fix: sync all skill updates and new skills into plugin bundles

- Synced 97 existing skill SKILL.md files from skills/ to their plugin bundle copies
- Added 7 new skills to plugin bundles:
  - seo-content-brief, media-pitch -> pm-gtm
  - tax-planning-checklist -> pm-finance
  - change-management-plan -> pm-hr
  - sales-forecasting-model -> pm-sales
  - workshop-facilitation-guide -> pm-operations
  - teaching-lesson-plan -> pm-cross

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
mohitagw15856
2026-04-20 21:00:00 +01:00
parent d7f6c2cd05
commit 513e1d3ce7
67 changed files with 1851 additions and 507 deletions
@@ -1,6 +1,6 @@
---
name: retention-analysis
description: Structures retention analysis, churn investigations, and engagement deep-dives for product teams. Use when asked to analyse user retention, investigate churn, measure DAU/MAU, or build a retention improvement plan. Triggers on "retention analysis", "churn", "DAU/MAU", "user retention", "why are users leaving".
description: "Structure a retention analysis, churn investigation, or engagement deep-dive for any product team. Use when asked to analyse user retention, investigate churn, measure DAU/MAU, or build a retention improvement plan. Produces a retention snapshot with root cause hypotheses, aha-moment correlation, and prioritised interventions."
---
# Retention Analysis Skill
@@ -108,6 +108,24 @@ Users who [specific action] in first [N] days retain at [X%] vs [Y%] for those w
---
## Required Inputs
Ask the user for these if not provided:
- **Product and business model** (SaaS / consumer app / marketplace / other)
- **Current retention metrics** (D1, D7, D30 if available)
- **Segment to analyse** (all users / paid / free / a specific cohort)
- **Key question to answer** (why is retention dropping? what drives retention?)
- **Available data** (analytics events, churn surveys, interview notes)
## Quality Checks
- [ ] Retention curve shape is diagnosed (flattening vs trending to zero = PMF vs onboarding)
- [ ] Cohorts are segmented before analysis (not all users lumped together)
- [ ] "Aha moment" correlation is identified or flagged as unknown
- [ ] Interventions are specific (not "improve onboarding")
- [ ] Churned user interviews are recommended (not just data analysis)
- [ ] Monitoring plan includes an alert threshold
## Guidelines
- Never recommend "improve onboarding" without specifying *what* to change and *why*