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.
Onboarding Map
Invoke as $onboarding-map.
Create the stage-level onboarding plan that expands research/journey-map.md.
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 the same
research/{slug}/ convention as $journey-map.
- 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 onboarding map to the active product path by default.
- Require
research/journey-map.md or research/{slug}/journey-map.md; if missing, recommend $journey-map.
- Load ICP, journey map, specs, customer feedback, metrics, and current product routes/components when present.
- Interview and recommend around: signup entry points, account creation, required setup, imports/integrations, team invites, empty states, first-session guidance, first 5 minutes/hour/day, aha threshold, drop-offs, recovery, and support touchpoints.
- Present the proposed onboarding model before writing.
- Write
research/onboarding-map.md and research/onboarding-map-interview.md in flat mode, or research/{slug}/onboarding-map.md and research/{slug}/onboarding-map-interview.md when product-path scope is active, after validation.
Output Shape
# Onboarding Map
> Based on: research/journey-map.md
> Date: YYYY-MM-DD
## Summary
## Personas And Entry Points
## Signup And Setup Flow
## Activation Path
## First Success
## Drop-Offs And Recovery
## Instrumentation Needs
## Product Gaps
## Next Steps
Alignment Page
Follow the shared alignment-page convention via the packaged convention resolver; output path is alignment/onboarding-map-{topic}.html.
Constraints
- Stay stage-specific; do not rewrite the whole journey map.
- Make onboarding steps concrete enough to drive specs, UX variations, and instrumentation.
- End with
## Next Steps, preferring $conversion-map, $lifecycle-metrics, $ux-variations as context dictates.
Default Shipping Contract
Follow the shared shipping contract convention in CLAUDE.md.
1---2name: onboarding-map3description: Plan signup, setup, activation, first success, onboarding drop-offs, and time-to-value for each lifecycle persona4---5
6## Pack Availability Guard
7
8Before telling the user to run a skill from another project-local pack, check `.agents/project.json.enabled_packs`. If the target pack is not enabled, recommend `npx skillpacks install <pack>` from the project shell, instead of the target skill.
9
10# Onboarding Map
11
12Invoke as `$onboarding-map`.
13
14Create the stage-level onboarding plan that expands `research/journey-map.md`.
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 the same `research/{slug}/` convention as `$journey-map`.
332. Read `research/.progress.yaml` when present. Normalize `active_path` (singular legacy) to `active_paths` (plural list) when reading; treat legacy `abandoned` as `archived` and exclude archived/deferred/revisit/promoted paths plus `research/_archive/` scopes from active target selection. Scope the onboarding map to the active product path by default.
343. Require `research/journey-map.md` or `research/{slug}/journey-map.md`; if missing, recommend `$journey-map`.
354. Load ICP, journey map, specs, customer feedback, metrics, and current product routes/components when present.
365. Interview and recommend around: signup entry points, account creation, required setup, imports/integrations, team invites, empty states, first-session guidance, first 5 minutes/hour/day, aha threshold, drop-offs, recovery, and support touchpoints.
376. Present the proposed onboarding model before writing.
387. Write `research/onboarding-map.md` and `research/onboarding-map-interview.md` in flat mode, or `research/{slug}/onboarding-map.md` and `research/{slug}/onboarding-map-interview.md` when product-path scope is active, after validation.
39
40## Output Shape
41
42```markdown
43# Onboarding Map
44
45> Based on: research/journey-map.md
46> Date: YYYY-MM-DD
47
48## Summary
49## Personas And Entry Points
50## Signup And Setup Flow
51## Activation Path
52## First Success
53## Drop-Offs And Recovery
54## Instrumentation Needs
55## Product Gaps
56## Next Steps
57```
58
59## Alignment Page
60
61Follow the shared alignment-page convention via the packaged convention resolver; output path is `alignment/onboarding-map-{topic}.html`.
62
63## Constraints
64
65- Stay stage-specific; do not rewrite the whole journey map.
66- Make onboarding steps concrete enough to drive specs, UX variations, and instrumentation.
67- End with `## Next Steps`, preferring `$conversion-map`, `$lifecycle-metrics`, `$ux-variations` as context dictates.
68
69## Default Shipping Contract
70
71Follow the shared shipping contract convention in CLAUDE.md.
72
GeorgeQLe