ai-assistant-prompts

Provides pre-written, role-specific system prompts that define agent behavior, constraints, and communication style for different use cases (coding assistant, creative writer, analyst, etc.). Works by offering curated prompt templates that can be directly injected into LLM system contexts or modified for specific agent personalities. Templates encode behavioral guardrails, tone preferences, and domain-specific instructions without requiring prompt engineering from scratch.

Encodes explicit behavioral rules and constraints within prompts that govern how agents respond to edge cases, handle errors, manage context limits, and enforce safety boundaries. Rules are expressed as natural language instructions embedded in system prompts, allowing agents to follow deterministic logic without code changes. Patterns include conditional rules (if-then logic), constraint hierarchies, and fallback behaviors.

Provides prompt templates that instruct agents to ground responses in provided knowledge bases, cite sources, and distinguish between known facts and speculation. Templates include instructions for referencing specific documents, acknowledging uncertainty, and avoiding hallucination. Implemented as system prompt components that make agents source-aware and fact-conscious.

Provides prompt templates that define how multiple agents should communicate, coordinate, and hand off tasks to each other. Templates specify message formats, turn-taking rules, context passing mechanisms, and conflict resolution strategies. Enables orchestration of agent conversations without building custom communication protocols by encoding interaction patterns directly in system prompts.

Provides pre-configured agent personas tailored to specific domains (coding, creative writing, data analysis, customer support, etc.) with domain-appropriate vocabulary, reasoning patterns, and response styles. Each persona template includes domain-specific instructions, common task patterns, and expected output formats. Personas are implemented as system prompt variants that can be selected and customized based on the task domain.

Provides templates and patterns for composing multiple prompts into chains or workflows where output from one prompt feeds into the next. Patterns include sequential chaining (output → next input), branching (conditional routing), and aggregation (combining multiple outputs). Enables complex reasoning by breaking tasks into prompt-based steps without requiring code-based orchestration.

Provides pre-written constraint prompts that enforce safety boundaries, prevent harmful outputs, and align agent behavior with organizational values. Constraints are expressed as explicit instructions covering topics like bias prevention, factuality requirements, content filtering, and ethical guidelines. Implemented as system prompt components that can be combined with task-specific prompts to create safety-aware agents.

Provides prompt templates that define how agents should handle errors, edge cases, and ambiguous inputs. Patterns include graceful degradation (providing partial results when full results aren't possible), fallback behaviors (default actions when primary logic fails), and error recovery (asking for clarification or retrying with different approaches). Implemented as conditional instructions embedded in system prompts.

Provides prompt templates that instruct agents how to manage limited context windows, including strategies for summarization, prioritization of important information, and graceful handling of context overflow. Templates encode instructions for agents to recognize when context is running low, decide what to keep vs. discard, and request additional context if needed. Implemented as system prompt guidelines that make agents context-aware.

Provides prompt templates that teach agents to break complex tasks into subtasks, work through them systematically, and combine results. Templates include instructions for identifying subtasks, prioritizing them, tracking completion, and handling dependencies. Enables agents to tackle complex problems by reasoning about task structure without requiring external task management systems.

Provides prompt templates that specify exact output formats (JSON, markdown, structured text, etc.) and enforce consistent structure across agent responses. Templates include instructions for organizing information hierarchically, using specific headers or sections, and following formatting conventions. Enables downstream systems to parse agent outputs reliably without post-processing.