smkalami/prompt-decorators

Prompt Decorators are structured prefixes, such as +++Reasoning and +++StepByStep, designed to enhance AI responses. Inspired by Python decorators, they make AI outputs more logical, accurate, and well-organized without requiring lengthy instructions, simplifying interactions for users.

50
/ 100
Established

Structured prompts using scoped control markers (e.g., `+++Reasoning`, `+++Brainstorm`) that compose into modular cognitive workflows without model retraining. The framework separates decorators into cognitive (reasoning, exploration, critique) and expressive (formatting, memory management) families, with persistent or single-message scope via `+++ChatScope` and `+++MessageScope`. Works platform-agnostically with any LLM by loading a definition file once per session, enabling stacking of arbitrary decorators to chain reasoning, refinement, and validation steps.

462 stars.

No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

462

Forks

56

Language

License

MIT

Last pushed

Oct 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/smkalami/prompt-decorators"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.