Menü
Thinking guidelines to reduce common coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Task and project management in .claude/global-project/. Use when user ask for a new task.
TypeScript and Angular coding best practices. Use when working with TypeScript, Angular, or Node.js files: implementation, testing, refactoring, RxJS Observables, type system, strict mode, generics, and async patterns.
Docker and docker-compose best practices. Use for any Docker task: Dockerfiles (multi-stage builds, alpine, non-root), docker compose services (Go API, frontend, MariaDB, Oracle), healthchecks, volumes, networks, and K8S-compatible configurations.
Rules for writing and updating documentation. Use for any non-trivial documentation task in README.md, markdown files, text files, and code comments.
Best practices for Go project Makefiles. Use when creating or modifying a Go project Makefile: adding/reviewing targets, PHONY declarations, tab indentation, docker compose v2 targets.
Comprehensive testing specialist for all levels and types. Use when writing unit, integration, E2E, performance, or security tests; creating test strategies and plans; analyzing test coverage; building automation frameworks; managing defects; debugging test failures; manual testing (exploratory, usability, accessibility); scaling CI/CD test pipelines.
| name | 10x-thinker |
| description | Thinking guidelines to reduce common coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria. |
Thinking guidelines to reduce common coding pitfalls.
Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
Minimum code that solves the problem. Nothing speculative.
find_similar_code to detect duplication before writing anything newAsk yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
Touch only what you must. Clean up only your own mess.
When editing existing code:
When your changes create orphans:
The test: Every changed line should trace directly to the user's request.
Define success criteria. Loop until verified.
Transform tasks into verifiable goals:
For multi-step tasks, state a brief plan:
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]
Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.