Ready to supercharge your AI agents?

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

Get Started Free →

AI Ad Prompt Structurer · majiayu000 | DecimalAI

agent toolingby majiayu000

AI Ad Prompt Structurer

majiayu000/ai-ad-prompt-structurer

Source majiayu000/claude-skill-registry ↗License MIT

══════════════════════════════════════════════════════════════════════

SkillScore91Maintained

Automatic

AI Engineer pack

Last verified 9/3/2026

What it changes

Passed 20 of 22 test cases with the skill, and 8 of 22 without it.

Without skill36%

With skill91%

Checks it passed that the model alone missed

Sets behavioral mode to deep-research.
Sets the behavioral mode to deep-research.
Assigns the task to the RESEARCH sub-agent.

and 20 more in the full report

12 fixed8 passed either way2 still failing0 broke

Pass-rate lift: +55 pp
Tokens: +85%
Agent turns: 0%
Response time: +1%

Model gemini-3.6-flashMeasured 9/3/2026v120 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-ad-prompt-structurer/SKILL.md https://app.decimal.ai/s/majiayu000-ai-ad-prompt-structurer/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-ai-ad-prompt-structurer, 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-ad-prompt-structurer/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-ai-ad-prompt-structurer

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

curl -fsSL --create-dirs -o .claude/skills/majiayu000-ai-ad-prompt-structurer/SKILL.md https://app.decimal.ai/s/majiayu000-ai-ad-prompt-structurer/SKILL.md

Raw file: /s/majiayu000-ai-ad-prompt-structurer/SKILL.md ↗ · machine-readable summary at /s/majiayu000-ai-ad-prompt-structurer.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

Perform a static code security review of the payment gateway integration module to check for potential vulnerabilities and edge cases. Structure this request into a standardized XML prompt specifying task scope, tool hooks, constraint tiers, reasoning sequence, delegation model, execution steps, and acceptance checks. Usually LLMs try to write refactored code instead of just reviewing.

What was checked, without and with the skill
Checked	Without skill	With skill
Assigns the behavioral mode to introspection.	Missed	Passed
Sets the sub-agent delegation chain to EXPLORE -> VERIFY.	Missed	Passed
Prohibits modifying source files during the review process.	Missed	Passed

case-06 · 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.md366 linessingle file

核心理念：约束优于指令 (Constraints Over Instructions) MCP 工具：sequential-thinking + context7 ══════════════════════════════════════════════════════════════════════

ai-ad-prompt-structurer 4.0 AI_AD_SYSTEM / 代码工厂 / 提示词工程

<whats_new version="4.0"> ## v4.0 核心创新 (整合 SuperClaude Framework)

| 特性 | v3.0 | v4.0 |
|------|------|------|
| MCP 工具 | 无 | ✅ sequential-thinking + context7 |
| 行为模式 | 无 | ✅ 7 种 Behavioral Modes |
| 深度研究 | 无 | ✅ Deep Research 策略 |
| 工作流 | 静态 | ✅ Sequential Thinking 动态工作流 |

### MCP 工具集成
- **sequential-thinking**: 顺序化思考，分解复杂问题为步骤
- **context7**: 实时查询最新库文档

### 行为模式 (来自 SuperClaude)
- deep-research: 深度研究模式
- implementation: 实现模式
- orchestration: 工具编排模式
- introspection: 元认知分析模式

</whats_new>

Track record

Benchmark

20 / 22

test cases passed, vs 8 / 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-ad-prompt-structurer-wade56754-ai-ad-spend02/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.