메뉴
Apply the retention decision matrix to a classified cohort and produce per-subscription recommendations (discount, pause, downgrade, human_triage, standard_offer, accept). Run after cancel reasons are classified.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Show Annual Recurring Revenue with QoQ and YoY trend and a growth trajectory. Use when the user asks about ARR, annual recurring revenue, annual run rate, or year-over-year revenue growth. Do NOT use for MRR, NRR, or monthly breakdowns.
Identify overdue invoices most likely heading toward write-off, while a save is still possible. Use when the user asks about bad debt, write-off risk, invoices unlikely to be recovered, or wants to see which AR is at risk of becoming bad debt. Do NOT use for general overdue lists or collections prioritisation.
List subscriptions whose payment card expires in the next 30 or 60 days, ranked by MRR at risk. Use when the user asks about expiring cards, cards about to expire, or wants to prevent involuntary churn from payment method expiry. Do NOT use for current payment failures or dunning analysis.
Show the full product catalog: all products, their plans with pricing and billing frequency, addons, and one-time items. Use when the user asks what plans are available, wants to see the product catalog, pricing, or available addons and items. Do NOT use for subscription status, customer-specific data, or coupon lookup.
Decompose churn into voluntary (customers who chose to leave) vs involuntary (failed payments) and identify which plans and products are driving losses. Use when the user asks why customers are churning, churn composition, voluntary vs involuntary split, or which products have the highest cancellation rate. Do NOT use for MRR, NRR, or retention rate questions.
Daily AR worklist: top 20 overdue invoices ranked by recovery probability (outstanding amount × payment-behaviour score). Use when the user asks who to chase for payments today, wants a collections prioritisation, or needs a daily AR action list. Do NOT use for aggregate overdue totals or bad-debt analysis.
| name | offer-recommender |
| description | Apply the retention decision matrix to a classified cohort and produce per-subscription recommendations (discount, pause, downgrade, human_triage, standard_offer, accept). Run after cancel reasons are classified. |
Applies config/retention-matrix.yaml (pre_churn_matrix or win_back_matrix) to the classified cohort. No API calls — pure rule evaluation, deterministic, re-runnable when YAML changes.
recommendation object appended per row{
"action": "discount",
"params": { "percent": 25, "duration_months": 3 },
"rationale": "High-LTV, price objection — aggressive discount preserves long-term value",
"rule_index": 0,
"ltv_tier": "high",
"ltd_tier": "veteran"
}
Supported actions: discount, pause, downgrade, human_triage, standard_offer, accept.
1. Run the matrix script:
python <skill-path>/scripts/apply_matrix.py \
--cohort <workspace>/retention-runs/<DATE>/cohort-<type>-classified.json \
--matrix <workspace>/config/retention-matrix.yaml \
--cohort-type <pre_churn|post_churn> \
--output <workspace>/retention-runs/<DATE>/cohort-<type>-recommendations.json
Script logic: buckets ltv (USD) and ltd (days) into tiers from the YAML, walks matrix rules top-to-bottom, first matching rule wins. An empty match: {} is a catch-all — every matrix should end with one.
2. Inspect summary output for:
human_triage → new reason bucket not covered by matrix rules.rule_index: -1 rows → no catch-all; stop pipeline and tell the user.3. Show the user action-count summary and a top-5 high-MRR preview table. Confirm output path.
0, buckets as low/new; catch-all handles it.rule_index: -1; flag and stop.