Go Style Agent Skill – Opinionated Skill for Writing Golang
Organized Go best practices for agents, but it's markdown files like any custom instruction.
Opinionated agent skills for maintainable TypeScript
Prompt library for Claude Code when AI code quality is already a known problem.
Developers using Claude Code for TypeScript projects
Cursor rules · Continue.dev configs · Anthropic's MCP examples
Reading the leaked prompts made the failure mode pretty obvious: the agent is optimized to get its feature working inside local context, not to improve the codebase as a whole. So it makes defensive patch fixes, leaves old paths around, avoids holistic cleanup, and slowly fills the repo with debt. My take is that it's intentionally designed to one shot new projects/features but you have a aggressively prompt it to write maintainable code.
I've been writing typescript for a number of years now (and startups and large companies) and have pretty strong opinions how to do it sustainably. The fact that we code with agents hasn't changed the fundamentals as much as vibe coders will have you believe. Hopefully others find this skill helpful.
Organized Go best practices for agents, but it's markdown files like any custom instruction.
It combines build, validation, auto-fix and a guarded publish pipeline (5 prereq gates + automatic rollback) into one zero-config CLI — run check --fix, then publish and hope is replaced by gates. The plugin system, repo scanner and the fact it 'builds itself' (esbuild ESM/CJS + .d.ts) make it feel pragmatic and production-minded, though much of the value is orchestration of existing tools rather than a brand new compiler-level trick.
Yet another AI content wrapper claiming human-sounding output in a saturated market.
Curated prompt library when dozens of skill packs already exist for Claude.
TypeScript in Postgres beats plv8's plain JavaScript with actual type safety.
Self-pruning skill layer for Claude Code that merges duplicates and updates from real usage.