kimtth/agent-skill-100-lines-or-less

academic-paper-review

Use when: review an academic paper with a structured review form and multiple reviewer personas.

api-design

Use when: design a clear, consistent, and evolvable API contract before implementing it.

architecture-decision-records

Use when: record a significant technical decision, its context, and consequences as an ADR.

authentication

Use when: implement or review authentication flows, sessions, tokens, and password handling securely.

authorization

Use when: design or review access control so users can only do what they are permitted to do.

bash

Use when: write or review robust shell scripts that fail fast and handle paths and input safely.

brainstorming

Use when: explore options or decompose an ambiguous problem before committing to one approach.

caching-strategies

Use when: add caching with the right layer, key design, invalidation, and consistency trade-offs.

ci-cd

Use when: design or improve a CI/CD pipeline for fast, reliable, automated build-test-deploy.

clean-architecture

Use when: structure an app so business logic is independent of frameworks, UI, and databases.

concurrency

Use when: write or review concurrent code that avoids races, deadlocks, and shared-state bugs.

cpp

Use when: write or review modern C++ with RAII, smart pointers, and value semantics.

critique

Use when: give structured, specific design critique with actionable fixes, not vague feedback.

csharp

Use when: write or review modern, idiomatic C# with async, nullable reference types, and clean structure.

database-migrations

Use when: write and apply schema migrations safely without downtime or data loss.

dependency-injection

Use when: decouple components by injecting their dependencies instead of constructing them inline.

design-patterns

Use when: apply a design pattern to a real problem without over-engineering the solution.

docker-compose

Use when: define multi-service local and test environments with Docker Compose reliably.

domain-driven-design

Use when: model a complex domain with a shared language, bounded contexts, and clear aggregates.

drizzle-orm

Use when: define type-safe schemas, migrations, and queries with Drizzle ORM and full TS inference.

duckdb-query

Use when: run analytical queries in-process over files, Parquet, or CSV with DuckDB.

error-handling

Use when: design error handling so failures are explicit, recoverable, and never silently swallowed.

event-driven-architecture

Use when: design systems around events and messages with reliable, decoupled processing.

extract-design-system

Use when: extract tokens, components, and patterns from an existing codebase into a documented system.

frontend-design

Use when: build or reshape UI with distinctive, intentional visual design instead of generic defaults.

git-bisect

Use when: find the commit that introduced a bug with a binary search over history.

git-rebase

Use when: clean up or reorder commits with rebase while keeping history safe and reviewable.

github-actions

Use when: write or review GitHub Actions workflows that are fast, secure, and maintainable.

go

Use when: write or review idiomatic Go with explicit errors, clear concurrency, and small interfaces.

graphql

Use when: design or review GraphQL schemas and resolvers with safe, efficient data access.

grill-me

Use when: pressure-test your own reasoning or a plan before committing to it.

grill-with-docs

Use when: verify claims or API usage against fetched official documentation, not memory.

handoff

Use when: write a handoff so another session or agent can resume work without context loss.

improve-codebase-architecture

Use when: propose structural improvements to a codebase without rewriting it wholesale.

input-validation

Use when: validate and sanitize untrusted input at boundaries to prevent bad data and attacks.

java

Use when: write or review modern, idiomatic Java with immutability, clear types, and clean structure.

kotlin

Use when: write or review idiomatic Kotlin with null safety, immutability, and concise expressions.

load-testing

Use when: measure system behavior under load to find limits, bottlenecks, and regressions.

merge-conflict-resolution

Use when: resolve git merge or rebase conflicts correctly without losing intended changes.

mocking

Use when: use test doubles correctly — mock true boundaries, not the code under test.