← 返回 Skills 市场
DTC Helper
作者
danyangliu
· GitHub ↗
· v1.0.0
287
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install dtc-ads-helper
功能描述
Diagnose DTC ads performance across Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, and Shopify Ads by validating pixel attribution, account...
使用说明 (SKILL.md)
DTC Helper
Purpose
Core mission:
- Validate pixel and attribution readiness for OCPX-style optimization.
- Analyze account structure and creative performance to explain ROAS volatility.
- Provide scale path and budget lift recommendations.
- Output landing page and conversion funnel optimization actions.
When To Trigger
Use this skill when the user asks for:
- DTC store growth troubleshooting
- ROAS instability diagnosis
- scaling strategy after initial traction
- landing page and funnel optimization for paid traffic
High-signal keywords:
- dtc, ecommerce, shop, checkout, conversion
- roas, cpa, budget, scale, optimize
- pixel, tracking, attribution, campaign
Input Contract
Required:
- store_url
- platform_account_snapshot
- pixel_event_snapshot
- recent_performance_window
Optional:
- creative_report
- landing_page_metrics
- cohort_ltv
- inventory_constraints
Output Contract
- Pixel and Attribution Readiness Verdict
- ROAS Volatility Root-Cause Tree
- Scale Path and Budget Lift Plan
- Landing Page and Funnel Fixes
- Execution Priority Queue
Workflow
- Check event completeness for core commerce events.
- Audit campaign/adset/ad structure and budget fragmentation.
- Compare creative performance by funnel stage.
- Diagnose ROAS swings by channel, offer, and audience.
- Produce scale-safe budget and funnel actions.
Decision Rules
- If Purchase event quality is low, pause aggressive scale and fix tracking first.
- If creative fatigue is detected, prioritize new hooks before raising budget.
- If funnel CVR is below threshold, route spend to best-converting LP first.
- If LTV is unknown, avoid over-bidding on upper-funnel traffic.
Platform Notes
Primary scope:
- Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, Shopify Ads
Platform behavior guidance:
- Meta/TikTok for creative-led demand creation.
- Google for intent capture and bottom-funnel efficiency.
- Shopify events must stay consistent with platform conversion definitions.
Constraints And Guardrails
- Do not infer profitability without COGS or contribution assumptions.
- Mark attribution blind spots explicitly.
- Keep scale recommendations bounded by measurement confidence.
Failure Handling And Escalation
- If pixel data is incomplete, output tracking repair plan first.
- If account permission blocks data access, provide minimum data request packet.
- If severe policy risk exists, route to Ads Compliance Review.
Code Examples
OCPX Readiness Check (YAML)
required_events:
- ViewContent
- AddToCart
- InitiateCheckout
- Purchase
event_quality_threshold: high
readiness: conditional
ROAS Volatility Slice (JSON)
{
"window": "last_14d",
"worst_segment": "retargeting-video-1",
"roas_drop_pct": 31,
"suspected_causes": ["creative_fatigue", "audience_overlap"]
}
Examples
Example 1: Sudden ROAS drop
Input:
- DTC store ROAS down 25% in 10 days
Output focus:
- root-cause breakdown
- quick stabilizing actions
- budget protection rules
Example 2: Scale decision
Input:
- Profitable baseline, wants 2x spend
Output focus:
- safe scaling ladder
- creative replacement cadence
- funnel readiness checklist
Example 3: LP conversion issue
Input:
- CTR stable, CVR down
Output focus:
- LP diagnosis
- checkout friction fixes
- retest plan
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
安全使用建议
This skill appears internally consistent and low-risk in itself, but it relies on you providing snapshots of ad accounts and tracking data. Before sharing anything: (1) do not paste live access tokens, passwords, or API keys—provide sanitized snapshots or exports instead; (2) remove any unrelated PII or billing details from exported data; (3) if you want the skill to run against live accounts (automation), expect it would need explicit API keys/permissions—ask for details and a justification before granting access; and (4) verify any human reviewer or consultant you share account exports with has appropriate access controls.
功能分析
Type: OpenClaw Skill
Name: dtc-ads-helper
Version: 1.0.0
The skill bundle defines a legitimate AI agent task for diagnosing DTC ad performance. The `SKILL.md` provides clear instructions, input/output contracts, and workflow details without any evidence of prompt injection attempts, malicious commands, data exfiltration, or other harmful behaviors. All files are standard metadata or descriptive content, aligning with the stated purpose.
能力评估
Purpose & Capability
Name and description (DTC ads diagnosis across multiple ad platforms) match the declared inputs (store_url, platform_account_snapshot, pixel_event_snapshot, performance window) and the described outputs (pixel readiness, ROAS root causes, scale plan). Required artifacts are reasonable for this purpose.
Instruction Scope
SKILL.md contains step-by-step checks (event completeness, campaign structure, creative analysis, funnel fixes) and failure handling that stay within ad-diagnostic scope. It does not instruct the agent to read system files, environment variables, or reach out to unknown endpoints; it expects the user to supply snapshots when needed.
Install Mechanism
No install spec or code files are included; the skill is instruction-only, so nothing is written to disk or fetched at install time. This minimizes installer risk.
Credentials
The skill declares no environment variables, credentials, or config paths. Inputs are explicit (snapshots and URLs) and align with the diagnostic task. There is no unexplained request for tokens, keys, or unrelated secrets.
Persistence & Privilege
always is false and the skill does not request persistent system-level presence or attempts to modify other skills or agent configuration. Autonomous invocation is allowed (platform default) but not combined with elevated privileges.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install dtc-ads-helper - 安装完成后,直接呼叫该 Skill 的名称或使用
/dtc-ads-helper触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of dtc-ads-helper.
- Diagnose DTC ads performance across Meta, Google Ads, TikTok Ads, YouTube Ads, and Shopify Ads.
- Validates pixel attribution, account structure, creative signals, and conversion funnel opportunities.
- Provides actionable outputs including ROAS root cause analysis, scale and budget recommendations, and landing page/funnel optimization steps.
- Includes clear input/output contracts, decision rules, and workflow for troubleshooting DTC growth and ROAS instability.
- Offers practical examples and quality checklist for skill deployment.
元数据
常见问题
DTC Helper 是什么?
Diagnose DTC ads performance across Meta (Facebook/Instagram), Google Ads, TikTok Ads, YouTube Ads, and Shopify Ads by validating pixel attribution, account... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 287 次。
如何安装 DTC Helper?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install dtc-ads-helper」即可一键安装,无需额外配置。
DTC Helper 是免费的吗?
是的,DTC Helper 完全免费(开源免费),可自由下载、安装和使用。
DTC Helper 支持哪些平台?
DTC Helper 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 DTC Helper?
由 danyangliu(@danyangliu-sandwichlab)开发并维护,当前版本 v1.0.0。
推荐 Skills