Agent skills
Standr.
Professional judgment for AI agents
AI agents generate correct output. The problem is what they don’t generate: consistent naming, navigable architecture, tests that buy confidence. Standr gives your agent the domain judgment to close that gap.
def apply_coupon(subscription: Subscription, coupon_code: str) -> dict: # Fetch coupon from database data = db.get_coupon(coupon_code) # expires_at is stored in UTC — compare against utcnow() if data is not None and data.expires_at > datetime.utcnow(): val = subscription.amount * data.discount_pct subscription.apply_discount( discount=val, promo_code=coupon_code ) db.save(subscription) result = {"ok": True, "discount": val} return result return {"ok": False, "discount": 0}
def apply_coupon(subscription: Subscription, coupon_code: str) -> dict: coupon = db.get_coupon(coupon_code) # expires_at is stored in UTC — compare against utcnow() if not coupon or coupon.expires_at <= datetime.utcnow(): return {"ok": False, "discount": 0} discount = subscription.amount * coupon.discount_pct subscription.apply_discount( discount=discount, coupon_code=coupon_code, ) db.save(subscription) return {"ok": True, "discount": discount}
Works with
AI output has a smell
You know it when you see it. Five endpoints that each invented their own conventions. An architecture that’s technically layered but structurally flat. A test suite that goes green without protecting a single invariant.
The output is correct. It just doesn’t look like someone cared.
Skills, not prompt packs
Prompt pack
A static text file. Front-loads instructions and hopes the model follows them. Quality varies with every run. Nothing adapts to your codebase.
standr skill
An executable workflow with judgment encoded. Reads your code, understands context, chains decisions, and makes targeted, defensible changes.
Plugins
Domain skills
architecture
Code in context
Code that works can still be structurally wrong. Standr reads your repo so changes strengthen the codebase instead of adding debt.
refactor
Code that reads
The gap between AI and human code is taste. Standr adds the judgment calls that make the code feel authored, not assembled.
testing
Code you trust
Passing tests don't mean safe code. Standr turns green suites into something you trust before shipping and can actually maintain.
More domains coming soon...
Install
$ npx skills add https://gitlab.com/standr.dev/standr $ claude plugin marketplace add https://gitlab.com/standr.dev/standr.git
$ claude plugin install architecture@standr
$ claude plugin install refactor@standr
$ claude plugin install testing@standr $ git clone https://gitlab.com/standr.dev/standr.gitThe best AI output is the kind nobody recognizes as AI.