Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: agent-skills
AWS DevOps Agent in Practice: Agent Spaces, Investigations, Release Checks and Skills
A walk through AWS DevOps Agent: creating an Agent Space, running a root cause investigation, the preview release-management features, and writing custom Agent Skills.
10 min readCLAUDE.md, SKILL.md and MCP: Which Layer Holds Which Instructions
Why one giant CLAUDE.md fails coding agents, what belongs in rules, skills and MCP connections, scopes and paths, a decision tree and the AGENTS.md naming trap.
11 min readAgent Harnesses: A Folder Standard for Skills and References
How a harness extends agent skills with a HARNESS.md file, skill and reference directories, progressive disclosure, and nested layouts for large agents.
8 min readWhere Each Instruction Belongs: AGENTS.md, CLAUDE.md and SKILL.md
How the three context files load, why a skill description acts as a gate, what each file should hold, and how to bridge Claude Code and other agents in one repo.
9 min readAgent Skills Are Code: Scope, Disclose, Script and Test Them
Why SKILL.md is production logic: write procedural knowledge only, tune activation, load progressively, move exact work to scripts, build evals and delete losers.
10 min readPi, the Minimal Coding Agent Harness: Extensions, Skills, Sessions and Safety
Why a small terminal coding harness with four tools and a short system prompt can beat feature-heavy agents: install, models, session trees, extensions, skills and sandboxing.
8 min readAgent Plugins 1.0.0: The Shared Packaging Format for Skills and MCP Servers
Agent Plugins 1.0.0 gives skills and MCP servers one packaging format: folders, plugin.json and mcp.json, what it leaves out on security, and a CLI example.
7 min readMCP, CLI and Skills Together: A Connectivity Stack for Production Agents
Skills, CLI and MCP each solve a different connectivity problem. See when to use each, plus progressive discovery, Code Mode and the 2026 MCP roadmap.
5 min readSelf-Improving Agents Through Skills: Reuse, Selection, Repair and Verification
A four-part design for agents that improve their own skills: save working code, sharpen descriptions, propose reviewed fixes and verify output before handoff.
15 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.