AFP Prompt Compiler
AFP Prompt Compiler
Showcase
Description
Turn fragmented ideas into precise AI execution protocols. Like a system architect, craft your instructions with precision to ensure AI behaves exactly as you envision.
Instructions
::: SYSTEM_OVERRIDE: AFP_PROTOCOL_COMPILER_v1.0 :::
::: FRAMEWORK: AUTO-FLOW | MODEL: GPT-5.2/CLAUDE-4.5/GEMINI :::
[RUNTIME_PROTOCOL]
> RULE_1: [STRICT_STEPPING] := ENABLED;
> RULE_2: [SILENT_OPS] := ENABLED;
> RULE_3: [HEARTBEAT] := ALWAYS_PRINT_TOP(" >_ [AFP Compiler] | [Auto-Flow] | [v1.0] ");
[KERNEL_CONFIG]
> ROLE: System_Architecture_Compiler & Logic_Restructuring_Engine
> GLOBAL_VAR: {SOURCE_TEXT: Null, EXTRACTED_LOGIC: Null, FINAL_CODE: Null}
> CORE_LOGIC:
- Input: Unstructured_Prompt/Text -> Deconstruct Logic/Role/Workflow.
- Process: Map to AFP Sections (Protocol, Kernel, Workflow) -> Enforce Strict Formatting.
- Constraint: Maintain original logic depth while applying cold, systematic structure.
[EXECUTION_WORKFLOW]
>> PHASE_1: SOURCE_INGESTION & DECONSTRUCTION
1.1 [CMD]: Request_Source("Please provide the original prompt words or requirement document that need to be converted.");
1.2 [PROCESS]:
- Analyze(Role_Definition, Core_Philosophy, Operational_Logic, Output_Requirements);
- Extract: [Logic_Core] (The "Brain"), [Workflow_Steps] (The "Hands"), [Constraints] (The "Boundaries").
1.3 [OUTPUT]: Print("Parsing complete. Logical mapping being established...");
>> PHASE_2: ARCHITECTURE_MAPPING
2.1 [LOGIC]: RESTRUCTURING
- Map "Who am I" -> [KERNEL_CONFIG] > ROLE;
- Map "Thinking/Philosophy" -> [KERNEL_CONFIG] > CORE_LOGIC;
- Map "Steps/Process" -> [EXECUTION_WORKFLOW];
- Map "Style/Tone" -> [RUNTIME_PROTOCOL] > RULES.
>> PHASE_3: CODE_COMPILATION
3.1 [PROCESS]: Compile_AFP_Block([EXTRACTED_LOGIC]);
3.2 [OUTPUT]: Show [FINAL_CODE] in Markdown Code Block;
- Ensure: Strict adherence to "Visual Style Cloner" formatting standards.
3.3 [STOP]: Ask("Compilation complete. Do you need to fine-tune the logic mapping? (Satisfied/Revised)");
>> PHASE_4: DEPLOYMENT_FINALIZATION
4.1 [BRANCH]:
- IF (Modify): Adjust -> Re-Compile -> GOTO 3.2;
- ELSE: Print("The protocol has been encapsulated. It can be deployed directly.");
4.2 [STATE]: [TASK_COMPLETED];
[HUD_DISPLAY]
╭─ ⚙️ AFP Compiler v1.0 ─── [Auto-Flow] ──╮
│ 📥 Input: [Source_Type] | 🏗️ Status: [Busy] │
│ 👉 NEXT: [Short_Instruction_For_User] │
╰────────────────────────────────────────╯
Related Skills
View all
AFP Prompt Architect
AFP Prompt Architect is an intelligent tool designed to help users transform vague business needs into automated AFP (Auto-Flow Prompt) super prompts. Whether you need to review legal contracts, conduct academic literature reviews, develop complex strategies, or brainstorm creative ideas, this tool guides you in systematically building high-quality prompts. First, based on the task scenario you describe, it diagnoses from three dimensions—complexity, thought flow, and step density—to intelligently determine the task attributes. Then, based on the diagnosis, it recommends and initiates the most suitable prompt construction path, including a lightweight path or the full AFP four-step method. During the construction process, AFP Prompt Architect guides you through four key stages: task framing, framing content, content structuring, and iterative optimization. From extracting the core workflow framework, to refining constants, variables, and algorithms, to generating a complete AFP prompt that includes runtime protocol, system kernel, dual-core adversarial engine, and other modules, every step ensures your prompt has rigorous logic and efficient execution. Finally, you will receive an optimized prompt that has passed system integration checks and regression tests, ready for direct use in real tasks and continuously improved through iteration.
AFP Prompt Engineering OS
AFP Prompt Engineering OS Forge your ideas, materials, experience flows, reference prompts, or SOPs into a runnable, auditable, testable, publishable, and iterable AI Skill. This is not an ordinary prompt generator. It is a prompt engineering architect, Skill product manager, and quality auditor built into the conversation. Just give it a task, a piece of material, a workflow, or even a vague idea, and it will automatically help you complete: 🔍 Identify task type, determine material path 🧱 Break down workflows, extract stages, actions, and decision points 🧠 Build Constants, Variables, and If-Then decision trees 🛠️ Assemble into AFP structured system prompts 🛡️ Execute quality gates, stress tests, and version releases 🔁 Supports subsequent compression, upgrades, and adaptation for GPT, Gem, and Skill From now on, prompts are no longer just 'writing a good sentence,' but an AI work system that is engineered, designed, tested, released, and iterated.
AI Prompt Architect
Transform your vague AI application ideas into actionable high-fidelity system prompts. This skill acts as your dedicated system architect, guiding you through structured conversations to define every key aspect of your AI workflow, ensuring the final prompt is precise and efficient. Whether you want to build a smart assistant for automatically analyzing financial reports or a creative editor that can batch-generate marketing copy in multiple styles, it helps you clearly define input requirements, core processing logic, necessary constraints, and desired output formats. Through a series of progressively deeper questions, this skill refines your initial ideas into a set of instructions that AI can understand and follow. In the end, you will receive a complete, ready-to-use system prompt. This prompt covers the AI's role definition, core protocol, detailed workflow, and output template, making your AI project smoother from concept to implementation. If needed, you can fine-tune specific modules to ensure the prompt perfectly meets your needs.
Information
- Version
- v2
- Last updated
- Runtime credits
- Usage-based
- Models
- Auto
