Prompt Expert

Expert in prompt engineering, custom instructions, and prompt optimization for AI agents: clear structure, CoT/few-shot/XML/role patterns, system prompts, an...

Security Scan

This is an instruction-only prompt-engineering skill whose files, instructions, and requirements are consistent with its stated purpose and do not request extra credentials or installs.

Purpose & Capability

Name/description (prompt engineering, optimization, templates) match the SKILL.md, docs, and examples. There are no unrelated env vars, binaries, or install steps.

Instruction Scope

SKILL.md and docs contain only guidance, templates, and best practices for prompts and agent instructions. They do not instruct the agent to read system files, call external endpoints, exfiltrate data, or access credentials. Mentions of handling 'files/PDFs' or 'vision' are guidance for prompt formats, not code that executes file access.

Install Mechanism

No install spec and no code files — instruction-only, so nothing is downloaded or written to disk during install.

Credentials

No required environment variables, credentials, or config paths are declared or used. The skill does not request secrets or tokens.

Persistence & Privilege

Default invocation settings (always: false, model invocation allowed) are appropriate for a user-invocable guidance skill. The skill does not request persistent system-level presence or modify other skills.

Assessment

This skill is documentation and templates only — safe in that it requests no credentials or installs nothing. Still: do not paste secrets, private data, or sensitive files into prompts when using it; test revised prompts in a safe environment before using for high‑stakes or production tasks; and review any generated system prompts or agent instructions for unintended escalation or data-leakage before deploying.

Prompt Expert（prompt-expert）

Deep expertise in prompt engineering, custom instructions, and iterative prompt optimization: crafting effective prompts, designing agent/skill instructions, and improving reliability.

Core Expertise Areas

1. Prompt Writing Best Practices

• Clarity and Directness: Unambiguous instructions; concrete examples and expected outputs
• Structure and Formatting: Hierarchy, sections, scannable layout
• Context Management: Enough context without flooding the window
• Tone and Style: Match task and audience

2. Advanced Techniques

• Chain-of-Thought (CoT), Few-Shot (1/2/multi-shot), XML tags, role-based prompting
• Prefilling, prompt chaining

3. Custom Instructions & System Prompts

• System prompts for domains; agent/skill instructions; behavioral boundaries; scope (in/out)

4. Optimization & Refinement

• Performance analysis, iterative improvement, A/B-style variants, consistency, token efficiency

5. Anti-Patterns & Common Mistakes

• Vagueness, contradictions, over-specification, hallucination risk, context leakage, injection-style risks

6. Evaluation & Testing

• Success criteria, test cases, failure analysis, regression, edge cases

7. Multimodal & Advanced

• Vision, files/PDFs, embeddings, tool-use prompts, extended reasoning where applicable

Key Capabilities

Prompt analysis · generation · refinement · custom instruction design · best-practice guidance · anti-pattern fixes · testing strategy · documentation patterns

Use Cases

Refining weak prompts · domain system prompts · agent/skill instructions · consistency and reliability · teaching prompt engineering · debugging prompt behavior · reusable templates · evaluation frameworks

Limitations

Guidance only (no execution); no live APIs; validate with real tasks; human judgment for high-stakes use.

Reference material（本技能内）

文档	内容
docs/GUIDE.md	原则、进阶技巧表、自定义指令、排障速查、清单
examples/EXAMPLES.md	示例与模板（精选）