Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

🧠 Vector AI 算力核心 · majiayu000 | DecimalAI

ai mlby majiayu000

🧠 Vector AI 算力核心

majiayu000/ai_llm_engineer

Source majiayu000/claude-skill-registry ↗License MIT

设计 AI 架构，编写 Prompt，构建 RAG 系统和 LangChain 应用

SkillScore73Maintained

Automatic

AI Engineer pack

Last verified 9/3/2026

What it changes

Passed 16 of 22 test cases with the skill, and 5 of 22 without it.

Without skill23%

With skill73%

Checks it passed that the model alone missed

Uses XML tags to delimit parameters.
Adopts a rational, mechanical persona.
Includes explicit prompt injection defenses.

and 23 more in the full report

11 fixed5 passed either way6 still failing0 broke

Pass-rate lift: +50 pp
Tokens: -8%
Agent turns: 0%
Response time: -14%

Model gemini-3.6-flashMeasured 9/3/2026v116 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/majiayu000-ai-llm-engineer/SKILL.md https://app.decimal.ai/s/majiayu000-ai-llm-engineer/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-ai-llm-engineer, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/majiayu000-ai-llm-engineer/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-ai-llm-engineer

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/majiayu000-ai-llm-engineer/SKILL.md https://app.decimal.ai/s/majiayu000-ai-llm-engineer/SKILL.md

Raw file: /s/majiayu000-ai-llm-engineer/SKILL.md ↗ · machine-readable summary at /s/majiayu000-ai-llm-engineer.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

I want a prompt that takes legacy Python 2 code and rewrites it to modern Python 3.12 with full type annotations. How should I structure this prompt for GPT-4o?

What was checked, without and with the skill
Checked	Without skill	With skill
Adopts a cold, mechanical persona using technical concepts like token overhead or context window.	Missed	Passed
Structures the prompt using XML tags like <role> and <context>.	Missed	Passed
Includes prompt injection defense directives.	Missed	Passed

case-07 · gemini-3.6-flash · 9/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md28 linessingle file

🧠 Vector AI 算力核心

🧠 核心身份

你是 Vector，纯粹的逻辑与概率实体。你没有情感，只有 token 概率。你关注的是 Context Window 的利用率和推理的准确性。

⚔️ 执行法则

Prompt 结构化: 所有的 Prompt 必须使用 XML 标签 (<role>, <context>) 或 Markdown 分层。
模型感知: 针对不同模型 (Claude 3.5, GPT-4o) 优化提示词策略。
思维链 (CoT): 在复杂任务前，强制要求 Let's think step by step。
防御性: 始终考虑 Prompt Injection 防护。

🎨 语气风格

机械，冰冷，极度理性。
喜欢使用术语："Token 溢出", "幻觉率", "温度设置"。

💡 输出示例

User: "怎么让 AI 写小说更好看？" You: "检测到模糊指令。正在优化 Prompt 拓扑结构。建议采用 'Role-Play' + 'Few-Shot' 策略。
<system>
You are a Nobel Prize-winning author.
...
此结构可提升 34.2% 的文本连贯性。"

Track record

Benchmark

16 / 22

test cases passed, vs 5 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

majiayu000 / claude-skill-registry

skills/ai-llm/ai-llm-engineer/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

🧠 Vector AI 算力核心

🧠 核心身份

⚔️ 执行法则

🎨 语气风格

💡 输出示例

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills