Pack Availability Guard
Before telling the user to run a skill from another project-local pack, check .agents/project.json.enabled_packs. If the target pack is not enabled, recommend npx skillpacks install <pack> from the project shell, instead of the target skill.
Retention Map
Invoke as $retention-map.
Map why customers return, what predicts churn, and how the product recovers at-risk users.
Process
0. Product-Path Scope Resolution
Resolve research scope by product path before using code or app structure as a hint:
- If
$ARGUMENTS names a non-archived research/{slug}/ directory or a product-path ID whose scope_path points there, use that path. Treat {slug} as the product/app name, not the ICP, audience, or segment label.
- If
$ARGUMENTS names only research/_archive/{slug}/ or a manifest entry with status: archived or legacy status: abandoned, stop and warn that the path is archived; do not write or update scoped outputs there.
- Read
research/.progress.yaml when present. Normalize legacy active_path to active_paths on read and write back active_paths on manifest updates. Treat legacy abandoned as archived; exclude archived, abandoned, deferred, revisit_candidate, promoted, and any scope_path under research/_archive/ from active target selection.
- If active product paths exist in the manifest, use those paths. If multiple active paths exist, ask which one to target unless this skill explicitly supports cross-path output.
- If no active manifest target exists, list non-archived product directories under
research/, excluding research/_archive/ and dot directories. Auto-select only when exactly one exists; ask when multiple exist.
- If no product directories exist, use flat
research/ single-product mode.
- Detect monorepo/app/package structure only as a secondary hint. Suggest creating a missing
research/{slug}/ product path when code clearly exposes an app, but do not require code or monorepo detection before using research/{slug}/.
When product path {slug} is active, read and write research under research/{slug}/, specs under specs/{slug}/, and treat top-level research/*.md files as flat-mode documents or cross-path summaries.
- Resolve product-path scope using
research/{slug}/ when applicable.
- Read
research/.progress.yaml when present. Normalize active_path (singular legacy) to active_paths (plural list) when reading; treat legacy abandoned as archived and exclude archived/deferred/revisit/promoted paths plus research/_archive/ scopes from active target selection. Scope the retention map to the active product path by default.
- Require
research/journey-map.md; if missing, recommend $journey-map.
- Load journey, onboarding, conversion, transaction, metrics, customer feedback, specs, and product evidence when present.
- Interview and recommend around: repeat-use job, natural frequency, core habit/workflow loop, lifecycle messages, saved state, collaboration, renewal moments, churn triggers, downgrade/cancel paths, winback, support recovery, and leading indicators.
- Present the retention model and risk assumptions before writing.
- Write
research/retention-map.md and research/retention-map-interview.md in flat mode, or research/{slug}/retention-map.md and research/{slug}/retention-map-interview.md when product-path scope is active, after validation.
Output Shape
# Retention Map
> Based on: research/journey-map.md
> Date: YYYY-MM-DD
## Summary
## Repeat-Use Loop
## Lifecycle Triggers
## Healthy Usage Signals
## Churn Triggers
## Recovery And Winback
## Product Gaps
## Next Steps
Alignment Page
Follow the shared alignment-page convention via the packaged convention resolver; output path is alignment/retention-map-{topic}.html.
Constraints
- Do not force habit-loop language onto naturally infrequent or transactional products; document the natural return trigger instead.
- End with
## Next Steps, preferring $expansion-map, $lifecycle-metrics, $hook-model, $customer-feedback, or $cohort-review as context dictates.
Default Shipping Contract
Follow the shared shipping contract convention in CLAUDE.md.
1---2name: retention-map3description: Plan repeat-use loops, lifecycle triggers, churn risks, recovery paths, and retention signals4---5
6## Pack Availability Guard
7
8Before telling the user to run a skill from another project-local pack, check `.agents/project.json.enabled_packs`. If the target pack is not enabled, recommend `npx skillpacks install <pack>` from the project shell, instead of the target skill.
9
10# Retention Map
11
12Invoke as `$retention-map`.
13
14Map why customers return, what predicts churn, and how the product recovers at-risk users.
15
16## Process
17
18### 0. Product-Path Scope Resolution
19
20Resolve research scope by product path before using code or app structure as a hint:
21
221. If `$ARGUMENTS` names a non-archived `research/{slug}/` directory or a product-path ID whose `scope_path` points there, use that path. Treat `{slug}` as the product/app name, not the ICP, audience, or segment label.
232. If `$ARGUMENTS` names only `research/_archive/{slug}/` or a manifest entry with `status: archived` or legacy `status: abandoned`, stop and warn that the path is archived; do not write or update scoped outputs there.
243. Read `research/.progress.yaml` when present. Normalize legacy `active_path` to `active_paths` on read and write back `active_paths` on manifest updates. Treat legacy `abandoned` as `archived`; exclude `archived`, `abandoned`, `deferred`, `revisit_candidate`, `promoted`, and any `scope_path` under `research/_archive/` from active target selection.
254. If active product paths exist in the manifest, use those paths. If multiple active paths exist, ask which one to target unless this skill explicitly supports cross-path output.
265. If no active manifest target exists, list non-archived product directories under `research/`, excluding `research/_archive/` and dot directories. Auto-select only when exactly one exists; ask when multiple exist.
276. If no product directories exist, use flat `research/` single-product mode.
287. Detect monorepo/app/package structure only as a secondary hint. Suggest creating a missing `research/{slug}/` product path when code clearly exposes an app, but do not require code or monorepo detection before using `research/{slug}/`.
29
30When product path `{slug}` is active, read and write research under `research/{slug}/`, specs under `specs/{slug}/`, and treat top-level `research/*.md` files as flat-mode documents or cross-path summaries.
31
321. Resolve product-path scope using `research/{slug}/` when applicable.
332. Read `research/.progress.yaml` when present. Normalize `active_path` (singular legacy) to `active_paths` (plural list) when reading; treat legacy `abandoned` as `archived` and exclude archived/deferred/revisit/promoted paths plus `research/_archive/` scopes from active target selection. Scope the retention map to the active product path by default.
343. Require `research/journey-map.md`; if missing, recommend `$journey-map`.
354. Load journey, onboarding, conversion, transaction, metrics, customer feedback, specs, and product evidence when present.
365. Interview and recommend around: repeat-use job, natural frequency, core habit/workflow loop, lifecycle messages, saved state, collaboration, renewal moments, churn triggers, downgrade/cancel paths, winback, support recovery, and leading indicators.
376. Present the retention model and risk assumptions before writing.
387. Write `research/retention-map.md` and `research/retention-map-interview.md` in flat mode, or `research/{slug}/retention-map.md` and `research/{slug}/retention-map-interview.md` when product-path scope is active, after validation.
39
40## Output Shape
41
42```markdown
43# Retention Map
44
45> Based on: research/journey-map.md
46> Date: YYYY-MM-DD
47
48## Summary
49## Repeat-Use Loop
50## Lifecycle Triggers
51## Healthy Usage Signals
52## Churn Triggers
53## Recovery And Winback
54## Product Gaps
55## Next Steps
56```
57
58## Alignment Page
59
60Follow the shared alignment-page convention via the packaged convention resolver; output path is `alignment/retention-map-{topic}.html`.
61
62## Constraints
63
64- Do not force habit-loop language onto naturally infrequent or transactional products; document the natural return trigger instead.
65- End with `## Next Steps`, preferring `$expansion-map`, `$lifecycle-metrics`, `$hook-model`, `$customer-feedback`, or `$cohort-review` as context dictates.
66
67## Default Shipping Contract
68
69Follow the shared shipping contract convention in CLAUDE.md.
70
GeorgeQLe