营销安装
- 作者仓库星标 5,641
- 作者更新于 实时读取
- 作者仓库 claude-ads
- 领域
- 工程开发
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @AgriciDaniel · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- 未声明（默认跨平台）
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。
需要注意： 未限定 allowed-tools，默认拥有全部工具权限。
---
name: ads-linkedin
description: LinkedIn Ads deep analysis for B2B advertising. Evaluates 27 checks across technical setup, audi…
category: 工程开发
runtime: 无特殊运行时
---
# ads-linkedin 输出预览
## PART A: 任务判断
- 适用问题：代码实现、重构、调试或代码审查。
- 输入要求：目标材料、限制条件、期望输出和验收方式。
- 证据边界：围绕“Process / What to Analyze / Technical Setup (25% weight)”读取原文规则，不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断：确认你的需求是否属于代码实现、重构、调试或代码审查，并标出输入、限制和预期结果。
- **02** 执行计划：优先按“Process / What to Analyze / Technical Setup (25% weight)”拆成步骤，说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果：给出可复制的命令、文件改动、检查清单或内容草稿，并说明如何继续迭代。
- **04** 风险边界：结合 读取文件、写入/修改文件、执行终端命令、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令；主要在本地完成；通常不需要额外 API Key。
- 先小样例验证，再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 先确认触发方式
原文没有稳定的斜杠命令要求。安装验证后通常全局生效，直接在对话里点名这个 Skill 并描述任务即可。
给清楚输入和边界
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是：读取文件、写入/修改文件、执行终端命令。
小样例验证后再放大
先用一个小任务确认它会围绕“Process / What to Analyze / Technical Setup (25% weight)”工作；涉及文件或命令时，先看 diff、日志、预览或测试结果。
复核后再交付
检查最终产物是否包含明确结果、必要证据和下一步动作；如果输出泛泛而谈，就补充输入、边界和验收标准后重跑。
---
name: ads-linkedin
description: LinkedIn Ads deep analysis for B2B advertising. Evaluates 27 checks across technical setup, audi…
category: 工程开发
source: AgriciDaniel/claude-ads
---
# ads-linkedin
## 什么时候使用
- 把工程方向的常用动作沉淀成 Agent 可调用的技能 适合处理工程开发场景下的代码实现、调试、重构、测试或代码审查，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代…
- 面向代码实现、重构、调试或代码审查，优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Process / What to Analyze / Technical Setup (25% weight)」组织步骤，不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令；主要在本地完成；通常不需要额外 API Key。
- 先跑小样例，确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown，不编造命令、平台或依赖。 证据边界与执行链路
作者原文负责流程事实；仓库文件负责来源和命令；流狐只补充适用场景、限制和质量判断。
skill "ads-linkedin" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Process / What to Analyze / Technical Setup (25% weight)
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件、执行终端命令 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
}LinkedIn Ads Deep Analysis
Terminology note (Oct 2025): Campaign Groups are now called Campaigns, and Campaigns are now called Ad Sets. This skill uses the new terminology.
Process
- Collect LinkedIn Ads data (Campaign Manager export, Insight Tag status)
- Read
ads/references/linkedin-audit.mdfor full 27-check audit - Read
ads/references/benchmarks.mdfor LinkedIn-specific benchmarks - Read
ads/references/scoring-system.mdfor weighted scoring - Evaluate all applicable checks as PASS, WARNING, or FAIL
- Calculate LinkedIn Ads Health Score (0-100)
- Generate findings report with action plan
What to Analyze
Technical Setup (25% weight)
- Insight Tag installed and firing on all pages (L01)
- Conversions API (CAPI) active, launched 2025 (L02)
- Conversion events configured for full funnel
- Revenue attribution tracking enabled
- Salesforce/HubSpot CRM integration (June 2025) enables closed-loop impression-to-revenue reporting
Audience Targeting (25% weight)
- Job title targeting uses specific titles, not just functions (L03)
- Company size filtering matches ICP (L04)
- Seniority level appropriate for offer (L05)
- Matched Audiences active: retargeting + contact lists (L06)
- ABM company lists uploaded (up to 300,000 companies) (L07)
- Audience expansion OFF for precision campaigns, ON for scale (L08)
- Predictive audiences tested, replaced Lookalikes Feb 2024 (L09)
Creative Quality (20% weight)
- Thought Leader Ads active, ≥30% budget allocation for B2B (L10)
- Ad format diversity: ≥2 formats tested (L11)
- Video ads tested (L12)
- Creative refresh every 4-6 weeks (L13)
Lead Gen & Performance (15% weight)
- Lead Gen Form ≤5 fields (13% CVR benchmark) (L14)
- Lead Gen Form synced to CRM in real-time (L15)
- Campaign objective matches funnel stage (L18)
- A/B testing active: creative or audience (L19)
- Message ad frequency ≤1 per 30-45 days (L20)
Bidding & Budget (15% weight)
- Bid strategy: Start with Manual CPC. Maximum Delivery is the most expensive option. (L16)
- Daily budget ≥$50 for Sponsored Content (L17)
- CTR ≥0.44% for Sponsored Content (L21)
- CPC within benchmark: $5-7 average, senior $6.40+ (L22)
- Lead-to-opportunity rate tracked, not just CPL (L23)
- Attribution: 30-day click / 7-day view configured (L24)
- Demographics report reviewed monthly (L25)
Thought Leader Ads (TLA) Assessment
Thought Leader Ads use employee/executive personal posts as sponsored content. Non-employee members eligible since March 2025. 2-5x higher engagement than standard Sponsored Content.
- CPC typically $2.29-$4.14 vs $13.23 for standard Sponsored Content
- CTR typically 2-3x higher than corporate-branded ads
- 2-5x higher engagement (includes non-employee member TLAs since March 2025)
- Best for: B2B thought leadership, brand awareness, engagement
Evaluate:
- Are TLAs being used? (If not, HIGH priority recommendation)
- Are they getting ≥30% of total LinkedIn budget?
- Are the right employees selected (industry credibility, active posters)?
- Is post content authentic and valuable (not salesy)?
Ad Format Benchmarks
| Format | Key Metric |
|---|---|
| Document Ads | 7.00% engagement rate |
| Conversation Ads | 50-60% open rate |
Note: EU Sponsored Messaging (InMail/Conversation Ads) discontinued since Jan 2022.
LinkedIn Audience Network
Expert consensus is OFF. Quality is poor, and it dilutes campaign performance data. Disable LinkedIn Audience Network unless specifically testing with isolated budget.
ABM Strategy Assessment
For B2B Enterprise accounts:
- Company list uploaded and segmented by tier (Tier 1, 2, 3)
- Custom content per tier (personalized messaging)
- Account penetration tracking (contacts reached per target account)
- Integration with CRM/ABM platform (Demandbase, 6sense, etc.)
LinkedIn Context
| Setting | Value |
|---|---|
| Minimum audience size | 500 (for ads to run) |
| Lead Gen Form CVR benchmark | 13% |
| TLA CPC range | $2.29-$4.14 |
| Standard SC CPC | $13.23 average |
| Hierarchy rename | Oct 2025 (Campaign Group → Campaign → Ad) |
| Predictive Audiences | Replaced Lookalikes Feb 2024 |
Key Thresholds
| Metric | Pass | Warning | Fail |
|---|---|---|---|
| CTR (Sponsored Content) | ≥0.44% | 0.30-0.44% | <0.30% |
| CPC (average) | ≤$7.00 | $7-10 | >$10.00 |
| Lead Gen CVR | ≥10% | 5-10% | <5% |
| Message frequency | ≤1/30 days | 1/15-30 days | >1/15 days |
| TLA budget share | ≥30% | 15-30% | <15% |
Output
LinkedIn Ads Health Score
LinkedIn Ads Health Score: XX/100 (Grade: X)
Technical Setup: XX/100 ████████░░ (25%)
Audience: XX/100 ██████████ (25%)
Creative: XX/100 ███████░░░ (20%)
Lead Gen: XX/100 █████░░░░░ (15%)
Budget & Bidding: XX/100 ████████░░ (15%)Deliverables
LINKEDIN-ADS-REPORT.md: Full 27-check findings with pass/warning/fail- TLA adoption roadmap (if not using)
- ABM strategy recommendations (for B2B)
- Lead Gen Form optimization priorities
- Quick Wins sorted by impact
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核