orchestration Architecture Controlling AI
An AI Harness is an orchestration layer that wraps and controls AI models. We dissect the 7 building blocks — System Prompt, Tools, Context, Skills, Hooks, Permissions, and Memory — and show how to build one with the Cla
2026-03-23 · 35 min read #ai-harness#claude-code#agent-sdk#skills#context