技能详情（站内镜像，无评论）
作者：danyangliu @danyangliu-sandwichlab
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 1 · 206 · 0 current installs · 0 all-time installs
⭐ 1
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：danyangliu-sandwichlab/creative-performance-analyzer
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
Instruction-only skill that provides creative-analysis templates and decision rules; it does not request credentials, install code, or access external systems automatically.
目的
The name/description say it will analyze creative performance across multiple ad platforms; the SKILL.md supplies decision rules, input/output contracts, and actionable plans. The skill is instruction-only (no code, no env vars), so its ability to 'analyze' depends on user-supplied data rather than automatic access to platform APIs — this is coherent but important to understand.
说明范围
Runtime instructions are limited to asking for campaign/product inputs, generating creative plans, QA checks, and escalation guidance. The SKILL.md does not instruct reading local files, environment variables, or calling external endpoints beyond normal output, so it stays within its stated purpose.
安装机制
No install spec and no code files are present. No binaries or downloads are requested, so there is nothing written to disk or executed by the skill at install time.
证书
The skill requests no environment variables, credentials, or config paths. This is proportionate for an instruction-only advisory tool; however, note that direct platform integration would normally require API credentials and an install mechanism, which are intentionally absent here.
持久
always is false (default) and the skill does not request persistent system privileges or modify other skills. It can be invoked by the agent normally; there is no indication of elevated persistence or cross-skill access.
综合结论
This skill is a template-driven advisor — it will not fetch data from Meta, TikTok, Google, Amazon, or other ad platforms on its own. If you expect automatic data pulls or live reports, this skill does not provide them (and would need explicit API credentials and an install mechanism to do so). Before using: (1) Do not paste production credentials into free-text prompts — the skill does not request them. (2) Test the skill with non-sensitive s…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Ads Creative Performance」。简介：Analyze creative performance post-launch across Meta (Facebook/Instagram), TikT…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/danyangliu-sandwichlab/creative-performance-analyzer/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
---
name: creative-performance-analyzer
description: Analyze creative performance post-launch across Meta (Facebook/Instagram), TikTok Ads, YouTube Ads, Google Ads, and Amazon Ads inventory.
---
# Ads Creative Performance
## Purpose
Core mission:
- winner loser detection, fatigue signals, next-test matrix
This skill is specialized for advertising workflows and should output actionable plans rather than generic advice.
## When To Trigger
Use this skill when the user asks for:
- ad execution guidance tied to business outcomes
- growth decisions involving revenue, roas, cpa, or budget efficiency
- platform-level actions for: Meta (Facebook/Instagram), TikTok Ads, YouTube Ads, Google Ads, Amazon Ads
- this specific capability: winner loser detection, fatigue signals, next-test matrix
High-signal keywords:
- ads, advertising, campaign, growth, revenue, profit
- roas, cpa, roi, budget, bidding, traffic, conversion, funnel
- meta, googleads, tiktokads, youtubeads, amazonads, shopifyads, dsp
## Input Contract
Required:
- product_or_offer
- target_audience
- placement_scope
Optional:
- existing_assets
- brand_tone
- prohibited_claims
- creative_constraints
## Output Contract
1. Creative Objective
2. Angle and Hook Set
3. Asset Specification
4. Test Variant Plan
5. Creative QA Notes
## Workflow
1. Anchor creative goal to funnel stage and KPI.
2. Generate angle family and hook variants.
3. Map each angle to placement format requirements.
4. Define variant matrix and test order.
5. Add quality and compliance checkpoints.
## Decision Rules
- If audience is cold, prioritize problem-agitation and proof-first hooks.
- If retargeting stage, prioritize offer clarity and urgency mechanics.
- If format limits are strict, simplify message hierarchy to one CTA.
## Platform Notes
Primary scope:
- Meta (Facebook/Instagram), TikTok Ads, YouTube Ads, Google Ads, Amazon Ads
Platform behavior guidance:
- Keep recommendations channel-aware; do not collapse all channels into one generic plan.
- For Meta and TikTok Ads, prioritize creative testing cadence.
- For Google Ads and Amazon Ads, prioritize demand-capture and query/listing intent.
- For DSP/programmatic, prioritize audience control and frequency governance.
## Constraints And Guardrails
- Never fabricate metrics or policy outcomes.
- Separate observed facts from assumptions.
- Use measurable language for each proposed action.
- Include at least one rollback or stop-loss condition when spend risk exists.
## Failure Handling And Escalation
- If critical inputs are missing, ask for only the minimum required fields.
- If platform constraints conflict, show trade-offs and a safe default.
- If confidence is low, mark it explicitly and provide a validation checklist.
- If high-risk issues appear (policy, billing, tracking breakage), escalate with a structured handoff payload.
## Code Examples
### Creative Brief Example
creative_id: CR-001
angle: pain_to_outcome
hook: "Stop wasting ad budget in week one"
formats: [9:16_video, 1:1_image]
### Variant Matrix
V1: hook_change
V2: CTA_change
V3: visual_proof_change
## Examples
### Example 1: New hook generation
Input:
- Existing creatives have high frequency fatigue
- Need fresh top-funnel hooks
Output focus:
- new angle families
- hook library
- test priorities
### Example 2: Asset adaptation by placement
Input:
- One hero concept, multiple platforms
- Need format-safe variations
Output focus:
- per-platform format specs
- copy-length adaptation
- QA checklist
### Example 3: Pre-launch creative scoring
Input:
- 12 creatives pending launch
- Limited review bandwidth
Output focus:
- quality scores
- reject/rework decisions
- launch candidate shortlist
## Quality Checklist
- [ ] Required sections are complete and non-empty
- [ ] Trigger keywords include at least 3 registry terms
- [ ] Input and output contracts are operationally testable
- [ ] Workflow and decision rules are capability-specific
- [ ] Platform references are explicit and concrete
- [ ] At least 3 practical examples are included