跪拜 Guibai
← All articles
AI Programming · Code Standards

Stop Repeating Yourself: Google Engineer Turns Agent Constraints into a Reusable Skill Library

By IT规划师 ·
Read original on juejin.cn ↗ Google Translate ↗ Alt translation

Every repeated instruction you give an AI agent is a failure of memory, not of intelligence — this skill library makes those constraints persistent and checkable, cutting both rework and the manual diff-review burden. Teams running AI assistants in daily development get a concrete way to stop re-explaining the same rules in every new session.

Summary

The recurring pain with AI coding agents isn't that they can't write code — it's that every engineering constraint you explain (read the existing code first, only touch the named files, run lint before commit) lives only in that one conversation and evaporates when the session ends. The agent re-derives your working style from scratch each time, then "fixes" three extra classes and leaves you to audit the diff by hand.

addyosmani/agent-skills, which hit GitHub Trending on 2026-11-12 with 812 stars that day, takes a different angle than switching to a stronger model or writing longer prompts. Instead of disposable prompt text, it standardizes everyday engineering practices into a library of skills the agent can read and check against persistently. The author argues this reduces rework more than prompt tuning does, and the project is aimed at teams who are already using AI assistants daily but are burned by "changes too much, afraid to merge."

The article also offers three no-install steps you can take today: write rules into an AGENTS.md, make the agent report its intended file changes before acting, and archive any instruction you've said more than twice. It's a process-layer fix, not a model-capability upgrade.

Takeaways
— The project addyosmani/agent-skills is authored by Google engineer addyosmani and entered GitHub Trending on 2026-11-12, gaining 812 stars that day.
— The source material's heat score of 96/100 is its own metric, not an official GitHub rating.
— The library's positioning is to standardize production-grade engineering practices into reusable skills that AI coding agents can read and follow repeatedly.
— Writing constraints into an AGENTS.md file once saves dozens of repeated explanations across sessions.
— Requiring the agent to output its intended file-change list before acting blocks most accidental modifications.
— Any instruction repeated three times should be archived into a file as the lowest-cost form of standardization.
— The approach works at the process layer and does not change model capabilities, so it won't appeal to teams looking for a stronger or faster model.
Conclusions

Prompts are inherently disposable; encoding constraints as persistent skills treats the real bottleneck as context loss, not model competence.

The three suggested steps show that most agent rework can be prevented with lightweight process changes, not heavier tooling or bigger models.

The article deliberately distinguishes "the direction is worth following" from "the project is good to use" — a useful brake against treating Trending buzz as validation.

Concepts & terms
AGENTS.md
A file in a repository that records working instructions for AI coding agents — such as 'read existing implementation before changing' or 'only modify specified files' — so constraints persist across sessions instead of living only in a prompt.
From the discussion
Featured comments
shushenghong

The rule 'say the same thing a third time, archive it' is the most practical. There's an extra layer of problem in a team: you archive it into your own config, your colleagues' agents still don't know, and when you hand off to someone else you have to repeat it all over again. Later we kept only one copy of rules and skills, put them in the shared environment everyone uses, with two or three people responsible for changes, and the rest just bring them along when assigning tasks.

See top comments, translated →
Source: juejin.cn ↗ Google Translate ↗ Backup ↗