메뉴
Design a comprehensive event tracking plan for product analytics. Outputs event taxonomy, tracking spec, implementation guide, and governance process.
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/kalilurrahman/kr-claudiator-skills --skill event-tracking-plan명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SOC 직업 분류 기준
SKILL.md 표시 중
| name | event-tracking-plan |
| description | Design a comprehensive event tracking plan for product analytics. Outputs event taxonomy, tracking spec, implementation guide, and governance process. |
| argument-hint | ["product type","analytics platform","team structure","current tracking gaps"] |
| allowed-tools | Read, Write |
An event tracking plan defines what user actions to track, how to name them, what properties to capture, and who owns each event. Without a plan, teams end up with thousands of inconsistently named events that nobody trusts. With one, analytics becomes the shared language of product decisions.
Format: {object}_{action}
Object: the thing being acted on (lowercase, singular)
Action: what happened (past tense verb, lowercase)
Examples:
page_viewed — User viewed a page
product_clicked — User clicked on a product
cart_item_added — Item added to cart
checkout_started — Checkout flow started
order_completed — Order placed successfully
account_created — New account registered
feature_used — Feature was used (be more specific when possible)
Anti-patterns:
✗ click_product — action before object
✗ productClicked — camelCase (use snake_case)
✗ buttonClick — too generic (which button?)
✗ trackEvent — not meaningful
// Segment / Amplitude / Mixpanel event spec
// LIFECYCLE EVENTS
analytics.track('account_created', {
user_id: string,
signup_method: 'email' | 'google' | 'github',
referral_source: string | null,
plan_type: 'free' | 'pro' | 'enterprise',
});
analytics.track('session_started', {
session_id: string,
user_id: string | null, // null for anonymous
platform: 'web' | 'ios' | 'android',
entry_page: string,
utm_source: string | null,
utm_campaign: string | null,
});
// ENGAGEMENT EVENTS
analytics.track('feature_used', {
feature_name: string, // Specific feature slug
context: string, // Where in the app
user_id: string,
is_first_use: boolean,
});
analytics.track('search_performed', {
query: string, // Normalised (no PII)
result_count: number,
filters_applied: string[],
source: 'header' | 'page' | 'modal',
});
// CONVERSION EVENTS
analytics.track('checkout_started', {
user_id: string,
cart_item_count: number,
cart_total_usd: number,
source: 'cart_page' | 'buy_now',
});
analytics.track('order_completed', {
order_id: string,
user_id: string,
order_total_usd: number,
item_count: number,
payment_method: 'card' | 'paypal' | 'apple_pay',
is_first_order: boolean,
coupon_used: boolean,
});
## Event: checkout_started
**Description:** Fires when user initiates the checkout flow from any entry point.
**Trigger:** User clicks "Checkout" button, cart is non-empty.
**Owner:** @product-checkout-pm
**Status:** Active
**First added:** 2024-01-15
**Last updated:** 2024-03-01
### Properties
| Property | Type | Required | Example | Notes |
|----------|------|----------|---------|-------|
| user_id | string | yes | "usr_abc123" | Anonymous: session_id |
| session_id | string | yes | "sess_xyz789" | |
| cart_item_count | integer | yes | 3 | |
| cart_total_usd | number | yes | 59.99 | Before tax/shipping |
| source | string | yes | "cart_page" | cart_page, product_page, mini_cart |
| has_coupon | boolean | no | false | |
| is_mobile | boolean | yes | false | |
### Example Payload
```json
{
"event": "checkout_started",
"userId": "usr_abc123",
"properties": {
"session_id": "sess_xyz789",
"cart_item_count": 3,
"cart_total_usd": 59.99,
"source": "cart_page",
"has_coupon": false,
"is_mobile": false
},
"timestamp": "2024-03-15T14:30:00.000Z"
}
## Governance Process
```markdown
## Event Tracking Governance
### Adding a New Event
1. Copy event spec template
2. Submit PR to tracking-plan repo
3. PM + data analyst review
4. Implement and QA in staging
5. Verify in analytics platform before merging
### Deprecating an Event
1. Mark event as `deprecated` in spec
2. Check for active dashboards/queries using this event
3. Announce in #data Slack channel
4. Remove after 90 days with no usage
### Event Naming Review
Monthly review in #tracking-plan channel:
- Inconsistencies flagged
- Deprecated events cleaned up
- New event requests reviewed
### Who Can Add Events
- Any engineer, with PM + data analyst sign-off
- Critical events (conversion, payment) require data team review
| Anti-Pattern | Problem | Fix |
|---|---|---|
| Tracking everything | Event flood; nobody knows what to use | Track decisions you need to make; nothing more |
| Tracking PII in event properties | Privacy violation; GDPR issues | Track user_id; never name, email, or payment details |
| Events not in tracking plan | Unknown events; no documentation | All events must be specced before implementation |
| No QA of events | Events fire with wrong data or not at all | Verify every event in analytics debugger before launch |
| Never deprecating events | 500 events, 400 unused; nobody trusts anything | Deprecation process; clean up quarterly |
The sections below extend this skill into a complete operating playbook so it can run end-to-end inside Claude Code, CoWork, or any agentic tool without further prompting. Pull only the sections you need for a given engagement.
Before producing any output, the skill confirms:
If any of these are missing, the skill asks targeted clarifying questions before generating output. It never invents constraints the user did not state.
The canonical workflow for Event Tracking Plan runs in five stages. Each stage has an explicit exit criterion so the skill knows when to advance.
Stage 1 — Frame. Restate the problem in one paragraph. Name the decision, the deadline, the stakeholders, and the success metric. Surface assumptions explicitly so they can be challenged.
Stage 2 — Diagnose. Inventory the current state with concrete evidence: metrics, quotes, screenshots, configs, tickets. Separate facts from interpretations. Identify the two or three root causes that explain most of the gap, not the long tail of symptoms.
Stage 3 — Design. Generate at least two viable options. For each option, capture: what changes, who owns it, what it costs, what it unblocks, what it risks, and how it could fail. Recommend one with a written rationale.
Stage 4 — Execute. Convert the chosen option into a sequenced plan: milestones, owners, dependencies, gating checks, communication cadence, and rollback triggers. Anything that cannot be assigned an owner and a date is not yet a plan.
Stage 5 — Validate. Define how success will be measured, when the measurement happens, and what action follows each possible result. Schedule the retrospective before the work starts, not after.
Depending on the request, the skill returns one or more of:
Every artifact uses clear headings, short paragraphs, and tables where comparison helps. No filler. No restating the prompt. No hedging language when a recommendation is warranted.
The skill applies the following heuristics when choices are not obvious:
| Anti-pattern | Why it fails | What the skill does instead |
|---|---|---|
| Generic best-practice list with no context | Reader cannot act on it | Tailors recommendations to the stated constraints |
| Recommendation without trade-offs | Hides the cost of being wrong | Names the price paid for the recommendation |
| Plan with no owners or dates | Cannot be executed or tracked | Assigns a named owner and a date to every action |
| Metrics theatre | Measures activity, not outcome | Ties every metric back to the user or business outcome |
| Boil-the-ocean scope | Nothing ships | Cuts scope to the smallest valuable slice |
| Buried recommendation | Reader misses the point | Leads with the recommendation in the first paragraph |
The skill self-checks each output against these gates before returning it:
If any gate fails, the skill rewrites the section before returning it.
Context: Design a comprehensive event tracking plan for product analytics. Outputs event taxonomy, tracking spec, implementation guide, and governance process.
Frame: the team needs a defensible recommendation within five working days; the audience is a cross-functional steering group; the cost of delay is higher than the cost of being slightly wrong.
Diagnose: the dominant constraint is decision latency, not analytical depth. Existing data is sufficient for a directional call.
Design: two viable options surfaced. Option A optimises for speed and reversibility. Option B optimises for completeness but slips the deadline by two weeks.
Execute: Option A recommended. Plan sequenced into a two-week sprint with named owners, a mid-point checkpoint, and a clear rollback trigger.
Validate: success measured against a single leading indicator at day 30 and a single lagging indicator at day 90. Retrospective scheduled for day 35.
A one-shot artifact rarely changes outcomes. The skill recommends a lightweight cadence to keep the work alive: