Skill Claude Code
Serverless is a billing-and-scaling model, not a badge of modernity.
not rated 2 6d ago A 22 tokens
2Stars on the repository
119Mods indexed here, across every type
6d agoLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied
Skill Claude Code
SLO (Service Level Objective): What we promise (99.9%).
not rated 2 6d ago A 23 tokens
Skill Claude Code
When: Not important (contact info).
not rated 2 6d ago A 16 tokens
Skill Claude Code
Always start with EXPLAIN ANALYZE to understand execution.
not rated 2 6d ago A 17 tokens
Skill Claude Code
The single highest-leverage decision is recognizing that most of what teams call.
not rated 2 6d ago A 19 tokens
Skill Claude Code
Ownership models are usually inherited rather than chosen, and the inherited one.
not rated 2 6d ago A 18 tokens
Skill Claude Code
Before writing anything, answer three questions: who reads this, what do they.
not rated 2 6d ago A 19 tokens
Skill Claude Code
Debt that exists only in engineers' heads cannot be prioritised, funded, or.
not rated 2 6d ago C 21 tokens
Skill Claude Code
The single most useful question before analysing anything is: what does it cost.
not rated 2 6d ago A 20 tokens
Skill Claude Code
Apply Arrange-Act-Assert pattern for clear, maintainable tests with detailed guidance.
not rated 2 6d ago A 22 tokens
Skill Claude Code
Comprehensive systematic approach to achieving complete test coverage through structured category-based testing.
not rated 2 6d ago A 20 tokens
Skill Claude Code
These three are not interchangeable, and picking the wrong one is the root of a.
not rated 2 6d ago A 22 tokens
Skill Claude Code
Comprehensive guidelines for when and how to use mocks, stubs, and fakes in tests.
not rated 2 6d ago A 25 tokens
Skill Claude Code
Three shapes get argued about as if one were correct.
not rated 2 6d ago A 16 tokens
Skill Claude Code
Every methodology — STRIDE, PASTA, LINDDUN, attack trees — is a technique for.
not rated 2 6d ago A 27 tokens
Skill Claude Code
Almost every downstream bug traces back to an index that was assumed regular and.
not rated 2 6d ago A 19 tokens
minimal
89Skill Claude CodeCodex
Design the tool surface an agent acts through so the model picks the right tool, recovers from its own mistakes, and terminates — without unbounded cost or duplicated side effects.
not rated 2
changed 28d ago A 0 tokens
verbose
90Skill Claude CodeCodex
Most agent failures are tool-description failures, not reasoning failures. When an agent calls the wrong tool, passes a malformed date, or loops on an error, the first place to look is not the prompt or the model — it is the schema. The model cannot read your implementation, your tests, or your intentions. It sees a…
not rated 2
changed 28d ago A 0 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: