[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M699QX73ZFW80T3CDPK68M9Q":3,"skill-same:01M699QX73ZFW80T3CDPK68M9Q":70},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M699QX73ZFW80T3CDPK68M9Q","generate-ppmplugin",null,"Build and verify a third-party `.ppmplugin` end to end. This recommended entry point detects Android and iOS source, confirms target platforms, then invokes the manifest, platform build, assemble, and audit stages in order. Advanced users can invoke a stage directly for focused reruns or debugging. Produces a native-only bundle (`manifest.json` plus an Android DEX and\u002For iOS framework) and stops on any failed stage rather than emitting an unverified partial build. Run after the native module exists.","microsoft\u002Fpower-platform-skills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M699JVYJFB75D9JM70BN4H0Q",1149,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpower-apps-mobile-extension\u002Fskills\u002Fgenerate-ppmplugin\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"generate ppmplugin","generate","point","android","invoke","source","sonnet","advanced","native","end","platform","only","assemble","edit","write","read","Bash","audit","framework","run","debugging","2026-11-10 10:12:30",false,"---\nname: generate-ppmplugin\ndescription: Build and verify a third-party `.ppmplugin` end to end. This recommended entry point detects Android and iOS source, confirms target platforms, then invokes the manifest, platform build, assemble, and audit stages in order. Advanced users can invoke a stage directly for focused reruns or debugging. Produces a native-only bundle (`manifest.json` plus an Android DEX and\u002For iOS framework) and stops on any failed stage rather than emitting an unverified partial build. Run after the native module exists.\nallowed-tools: Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion, Skill\nmodel: sonnet\n---\n\n# \u002Fgenerate-ppmplugin\n\n**The recommended entry point** for the third-party-control build track. In the normal flow, the user invokes `\u002Fgenerate-ppmplugin` and it drives the five stage skills (`\u002Fgenerate-ppmplugin-manifest`, `\u002Fbuild-android-binary`, `\u002Fbuild-ios-binary`, `\u002Fassemble-ppmplugin`, `\u002Faudit-ppmplugin`) in order. Advanced users may invoke a stage directly to rerun or debug only that stage. Inspect the repo, pick the right target set, run manifest → build skill(s) → assemble → audit in sequence, and produce a *verified* `.ppmplugin` on disk (or a clear stop with the failing stage).\n\nRead [`shared\u002Fppmplugin-format.md`](..\u002F..\u002Fshared\u002Fppmplugin-format.md) §1 — the bundle layout this orchestrator produces.\n\n## What this skill does NOT do\n- Does not author the manifest, build the DEX, build the framework, zip the bundle, or run the audit itself — those are the stage skills. This skill **invokes** them in the right order, with the right inputs, and gates between them.\n- Does not skip any stage's confirmations \u002F mismatch gates \u002F replace-existing prompts — those still surface to the user. The orchestrator just removes the \"which stage next?\" decision so the user never has to invoke a stage directly.\n- Does not upload to Dataverse or wire into a canvas app (Stage 3 — deferred).\n- Does not edit source code under `src\u002F`, `ios\u002F`, `android\u002F` — every stage builds from a staged copy. The repo is read-only from the build's perspective.\n\n---\n\n## Step 1 — Read shared docs + prereq summary\n\n1. Read [`shared\u002Fshared-instructions.md`](..\u002F..\u002Fshared\u002Fshared-instructions.md) and [`shared\u002Fppmplugin-format.md`](..\u002F..\u002Fshared\u002Fppmplugin-format.md).\n2. Confirm the working directory is a third-party-control repo: a `package.json` (dev-only `\u003Ckebab>-control` name — **not** a published `@powerapps\u002Fextension-*` scope; this track ships a binary, not an npm package) and either `android\u002F` or `ios\u002F` (or both). If missing, STOP with `NEEDS_CONTEXT: not a third-party-control-ready repo — missing \u003Clist>` and point at [`shared\u002Frepo-layout.md`](..\u002F..\u002Fshared\u002Frepo-layout.md).\n3. Print the orchestrator prereq block (sub-skills each re-run their own prereq check when invoked — this is the summary the user sees up front so they know what's required end-to-end):\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n Prereqs — \u002Fgenerate-ppmplugin (end-to-end)\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n \u002Fgenerate-ppmplugin-manifest  — no toolchain (pure read + validate + write)\n \u002Fbuild-android-binary         — JDK 17, Android SDK Build-Tools 35 (d8), Gradle\n \u002Fbuild-ios-binary             — Xcode 16+ (26.2+ recommended; CocoaPods optional — header-only path)  (Mac-only)\n \u002Fassemble-ppmplugin           — jar (JDK)\n \u002Faudit-ppmplugin              — jar (JDK); dexdump or strings (DEX scan)\n```\n\nEach stage will surface its own prereq failure when reached (don't pre-fail the orchestrator on a missing tool the user may have on a different machine).\n\n---\n\n## Step 2 — Detect available targets\n\nLook at the repo to see which native platforms could actually build. **Detection is structural, not aspirational** — the user can't ship a platform whose source doesn't exist.\n\n| Target | Detection signal |\n|---|---|\n| Android | `android\u002Fbuild.gradle` exists AND `android\u002Fsrc\u002Fmain\u002Fjava\u002F**\u002F*.kt` contains a `ReactContextBaseJavaModule` subclass |\n| iOS | `ios\u002FRCT*Module.h` declaring `\u003CRCTBridgeModule>` AND a `.m` with `+ (NSString *)moduleName` (**NOT** `RCT_EXPORT_MODULE`) (podspec **optional** — only declares extra iOS system frameworks; `\u002Fbuild-ios-binary` builds from the `.h\u002F.m` source + the `react-native` devDep headers, not the podspec) |\n\nPrint a visible ✓\u002F✗ block:\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n Targets available in this repo\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n ? ✓ Android — android\u002Fbuild.gradle + PenInputModule.kt found\n ? ✓ iOS     — ios\u002FRCTPenInputModule.h (+ .m with +moduleName) found\n```\n\n(If a signal is present but malformed — e.g. `android\u002F` exists but no Kotlin module — list it as ✗ with the specific gap. `\u002Fgenerate-ppmplugin-manifest` will run the deeper structure preflight; this orchestrator just sees if there's enough to consider the platform a viable target.)\n\nIf neither target is viable → STOP with `NEEDS_CONTEXT: no native target available — repo has neither a buildable android\u002F nor ios\u002F module`. The `.ppmplugin` format requires at least one native entrypoint; a manifest-only bundle is not shippable.\n\n---\n\n## Step 3 — Recommend + confirm the target set\n\nUse the detection from Step 2 to pre-mark the recommended option, then confirm with `AskUserQuestion`:\n\n- **Both available** → recommend **Both**. Reasoning: the whole pipeline runs in one shot; the user gets a bundle that works on every mobile platform.\n- **Android only available** → recommend **Android-only**. No iOS source to build.\n- **iOS only available** → recommend **iOS-only**. No Android source to build.\n\n```text\nQuestion: Which target(s) should this .ppmplugin ship?\n- Both (Recommended)           — runs \u002Fbuild-android-binary AND \u002Fbuild-ios-binary\n- Android only                  — skips iOS even though the source is here\n- iOS only                      — skips Android even though the source is here\n```\n\nOnly show options whose target is viable. If only Android is viable, do not offer \"Both\" or \"iOS only\" — just confirm \"Android-only\" (one option is still worth confirming so the user can cancel).\n\n**On Mac-only constraint:** if the user picks Both or iOS-only on a non-Mac, surface a one-line warning (`\u002Fbuild-ios-binary` is Mac-only and will halt the orchestrator when reached). Offer to fall back to Android-only or stop.\n\nRecord the chosen target set; it's the contract every downstream sub-skill sees.\n\n---\n\n## Step 4 — Run the stages in sequence (with gates)\n\nInvoke each stage via the `Skill` tool. After each step, check its result; on `DONE` continue, on `BLOCKED` \u002F `NEEDS_CONTEXT` halt the orchestrator with a clear handoff. Do not try to auto-recover — a failed stage is a signal the user needs to look.\n\n### 4.1 — `\u002Fgenerate-ppmplugin-manifest`\n\nInvoke `Skill: generate-ppmplugin-manifest`. On the normal flow the committed `.\u002Fmanifest.json` already exists (authored by `\u002Fgenerate-native-extension` at scaffold time), so the sub-skill **validates it, reconciles its `entrypoints` to the chosen target, and writes the staged build copy** `ppmplugin\u002Fstaging\u002Fmanifest.json` — it does not re-author the contract. (If the repo has no `.\u002Fmanifest.json` — a hand-authored module — the sub-skill falls back to authoring it from source.) It runs its own structure preflight, asks the target via `AskUserQuestion` (default to the orchestrator's choice from Step 3 — recorded in `.extension-state.md` so the sub-skill doesn't re-prompt unnecessarily), and returns `DONE` with the staged manifest path.\n\n**Re-run safety.** If a staged manifest already exists from a prior run, the sub-skill's re-run mode (Step 1.5 in its SKILL.md) handles update \u002F keep-as-is; that's not the orchestrator's concern.\n\n### 4.2 — Build skill(s) in parallel where possible\n\nThe Android and iOS builds are **independent** — they touch different staging directories (`ppmplugin\u002Fstaging\u002Fandroid-build\u002F` vs `…\u002Fios-build\u002F`) and produce different outputs. Run them concurrently when both are selected:\n\n| Target set | Sub-skills invoked |\n|---|---|\n| Android-only | `Skill: build-android-binary` |\n| iOS-only | `Skill: build-ios-binary` |\n| Both | both, in a single turn (parallel `Skill` tool calls) |\n\nEach build skill returns `DONE` (with the staged binary path) or `BLOCKED` (prereq \u002F build failure). On a Both target, if one build fails and the other succeeds, ask via `AskUserQuestion`:\n\n> *\"`\u002Fbuild-\u003Cplatform>` failed; `\u002Fbuild-\u003Cother>` succeeded. How do you want to proceed?\"*\n> - **Fix and re-run the failing build** — stop the orchestrator; the user investigates the failure\n> - **Ship `\u003Cother>`-only** — drop the failing platform from the target set, continue to assemble\n> - **Stop**\n\nIf both fail → STOP with `BLOCKED: no platform built — see sub-skill output above`.\n\n### 4.3 — `\u002Fassemble-ppmplugin`\n\nInvoke `Skill: assemble-ppmplugin`. The stage reconciles the manifest's native entrypoints against the staged binaries, re-validates, zips, and verifies. It returns `DONE` with the `.ppmplugin` path.\n\nIf the user dropped a platform in Step 4.2 (Ship `\u003Cother>`-only), the stage's own reconcile gate will offer to remove the missing entrypoint from `manifest.json` — accept that, since the orchestrator already made that decision upstream. Pass through without re-prompting if the underlying tooling allows.\n\n### 4.4 — `\u002Faudit-ppmplugin` (final verification gate)\n\nInvoke `Skill: audit-ppmplugin` on the `.ppmplugin` that `\u002Fassemble-ppmplugin` just produced (pass the bundle path). This is the gate that turns \"well-formed zip\" into \"will actually load on device\": it re-runs the validator rules against the built artifact, scans the DEX for SDK-era leakage (`INativeExtension*`, `sendAsync`, `HermesBytecodeLoader`, …), checks manifest↔bundle consistency and the source-to-receiver contract, and returns a verdict.\n\n- `DONE` (0 CRITICAL) → the bundle is verified; continue to Step 5 and report **READY TO UPLOAD**. Surface any WARNINGs in the final report.\n- `BLOCKED` (≥1 CRITICAL) → do NOT report success. Halt with the audit's CRITICAL findings and the owning-stage handoff (audit already routes each finding to `\u002Fgenerate-ppmplugin-manifest` or the build skill). The bundle exists on disk but is **not** upload-ready; the user fixes upstream and re-runs `\u002Fgenerate-ppmplugin`.\n\nBecause the orchestrator runs audit automatically, the user never invokes `\u002Faudit-ppmplugin` themselves on the happy path — it's the last internal stage.\n\n---\n\n## Step 5 — Report\n\nPrint the final deliverable as a visible block (informational, no question):\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n \u002Fgenerate-ppmplugin — DONE\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n Bundle: ppmplugin\u002Fpen-input.ppmplugin   (v0.1.4)   ✓ audit: READY TO UPLOAD\n Target: Both (Android DEX + iOS framework)\n Steps:  manifest ✓  build-android ✓  build-ios ✓  assemble ✓  audit ✓\n Next:   • deploy the dispatcher PCF → \u002Fpublish-pcf-companion\n         • upload this .ppmplugin via the wrap wizard + wire the PCF into a\n           canvas app (Stage 3 — not yet a skill).\n```\n\nThen offer the actionable next step via `AskUserQuestion` (shared-instructions §9.1 — invoke via the Skill tool):\n- **Run \u002Fpublish-pcf-companion** (deploy the dispatcher PCF to a Power Platform env — needed before the control works in a canvas app)\n- **Run \u002Fdebug-extension** (debug\u002Frefine the control, then re-run \u002Fgenerate-ppmplugin)\n- **Stay — I'll upload the .ppmplugin manually** (Stage 3 isn't a skill yet)\n\nReturn `DONE` with the bundle path. Only report this block when audit returned `DONE` — a bundle\nthat failed audit is reported via the failure handoff below, never as success.\n\n---\n\n## Failure handoffs\n\nThe orchestrator's value is *one entry point on the happy path*. On a failure it should surface,\n**not absorb**. Each handoff names the failing stage and normally tells the user to re-run\n`\u002Fgenerate-ppmplugin` after fixing; direct stage invocation is reserved for a focused rerun or\ndiagnostic:\n\n| Failure | Handoff message |\n|---|---|\n| Manifest derivation blocked | `BLOCKED at manifest stage — \u003Creason>. Fix the flagged item, then re-run \u002Fgenerate-ppmplugin.` |\n| Android build failed | `BLOCKED at android-build stage — \u003Creason>. The manifest in ppmplugin\u002Fstaging\u002Fmanifest.json is preserved; re-run \u002Fgenerate-ppmplugin after fixing.` |\n| iOS build failed (Mac-only) | `BLOCKED at ios-build stage — \u003Creason>. If you don't have Xcode here, re-run on a Mac or pick \"Android-only\" target.` |\n| Assemble failed | `BLOCKED at assemble stage — \u003Creason>. The staged binaries are intact; re-run \u002Fgenerate-ppmplugin after fixing.` |\n| Audit found CRITICAL | `BLOCKED at audit stage — \u003CN> CRITICAL finding(s). The .ppmplugin was built but is NOT upload-ready. \u003Cfirst finding + its routed fix>. Fix upstream, then re-run \u002Fgenerate-ppmplugin.` |\n\nNever report a partial or unverified `.ppmplugin` as success. A bundle missing a declared\nentrypoint, or carrying SDK-leakage in its DEX, will fail during upload or silently on device;\nsurface the gap here instead.\n","# \u002Fgenerate-ppmplugin\n\n**The recommended entry point** for the third-party-control build track. In the normal flow, the user invokes `\u002Fgenerate-ppmplugin` and it drives the five stage skills (`\u002Fgenerate-ppmplugin-manifest`, `\u002Fbuild-android-binary`, `\u002Fbuild-ios-binary`, `\u002Fassemble-ppmplugin`, `\u002Faudit-ppmplugin`) in order. Advanced users may invoke a stage directly to rerun or debug only that stage. Inspect the repo, pick the right target set, run manifest → build skill(s) → assemble → audit in sequence, and produce a *verified* `.ppmplugin` on disk (or a clear stop with the failing stage).\n\nRead [`shared\u002Fppmplugin-format.md`](..\u002F..\u002Fshared\u002Fppmplugin-format.md) §1 — the bundle layout this orchestrator produces.\n\n## What this skill does NOT do\n- Does not author the manifest, build the DEX, build the framework, zip the bundle, or run the audit itself — those are the stage skills. This skill **invokes** them in the right order, with the right inputs, and gates between them.\n- Does not skip any stage's confirmations \u002F mismatch gates \u002F replace-existing prompts — those still surface to the user. The orchestrator just removes the \"which stage next?\" decision so the user never has to invoke a stage directly.\n- Does not upload to Dataverse or wire into a canvas app (Stage 3 — deferred).\n- Does not edit source code under `src\u002F`, `ios\u002F`, `android\u002F` — every stage builds from a staged copy. The repo is read-only from the build's perspective.\n\n---\n\n## Step 1 — Read shared docs + prereq summary\n\n1. Read [`shared\u002Fshared-instructions.md`](..\u002F..\u002Fshared\u002Fshared-instructions.md) and [`shared\u002Fppmplugin-format.md`](..\u002F..\u002Fshared\u002Fppmplugin-format.md).\n2. Confirm the working directory is a third-party-control repo: a `package.json` (dev-only `\u003Ckebab>-control` name — **not** a published `@powerapps\u002Fextension-*` scope; this track ships a binary, not an npm package) and either `android\u002F` or `ios\u002F` (or both). If missing, STOP with `NEEDS_CONTEXT: not a third-party-control-ready repo — missing \u003Clist>` and point at [`shared\u002Frepo-layout.md`](..\u002F..\u002Fshared\u002Frepo-layout.md).\n3. Print the orchestrator prereq block (sub-skills each re-run their own prereq check when invoked — this is the summary the user sees up front so they know what's required end-to-end):\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n Prereqs — \u002Fgenerate-ppmplugin (end-to-end)\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n \u002Fgenerate-ppmplugin-manifest  — no toolchain (pure read + validate + write)\n \u002Fbuild-android-binary         — JDK 17, Android SDK Build-Tools 35 (d8), Gradle\n \u002Fbuild-ios-binary             — Xcode 16+ (26.2+ recommended; CocoaPods optional — header-only path)  (Mac-only)\n \u002Fassemble-ppmplugin           — jar (JDK)\n \u002Faudit-ppmplugin              — jar (JDK); dexdump or strings (DEX scan)\n```\n\nEach stage will surface its own prereq failure when reached (don't pre-fail the orchestrator on a missing tool the user may have on a different machine).\n\n---\n\n## Step 2 — Detect available targets\n\nLook at the repo to see which native platforms could actually build. **Detection is structural, not aspirational** — the user can't ship a platform whose source doesn't exist.\n\n| Target | Detection signal |\n|---|---|\n| Android | `android\u002Fbuild.gradle` exists AND `android\u002Fsrc\u002Fmain\u002Fjava\u002F**\u002F*.kt` contains a `ReactContextBaseJavaModule` subclass |\n| iOS | `ios\u002FRCT*Module.h` declaring `\u003CRCTBridgeModule>` AND a `.m` with `+ (NSString *)moduleName` (**NOT** `RCT_EXPORT_MODULE`) (podspec **optional** — only declares extra iOS system frameworks; `\u002Fbuild-ios-binary` builds from the `.h\u002F.m` source + the `react-native` devDep headers, not the podspec) |\n\nPrint a visible ✓\u002F✗ block:\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n Targets available in this repo\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n ? ✓ Android — android\u002Fbuild.gradle + PenInputModule.kt found\n ? ✓ iOS     — ios\u002FRCTPenInputModule.h (+ .m with +moduleName) found\n```\n\n(If a signal is present but malformed — e.g. `android\u002F` exists but no Kotlin module — list it as ✗ with the specific gap. `\u002Fgenerate-ppmplugin-manifest` will run the deeper structure preflight; this orchestrator just sees if there's enough to consider the platform a viable target.)\n\nIf neither target is viable → STOP with `NEEDS_CONTEXT: no native target available — repo has neither a buildable android\u002F nor ios\u002F module`. The `.ppmplugin` format requires at least one native entrypoint; a manifest-only bundle is not shippable.\n\n---\n\n## Step 3 — Recommend + confirm the target set\n\nUse the detection from Step 2 to pre-mark the recommended option, then confirm with `AskUserQuestion`:\n\n- **Both available** → recommend **Both**. Reasoning: the whole pipeline runs in one shot; the user gets a bundle that works on every mobile platform.\n- **Android only available** → recommend **Android-only**. No iOS source to build.\n- **iOS only available** → recommend **iOS-only**. No Android source to build.\n\n```text\nQuestion: Which target(s) should this .ppmplugin ship?\n- Both (Recommended)           — runs \u002Fbuild-android-binary AND \u002Fbuild-ios-binary\n- Android only                  — skips iOS even though the source is here\n- iOS only                      — skips Android even though the source is here\n```\n\nOnly show options whose target is viable. If only Android is viable, do not offer \"Both\" or \"iOS only\" — just confirm \"Android-only\" (one option is still worth confirming so the user can cancel).\n\n**On Mac-only constraint:** if the user picks Both or iOS-only on a non-Mac, surface a one-line warning (`\u002Fbuild-ios-binary` is Mac-only and will halt the orchestrator when reached). Offer to fall back to Android-only or stop.\n\nRecord the chosen target set; it's the contract every downstream sub-skill sees.\n\n---\n\n## Step 4 — Run the stages in sequence (with gates)\n\nInvoke each stage via the `Skill` tool. After each step, check its result; on `DONE` continue, on `BLOCKED` \u002F `NEEDS_CONTEXT` halt the orchestrator with a clear handoff. Do not try to auto-recover — a failed stage is a signal the user needs to look.\n\n### 4.1 — `\u002Fgenerate-ppmplugin-manifest`\n\nInvoke `Skill: generate-ppmplugin-manifest`. On the normal flow the committed `.\u002Fmanifest.json` already exists (authored by `\u002Fgenerate-native-extension` at scaffold time), so the sub-skill **validates it, reconciles its `entrypoints` to the chosen target, and writes the staged build copy** `ppmplugin\u002Fstaging\u002Fmanifest.json` — it does not re-author the contract. (If the repo has no `.\u002Fmanifest.json` — a hand-authored module — the sub-skill falls back to authoring it from source.) It runs its own structure preflight, asks the target via `AskUserQuestion` (default to the orchestrator's choice from Step 3 — recorded in `.extension-state.md` so the sub-skill doesn't re-prompt unnecessarily), and returns `DONE` with the staged manifest path.\n\n**Re-run safety.** If a staged manifest already exists from a prior run, the sub-skill's re-run mode (Step 1.5 in its SKILL.md) handles update \u002F keep-as-is; that's not the orchestrator's concern.\n\n### 4.2 — Build skill(s) in parallel where possible\n\nThe Android and iOS builds are **independent** — they touch different staging directories (`ppmplugin\u002Fstaging\u002Fandroid-build\u002F` vs `…\u002Fios-build\u002F`) and produce different outputs. Run them concurrently when both are selected:\n\n| Target set | Sub-skills invoked |\n|---|---|\n| Android-only | `Skill: build-android-binary` |\n| iOS-only | `Skill: build-ios-binary` |\n| Both | both, in a single turn (parallel `Skill` tool calls) |\n\nEach build skill returns `DONE` (with the staged binary path) or `BLOCKED` (prereq \u002F build failure). On a Both target, if one build fails and the other succeeds, ask via `AskUserQuestion`:\n\n> *\"`\u002Fbuild-\u003Cplatform>` failed; `\u002Fbuild-\u003Cother>` succeeded. How do you want to proceed?\"*\n> - **Fix and re-run the failing build** — stop the orchestrator; the user investigates the failure\n> - **Ship `\u003Cother>`-only** — drop the failing platform from the target set, continue to assemble\n> - **Stop**\n\nIf both fail → STOP with `BLOCKED: no platform built — see sub-skill output above`.\n\n### 4.3 — `\u002Fassemble-ppmplugin`\n\nInvoke `Skill: assemble-ppmplugin`. The stage reconciles the manifest's native entrypoints against the staged binaries, re-validates, zips, and verifies. It returns `DONE` with the `.ppmplugin` path.\n\nIf the user dropped a platform in Step 4.2 (Ship `\u003Cother>`-only), the stage's own reconcile gate will offer to remove the missing entrypoint from `manifest.json` — accept that, since the orchestrator already made that decision upstream. Pass through without re-prompting if the underlying tooling allows.\n\n### 4.4 — `\u002Faudit-ppmplugin` (final verification gate)\n\nInvoke `Skill: audit-ppmplugin` on the `.ppmplugin` that `\u002Fassemble-ppmplugin` just produced (pass the bundle path). This is the gate that turns \"well-formed zip\" into \"will actually load on device\": it re-runs the validator rules against the built artifact, scans the DEX for SDK-era leakage (`INativeExtension*`, `sendAsync`, `HermesBytecodeLoader`, …), checks manifest↔bundle consistency and the source-to-receiver contract, and returns a verdict.\n\n- `DONE` (0 CRITICAL) → the bundle is verified; continue to Step 5 and report **READY TO UPLOAD**. Surface any WARNINGs in the final report.\n- `BLOCKED` (≥1 CRITICAL) → do NOT report success. Halt with the audit's CRITICAL findings and the owning-stage handoff (audit already routes each finding to `\u002Fgenerate-ppmplugin-manifest` or the build skill). The bundle exists on disk but is **not** upload-ready; the user fixes upstream and re-runs `\u002Fgenerate-ppmplugin`.\n\nBecause the orchestrator runs audit automatically, the user never invokes `\u002Faudit-ppmplugin` themselves on the happy path — it's the last internal stage.\n\n---\n\n## Step 5 — Report\n\nPrint the final deliverable as a visible block (informational, no question):\n\n```\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n \u002Fgenerate-ppmplugin — DONE\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n Bundle: ppmplugin\u002Fpen-input.ppmplugin   (v0.1.4)   ✓ audit: READY TO UPLOAD\n Target: Both (Android DEX + iOS framework)\n Steps:  manifest ✓  build-android ✓  build-ios ✓  assemble ✓  audit ✓\n Next:   • deploy the dispatcher PCF → \u002Fpublish-pcf-companion\n         • upload this .ppmplugin via the wrap wizard + wire the PCF into a\n           canvas app (Stage 3 — not yet a skill).\n```\n\nThen offer the actionable next step via `AskUserQuestion` (shared-instructions §9.1 — invoke via the Skill tool):\n- **Run \u002Fpublish-pcf-companion** (deploy the dispatcher PCF to a Power Platform env — needed before the control works in a canvas app)\n- **Run \u002Fdebug-extension** (debug\u002Frefine the control, then re-run \u002Fgenerate-ppmplugin)\n- **Stay — I'll upload the .ppmplugin manually** (Stage 3 isn't a skill yet)\n\nReturn `DONE` with the bundle path. Only report this block when audit returned `DONE` — a bundle\nthat failed audit is reported via the failure handoff below, never as success.\n\n---\n\n## Failure handoffs\n\nThe orchestrator's value is *one entry point on the happy path*. On a failure it should surface,\n**not absorb**. Each handoff names the failing stage and normally tells the user to re-run\n`\u002Fgenerate-ppmplugin` after fixing; direct stage invocation is reserved for a focused rerun or\ndiagnostic:\n\n| Failure | Handoff message |\n|---|---|\n| Manifest derivation blocked | `BLOCKED at manifest stage — \u003Creason>. Fix the flagged item, then re-run \u002Fgenerate-ppmplugin.` |\n| Android build failed | `BLOCKED at android-build stage — \u003Creason>. The manifest in ppmplugin\u002Fstaging\u002Fmanifest.json is preserved; re-run \u002Fgenerate-ppmplugin after fixing.` |\n| iOS build failed (Mac-only) | `BLOCKED at ios-build stage — \u003Creason>. If you don't have Xcode here, re-run on a Mac or pick \"Android-only\" target.` |\n| Assemble failed | `BLOCKED at assemble stage — \u003Creason>. The staged binaries are intact; re-run \u002Fgenerate-ppmplugin after fixing.` |\n| Audit found CRITICAL | `BLOCKED at audit stage — \u003CN> CRITICAL finding(s). The .ppmplugin was built but is NOT upload-ready. \u003Cfirst finding + its routed fix>. Fix upstream, then re-run \u002Fgenerate-ppmplugin.` |\n\nNever report a partial or unverified `.ppmplugin` as success. A bundle missing a declared\nentrypoint, or carrying SDK-leakage in its DEX, will fail during upload or silently on device;\nsurface the gap here instead.\n",{"name":5,"model":25,"description":7,"allowed-tools":45},"Read, Write, Edit, Bash, Glob, Grep, AskUserQuestion, Skill","main","0a55a88fa2855404029d1e5450faf92878baf763","plugins\u002Fpower-apps-mobile-extension\u002Fskills\u002Fgenerate-ppmplugin",232,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills","https:\u002F\u002Fmicrosoft.github.io\u002Fpower-platform-skills\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 21:46:39",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add microsoft\u002Fpower-platform-skills --skill generate-ppmplugin",{"tool":62,"command":63},"bunx","bunx skills add microsoft\u002Fpower-platform-skills --skill generate-ppmplugin",{"tool":65,"command":66},"pnpm","pnpm dlx skills add microsoft\u002Fpower-platform-skills --skill generate-ppmplugin","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpower-apps-mobile-extension\u002Fskills\u002Fgenerate-ppmplugin\u002FSKILL.md",true,[],[71,79,99,122,140,154],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":78},"01M78JN2BFRRV1J54Q6WKZQ08D","compare-site-configurations","Compare Power Pages site configurations between two environments, such as dev, test and production, or between a local download and the live site, and explain which differences change site behavior. Use when a site works in one environment but not another (for example, works in dev but fails in test), to check configuration drift before promoting or deploying, or to see what changed between two sites. Produces a shareable HTML report and a JSON file that VS Code can import.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fpower-pages\u002Fskills\u002Fcompare-site-configurations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":40},"01M699WVHX0XN59EPBTTPEKYPG","setup","Use when Process Intelligence needs building, explicit cloud\u002Faccount\u002Fenvironment configuration, sign-in, connection diagnostics, or recovery from an authentication error.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Fsetup\u002FSKILL.md",[],[81,86,87,88,89,90,91,92,93,94,35,95,96,97,34,98],"configuration","diagnostics","error","environment","cloud","when","connection","authentication","use","recovery","process","sign","intelligence",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":110,"publishedAt":40},"01M699WSR9EX55YY1WD9J22FEG","report-issue","Use when the user wants a Process Intelligence bug-report draft or support summary for a failed operation.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Freport-issue\u002FSKILL.md",[105],{"categoryNo":106,"categoryName":107,"taxonomyType":108,"taxonomyTypeDesc":109},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[111,112,113,114,94,91,115,116,96,117,98,118,119,120,121],"issue","report","report issue","bug-report","operation","draft","bug","summary","user","for","support",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":40},"01M699WR26YQ9Q21KE6MJF5B2G","investigate-process","Use when a broad Process Mining business question, observed pattern or competing explanation needs investigation across analytical perspectives.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Finvestigate-process\u002FSKILL.md",[],[129,96,130,131,94,132,133,91,134,135,136,34,137,138,139],"investigate","investigate process","question","process mining","business","across","perspectives","mining","pattern","investigation","analytical",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":40},"01M699WP9SDG5ZR12P8VYNXKTN","derive-metric","Use when a requested measure is missing, a saved custom metric needs reuse, or an ephemeral formula or derived scalar is needed.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Fderive-metric\u002FSKILL.md",[],[147,148,149,150,151,152,94,91,153,34],"metric","derive metric","missing","formula","custom","reuse","saved",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":40},"01M699WMG5R8P6SMTDAS1TKF9E","compare-cohorts","Use when comparing process cohorts, departments, periods or before-and-after results under matched definitions.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fpower-platform-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprocess-intelligence\u002Fskills\u002Fcompare-cohorts\u002FSKILL.md",[],[161,162,94,91,163,96,34],"compare","compare cohorts","results"]