--- name: rshankras/store-growth-audit source: https://app.decimal.ai/s/rshankras-store-growth-audit@1/SKILL.md source_sha256: 8d63061b052e --- # Store Growth Audit Walk an app โ€” new or live โ€” through the full App Store growth playbook, phase by phase, and produce a scorecard: what's installed, what's missing, what to do next, and who fixes it. > The invariant: **every item has a detection rule**. Status comes from an ASC read, a codebase > check, or an explicit question โ€” never from vibes. If the user doesn't know, the item is > ๐ŸŸ  *unverified*, not assumed โœ…. ## Where it fits (read the seams) - **Not `store-signals`.** That is the continuous *signal โ†’ backlog* loop: are the numbers moving, did last cycle's bets pay off? This is the *structural* audit: is the machinery even installed? Run this quarterly (or pre-launch); run store-signals monthly. Trend questions route there. - **Not `analytics-interpretation`.** Metric-quality judgments ("is 3.2% conversion good?") route there; this skill only records the baseline and whether benchmarks were checked. - **Fixes never happen here.** Every ๐Ÿ”ด/๐ŸŸ  routes to a named sibling skill and (when driven from SwiftShip) an `/apple:*` command. This skill detects, scores, and routes. Read-only on ASC. ## When This Skill Activates - "Audit my app's growth / store presence / what levers am I missing" - A new app is approaching first submission and needs a growth plan, not just metadata - Quarterly re-audit cadence, or after a launch that undershot expectations - Before deciding to spend on paid acquisition ("is the free machinery done first?") - Portfolio triage: "which of my apps is leaving the most on the table" ## The Model: P0โ€“P9 54 items across ten phases. Each phase is a theme; the item detail lives in the checklist files. | Phase | Theme | Items | Goal | |-------|-------|-------|------| | P0 | Day-one money toggles | 4 | Free margin + a measurement baseline before anything else | | P1 | On-metadata ASO | 7 | Every indexed field working (title, subtitle, keywords, events, IAPs) | | P2 | Conversion assets | 5 | Icon, screenshots, trust signals that convert impressions | | P3 | Localization | 5 | Metadata-first market expansion + PPP pricing | | P4 | Ratings machinery | 4 | Prompting, replying, and protecting the rating | | P5 | Experimentation | 4 | PPO, CPPs, events as a testing habit | | P6 | Featuring & free discovery | 6 | Nominations, new-OS adoption, storefronts, web presence | | P7 | Paid & external traffic | 8 | Apple Ads ladder, launch spikes, pre-orders, codes | | P8 | Earnings | 7 | Paywall experiments, win-backs, web checkout, bundles | | P9 | Retention loop & ops | 4 | Retention surfaces + the recurring refresh calendar | **Compressed priority** (used for action selection, not the maturity ladder): P0 money toggles first โ†’ P1โ€“P3 (metadata, conversion, localization) โ†’ P8.4 web checkout + P8.6 volume purchasing (the 2026-era revenue unlocks) โ†’ everything else โ†’ P7 paid traffic last. Paid spend on top of broken free machinery is burned money. ## Reference Files | File | Purpose | |------|---------| | `detection-playbook.md` | Gather-once machinery: the MCP batch table, the codebase grep table, the single MANUAL question batch | | `audit-checklist-p0-p4.md` | Items P0.1โ€“P4.4 (25): foundations โ€” money toggles through ratings | | `audit-checklist-p5-p9.md` | Items P5.1โ€“P9.4 (29): growth loops โ€” experimentation through ops | ## Audit Process 1. **Resolve app, mode, and scope.** Get the `appId` (from `.planning/STATE.md` when driven by SwiftShip, else `list_apps` + confirm with the user). App live on the store โ†’ *existing* mode; not yet shipped โ†’ *pre-launch* mode. Scope defaults to the full P0โ€“P9; a named phase runs scoped (see **Scoped Runs**). A prior scorecard (`GROWTH.md`), if present, is the diff baseline. 2. **Gather evidence โ€” one pass, per `detection-playbook.md`.** Run the full MCP read batch, the full codebase grep pass, and ONE batched AskUserQuestion round for every MANUAL item. Never interleave gathering with scoring; never ask questions one at a time. 3. **Score all 54 items** against the gathered evidence using each item's `rule:`. Honor `applies-if:` guards (โšช N/A) and โณ ANNOUNCED flags. Every status carries a terse, citable evidence string (`locales: en-US only`, `SBP: enrolled (user, 2026-07)`). 4. **Compute phase scores + maturity level** (rules below), and โ€” when a prior scorecard exists โ€” per-item deltas: fixed / regressed / new since last audit. 5. **Select the top 5 actions** (rule below). 6. **Write or refresh the scorecard** โ€” in a SwiftShip project this is `.planning/GROWTH.md` (schema in SwiftShip's `templates/GROWTH.md`); standalone, write `GROWTH.md` beside the audit. Append an audit-history row; refresh the recurring calendar's next-due dates. 7. **Print the digest and route.** Maturity level, phase bar, top-5 with routes, deltas, unanswered MANUAL items, next three calendar due-dates, and the suggested next command/skill. ## Item Record Format Each checklist item is a stanza: ```markdown #### P3.1 Metadata-only localization (ja de fr es pt ko zh-Hans) โ€” core - detect: MCP `list_locales` - rule: โœ… โ‰ฅ7 target locales localized ยท ๐ŸŸ  1โ€“6 non-English locales ยท ๐Ÿ”ด en-only - new-app: plan โ€” seed target locales in the first submission - fix: product/localization-strategy โ†’ /apple:localize ``` - **ID** (`P.`) is stable forever โ€” scorecards diff by ID; never renumber. - **Flags** after the name: `core` (phase-gating), `RECURRING` (calendar-driven), `โณ ANNOUNCED (WWDC26)`. - **detect:** `MCP ` ยท `CODE ` ยท `MANUAL ` ยท `HYBRID` (combination). - **rule:** explicit โœ…/๐ŸŸ /๐Ÿ”ด thresholds; optional `applies-if:` guard โ†’ โšช N/A when it fails. - **new-app:** how pre-launch mode scores it โ€” `plan` / `code` / `defer` (see Modes). - **fix:** `sibling-skill โ†’ /apple:command` โ€” the skill path works standalone; the command half applies when driven from SwiftShip. **Status vocabulary:** โœ… done/healthy ยท ๐ŸŸ  partial, stale, or unverified ยท ๐Ÿ”ด missing ยท โšช N/A (applies-if failed; excluded from denominators) ยท โณ ANNOUNCED (not yet scoreable; excluded from denominators; carries `prep:` and `recheck:` lines instead of a live rule). ## Scoring & Maturity - **Phase score:** `โœ… n / N applicable` โ€” โšช and โณ items are excluded from N. - **Phase grade:** - `Complete` โ€” all applicable items โœ… - `Working` โ€” โ‰ฅ50% โœ… **and no `core` item ๐Ÿ”ด** - `Gaps` โ€” any `core` item ๐Ÿ”ด, or <50% โœ… - `Not started` โ€” no applicable item โœ… - **`core` items (13):** P0.1, P0.2, P1.1, P2.2, P2.4, P3.1, P4.1, P4.2, P5.1, P6.1, P8.1, P8.4, P9.2. - **Growth maturity level (0โ€“9):** the highest P such that every phase โ‰ค P grades at least `Working`. An app with P0โ€“P3 working but P4 in gaps is Level 3, no matter how good P5โ€“P9 look. The ladder follows numeric phase order; the compressed priority shapes only action selection. **Top-5 action selection:** from all applicable ๐Ÿ”ด + ๐ŸŸ  items, order by compressed-priority tier (T1: P0 ยท T2: P1โ€“P3 ยท T3: P8.4 + P8.6-when-live ยท T4: P4โ€“P6, rest of P8, P9 ยท T5: P7), then within a tier: `core` first, ๐Ÿ”ด before ๐ŸŸ , lowest effort first. Two overrides: an **overdue RECURRING** calendar item jumps to the top; always include at least one metadata-only quick win (shippable without a binary release). ## Modes: Existing vs Pre-Launch | | Existing app | Pre-launch | |---|---|---| | Evidence | ASC reads + codebase + MANUAL | `.planning/` docs + codebase + MANUAL | | `new-app: plan` items | scored normally | planned-in-docs โ†’ ๐ŸŸ  `planned`; absent โ†’ ๐Ÿ”ด | | `new-app: code` items | scored normally | scored normally (greps work pre-launch) | | `new-app: defer` items | scored normally | โšช with an activation trigger noted (e.g. "30 days post-launch") | | Output framing | audit + deltas | launch plan (history row tagged `mode: pre-launch`) | The first post-launch audit diffs cleanly against the pre-launch scorecard โ€” same IDs, same schema. ## Scoped Runs (single phase) "Run phase 3" = audit + worklist for that stage only. - **Scope**: one phase (`P3`, bare `3` accepted) or a short range/list (`P1-P3`, `P0,P4`). Default remains the full P0โ€“P9 audit. - **Evidence**: pull only the `detection-playbook.md` rows whose items are in scope โ€” MCP calls, greps, and MANUAL questions alike. A P1 run needs `get_metadata`/`list_locales`/`list_iap`/ `list_app_events`, not sales reports or paywall greps. - **Scorecard**: update only the in-scope phase tables and their Phase Scores rows; every other row stays untouched (stable IDs make the partial update safe). Append an Audit History row tagged `scope: P3`. Recompute the maturity level from the refreshed rows plus the untouched remainder โ€” mark it `(est.)` if any out-of-scope phase has never been audited. - **Output**: instead of the top-5, print the **phase worklist** โ€” every applicable in-scope item with status, evidence, and route โ€” ordered `core` first, ๐Ÿ”ด before ๐ŸŸ , lowest effort first. End by offering to start the first route (gated, as always). - A scoped run never rewrites items outside its scope, and never counts as a full re-audit for the Recurring Calendar's "announced-features recheck" row unless the โณ items are in scope. ## Output Format The scorecard file (schema = SwiftShip `templates/GROWTH.md`): header (app, date, mode, maturity) ยท phase-score table ยท top-5 actions ยท ten per-phase tables (`ID | Item | Status | Evidence | Next step | Route`) ยท Watchlist (โณ announced) ยท Recurring Calendar ยท Baseline Metrics Snapshot ยท append-only Audit History. The printed digest never dumps 54 rows: ``` Growth audit: โ€” Level 4/9 (existing, re-audit) P0 โ–“โ–“โ–“โ–‘ 3/4 ยท P1 โ–“โ–“โ–“โ–“โ–“โ–‘โ–‘ 5/7 ยท P2 โ–“โ–“โ–“โ–‘โ–‘ 3/5 ยท P3 โ–“โ–‘โ–‘โ–‘โ–‘ 1/5 ยท P4 โ–“โ–“โ–“โ–“ 4/4 โ€ฆ Top 5: 1) P0.1 Apply to Small Business Program (route: growth/indie-business) โ€ฆ Since last audit: 3 fixed, 1 regressed (P9.3 update freshness) Unverified (you were unsure): P0.3 peer benchmarks, P7.2 brand defense Calendar: featuring nomination due in 12 days ยท keyword refresh due 2026-10-01 Next: /apple:localize (or product/localization-strategy standalone) ``` ## Routing Map The only place the full route list lives; stanzas carry the short form. | Audit area | Sibling skill (canonical) | SwiftShip command | |---|---|---| | SBP, business ops | `growth/indie-business` | โ€” (ASC manual) | | Billing grace/retry, subscription lifecycle | `generators/subscription-lifecycle` | `/apple:subscription` | | Analytics baseline, benchmarks | `growth/analytics-interpretation` | `/apple:learn-from-store` | | Keywords, metadata fields, AI tagging | `app-store/keyword-optimizer` | `/apple:metadata` (or `/apple:aso` if installed) | | Apple Ads (discovery, exact, halo, brand) | `app-store/apple-search-ads` | `/apple:aso` if installed | | Screenshots, previews, Creative Assets | `app-store/screenshot-planner` | `/apple:screenshots` | | Icon + PPO + CPP experiments | `generators/product-page-optimization`, `generators/custom-product-pages` | `/apple:experiment` | | In-app events | `generators/in-app-events` | `/apple:event` | | Localization + PPP pricing | `product/localization-strategy`, `monetization` (pricing-models) | `/apple:localize` | | Ratings: prompting, replies, protection | `app-store/ratings-mechanics`, `generators/review-prompt`, `app-store/review-response-writer` | `/apple:ratings` (health + replies); `/apple:ship` (phased release) | | Featuring nominations | `generators/featuring-nomination` | โ€” (ASC manual, calendar-driven) | | New-OS adoption | โ€” | `/apple:modernize` | | App Intents / Spotlight | `apple-intelligence/app-intents`, `generators/spotlight-indexing` | `/apple:plan` | | Web SEO, landing page, deal sites | `app-store/web-presence` | โ€” | | Pre-orders, offer codes, waitlist | `generators/pre-orders`, `generators/offer-codes-setup`, `product/beta-testing` | `/apple:testflight` | | Paywall + pricing experiments | `generators/paywall-generator`, `monetization` | `/apple:subscription` | | Win-backs, retention messaging | `generators/win-back-offers` | `/apple:subscription` | | External purchase links / web checkout | `monetization/external-purchases` | โ€” | | Bundles, Family Sharing, volume licensing | `monetization/bundles-and-licensing` | โ€” | | Retention surfaces | `generators/onboarding-generator`, `generators/push-notifications`, `generators/widget-generator`, `generators/live-activity-generator` | `/apple:plan` | ## Caveats - **Read-only on ASC.** The audit never mutates anything โ€” not even analytics report setup (that routes to store-signals / `/apple:learn-from-store`). Surface โ†’ score โ†’ route. - **MANUAL honesty.** Ask once, in one batch. "I don't know" scores ๐ŸŸ  *unverified* โ€” the scorecard tells the user what to go check, it never guesses. - **โณ items are rechecked every audit.** Apple ships announced features on its own schedule; each โณ stanza carries a dormant detection rule โ€” when the feature is live, apply it and drop the flag. - **Never reset the ratings summary** (P4.4). That item is a guardrail, not a task: resetting discards accumulated social proof and is almost never recoverable. Default โœ…; flip to ๐Ÿ”ด only if a reset is planned or happened โ€” then route to `app-store/ratings-mechanics` to stop it. - Stable IDs. New items get new numbers; retired items keep their row with status `retired`.