Prompt Master Java Edition
Paste the following prompt into your AI chat to install this skill:
Follow https://skillhub.cn/install/skillhub.md to install @user_5d00e27d/majia-system-prompt-java into your AI assistant.
About this skill
Problem It Solves
Vague prompts sent directly to LLMs often drift off direction, produce wrong formats, and require repeated refinement. Prompt Master Java Edition treats the gap between user intent and executable instruction as a pipeline: check safety first, assess intent granularity, then route work into M1 through M5 modes to reduce uncertainty from one-shot prompts.
How It Works
- Safety first: intercepts prohibited or risky requests before generation.
- Intent triage: classifies requests as rough, partial, or clear to decide whether M1 research is needed.
- Mode routing: selects research, template reuse, creative generation, analysis, or workflow orchestration.
- Output gating: uses
PASS / WARN / BLOCKconfidence labels before results can enter cache. - Local cache: reuses user preference packs for familiar domains to avoid repeated context costs.
Where It Fits
Useful in Java systems that need stable prompt drafting, documentation, analysis, or planning outputs. It does not replace domain experts and should keep human review for sensitive, highly regulated, or high-stakes conclusions.
Use Cases
- Integrate DeepSeek in a Java service to turn vague customer requests into executable prompts with PASS or WARN status.
- Serve text-to-image, code, and document generation through Spring Boot REST, asking for Word, txt, or md.
- Reuse cached user preference packs for repeat tasks to build shorter contexts and continue generation.
- Trigger M1 research when requests are vague, classify by generation, analysis, advice, or lookup, then route M1-M5.
Best For
- Java backend engineers integrating LLMs who need stable prompts and output status from vague business requests.
- AI workspace team leads who need M1 research, confidence labels, RAG, and local cache behavior.
- Product engineers building text-to-image or code assistance who need format checks and mode routing.
- Application owners maintaining enterprise outputs who need safety checks, replacement, and refusal logic.
Related Skills
A free matrix publishing assistant for Skill developers, guiding distribution to Tencent SkillHub, XiaLiao, XiaYou SkillHub, GitHub, and ClawHub with create, update, and delete safeguards.
A guide for writing Seedance 2.0 video prompts, covering @ references, camera moves, time segments, audio direction, and common pitfalls.
Collects daily conversations, task logs, and errors, then runs a nine-module review to surface blind spots, generate actions, and update memory.
Local long-term memory for AI agents that appends key facts and daily logs, supports cross-session context and search recall, and auto-archives old diaries to gzip files.