conf-app

Enable, launch, monitor, troubleshoot, and stop the local joint-debug environment across conf-app, its Cloudflare Worker, ngrok, Forge tunnel, and diagramly.ai. Use for requests mentioning joint-debug, join-debug, combined local AI Repair testing, starting or monitoring the five-service stack, or closing that stack.

Get the per-space macro count for ONE named client (Confluence tenant/domain), triangulated across three independent sources: Metrics KV (current inventory), Cloudflare D1 (lifetime rows), and Mixpanel (90-day distinct macros viewed). Use whenever a request names one specific tenant (e.g. acme-corp, "our biggest lite customer") and asks how many macros or diagrams it has per space, wants to size a tenant against the Lite 100-macro paywall, reconcile per-space counts that disagree between KV/D1/Mixpanel, spot spaces with many macros but few recent views, or count distinct macros viewed per space over the last N days — even when only one source is named. Prefer this over conf-app, mixpanel, duckdb, or growth whenever the subject is one named tenant and the answer is a per-space macro tally. Do NOT use for product-wide totals across all tenants (use conf-app), single-page macro counts (find-macros-on-page), render-time/duration metrics (rendering-perf), install/marketplace counts (forge-installs), or one-off KV

Manage the ZenUML Lite paywall rollout (Lite variant only — Full and Diagramly have no restrictions). Decide which domains to enroll in CUSTOMER_SUCCESS_SERVICE (CSS), monitor daily paywall activity, and generate the exact KV commands to execute. Use this skill whenever the user asks about paywall rollout, which clients to enable, the CSS flag, tenant enrollment state, space licensing, or "who should be on the paywall list". Also use when the user asks to check a specific domain's paywall state, wants to understand why a tenant is or isn't seeing the paywall, or wants to A/B compare paywall impact (treatment vs. control tenants).

Near-term Atlassian Marketplace cash view for the ZenUML apps — what vendor income to expect over the next few days (client subscriptions renewing) and which paying clients missed a payment in the past few days (renewal lapsed / in grace / dead payment method). Use when the user asks "what income am I expecting", "what's landing this week", "any renewals coming up", "did anyone miss a payment", "who's late", "income projection for the next few days", or wants a daily payments radar. Built on the marketplace-audit engine (licenses + transactions joined on cloudId), payers only, all revenue apps. For lifetime revenue / top payers / a full renewals-in-a-window audit use `marketplace-audit`; for a single tenant's paid status use `tenant`.

Audit Atlassian Marketplace vendor reporting (licenses + sales transactions) for the ZenUML apps at the PORTFOLIO / cohort level — lifetime vendor revenue, renewals due in a date window, annual vs monthly billing, overdue / lapsing payers, top payers, churned payers. Use whenever the user asks about revenue, renewals, "who's overdue", "which annual customers renew this month", biggest paying customers, or any rollup across the customer base — even if they don't say "Marketplace". For a SINGLE tenant's paid status / size / profile ("is <domain> a paying customer", "look up <domain>", trial expiry), use the `tenant` skill instead. Discriminator: a cohort / time-window / ranking -> this skill; one domain in the question -> `tenant`. Prefer this over ad-hoc curl: it uses the fast bulk export endpoint and joins licenses to transactions correctly on cloudId (naive approaches truncate at a 50-row page cap and undercount revenue). Also hosts the shared engine (`scripts/mp_report.py`) + `sync` snapshot that the `tenan

Fulfil a Lite paywall lockout / "temporary editing extension" request — grant a temporary license that lifts the Lite per-space 100-macro limit, by default for ONLY the requesting user, then draft the customer reply. Use whenever a customer (via the JSM extension-request flow or direct email) asks to re-open editing on a space that hit the diagram limit, or when handed a request with a client domain + space key + macro count. It resolves the cloudId, verifies the exact space key, writes the SPACE_LICENSE_KV record, verifies it, computes the Full-plan upgrade price, and drafts the reply from the canonical template. Triggers on "extend", "extension request", "temporary editing extension", "grant a space license", "re-open editing", "paywall lockout", "lift the limit for <space>", "request: temporary Lite editing extension". For the reply template + sent log see the handbook page paywall/extension-request-replies.md; for per-space macro counts use macro-count.

Look up ONE Confluence tenant (by domain / slug / cloudId) and answer "is this a paying customer, how big are they, what state are they in" — across all ZenUML apps (Full / Lite / Diagramly), including the Lite Stripe/KV space-license layer. Use whenever the question is about a SINGLE tenant: "is <domain> a paying customer", "look up / who is <domain>", "tenant profile", "how big is <domain>", "is X on a trial / when does the trial expire", or a tenant's paid status for a paywall / conversion / extension-request decision. For cohort / rollup / portfolio questions (total revenue, renewals due in a window, overdue payers, top payers) use the `marketplace-audit` skill instead. Discriminator: one domain in the question -> this skill; a cohort/time-window/ranking -> marketplace-audit. Triggers on tenant, whois, "is <domain> paying", paid status, tenant lookup, cloudId, tenant profile, tenant size, trial expiry.

Detects Lite paywall bypassers from the paywall_gate_evaluated Mixpanel event — users who SAVED a macro on a genuinely over-limit, CSS-on, unpaid space where the fail-open gate silently did not fire (#302). Produces a ranked per-tenant conversion-targeting report (confirmed vs unconfirmed tiers + an Enterprise-Bundle revenue floor) plus a JSON sidecar for later customer-recovery ingestion. Use when the user asks to find paywall bypassers, who is bypassing the Lite 100-macro limit, who is getting the paid feature for free, fail-open leak detection, "#302 bypass", or wants a per-tenant list of over-limit Lite users slipping past the paywall.

List ZenUML (and other) macros on any Confluence page in render order, with their customContentId, type, title, and ADF localId — and fetch a chosen macro's stored body (DrawIO XML / Mermaid / PlantUML / ZenUML DSL / OpenAPI). Two operations, one skill. Use whenever investigating a customer page, locating which macro to inspect/reproduce, correlating "the third diagram on page X" to a specific customContentId, or extracting a stored macro source for rebuild. Triggers on "what macros are on this page", "find the macro at <URL>", "fetch the macro source", "extract macro XML", "rebuild this customer's macro", or any starting step of a customer-page investigation.

Drive the ZenUML Graph (DrawIO) macro through any entry point — slash-menu insert, in-editor Edit, copy-then-edit fallback, or view-mode Edit — and into the inner DrawIO editor to append a timestamp shape and Publish. Classifies the save outcome as success or did-not-persist, and records whether the paywall was observed. Use whenever you need to verify a Graph macro insert / edit / save end-to-end via Playwright MCP without re-deriving the Forge → DrawIO iframe chain. Triggers on "insert graph macro", "edit graph macro", "publish graph", "spot check drawio publish", "test graph save", "verify graph publish on lite", or any ad-hoc Graph-macro MCP spot check on lite-stg / full-stg / dia-stg / zenuml-stg / prod.

[today] [1d] [1w] — Quick health check of ZenUML Confluence app via Mixpanel. Queries key events (macro_viewed/view_macro, macro_create_succeeded/create_macro_end, macro_save_succeeded/edit_macro_end, save_failed) across time windows, broken down by event_category, compared to previous period and same time last week. Flags anomalies like zero views or error spikes. Use when the user wants to check app health, verify the app is working after a deploy, monitor event volumes, or investigate if something is broken. Triggers on "health check", "is the app working", "check mixpanel", "any errors", "event volumes", "is anything broken", "post-deploy check", or any request to verify the conf-app is healthy.

Inspect MacroMetrics KV cache for a domain and space. Usage: /metrics <domain> [space] Returns stored metrics data with diagnostic information (status, freshness, available spaces). Triggers on "check metrics", "metrics for domain", "inspect KV cache", "metrics data", "is metrics data available", "why no metrics".

Focused production validation for the AI Repair flow in diagram editors: syntax error banner, AI Repair modal, asynchronous fix-diagram job polling, editable diff, Apply Code, and save/render after applying the repair. Invoked by release-app Step 2.6 when AI repair, SyntaxErrorBox, GenerateService, diagramly fix-diagram, or validation/error-surface commits are detected. Triggers on "pvt-ai-repair", "test ai repair", "validate ai repair", "repair broken diagram".

Focused production validation for the paywall WARNING page-banner (Lite, 85–99 macro band) on the single `zenuml-page-banner` Forge pageBanner host. Covers render + count, both CTAs (Copy admin message, Request extension), dismiss/7-day snooze, the critical-band (100+) no-banner boundary, the below-band (<85) no-banner case, and single-host priority (paywall outranks CSAT). Checks Mixpanel events (paywall_banner_shown, paywall_banner_dismissed, advocacy_message_copied, extension_request_clicked — all surface=page_banner). This is the full granular matrix; CI keeps only a slim 3-test subset in tests/e2e-tests/tests/insert/paywall-page-banner.spec.ts. For the paywall MODAL (100+ hard gate) use pvt-paywall instead. Triggers on "pvt-paywall-banner", "test paywall banner", "validate warning banner".

Production Validation Testing (PVT) — quick sanity check immediately after a release. Runs Mermaid only on production to confirm the app is live and the new version is rendering. Not a full smoke test — CI already handles that. Use after /release-app completes. Triggers on "pvt", "production validation", "validate release", "validate production".

Create a Confluence page with one or more ZenUML macros entirely via REST API — no browser, no editor UI. Use whenever you need to render a macro with specific content (e.g. a known-wide DrawIO XML, a specific Mermaid input) to validate a rendering change. Triggers on "create test page", "render test", "API test page", "skip the editor", or when validating a viewer/renderer fix. Built for ZEN-1168-style use cases.

Use when you need a Mixpanel fact or query path for the conf-app / ZenUML Confluence add-on — which project, which event name (and the 2026-04 rename), the internal-domain exclude filter, whether isForge/isLite/product_type is usable, MCP-vs-JQL, or how to authenticate. Canonical reference for Mixpanel project 3373228. Triggers on mixpanel, macro_viewed, view_macro, create_macro, edit_macro, JQL, is_internal_client_domain, product_type, isForge, "which mixpanel project", "how to query mixpanel". For churn/retention/growth/D1 analysis use the conf-app skill instead.

Read the deployed version label from a live Forge macro iframe on any Confluence page. Covers enabling zenumlDebug in the correct (iframe) storage origin, reloading, and extracting the version string. Use after a release, in a spot check, or in PVT to confirm the expected tag is live.

Focused production validation for the Graph (DrawIO) macro: nested Forge + DrawIO iframes, title field, at least one shape on the canvas (required — avoids false PASS on empty diagrams), Publish from inner editor, and verified rendered geometry on the Confluence page. Invoked by release-app Step 2.6 when graph/drawio-related commits are detected. Triggers on "pvt-drawio", "test drawio", "validate graph macro".

Focused production validation for the macro edit path (Forge custom UI modal, editor mount, Publish). Confirms opening Edit from the viewer loads the editor iframe and can publish or cancel without blank states. Invoked by release-app Step 2.6 when editor-related commits are detected. Triggers on "pvt-edit", "test macro edit", "validate editor", "pvt-editor".

Focused production validation for macro fullscreen / expanded viewer (Forge fullscreen modal bridge). Opens fullscreen from the viewer toolbar, verifies the diagram remains usable, then exits cleanly. Invoked by release-app Step 2.6 when fullscreen-related commits are detected. Triggers on "pvt-fullscreen", "test fullscreen", "validate fullscreen viewer".

Focused production validation for the paywall modal across both trigger paths: Edit (existing) and Fullscreen viewer (added 2026-05-17). Tests every interactive element, every dismissal path, post-dismiss state per trigger, and Mixpanel events (upgrade_modal_shown, paywall_triggered with action_type={page_editor,fullscreen_viewer}, advocacy_message_copied with ui_component=modal, paywall_continued_editing). Invoked automatically by release-app Step 2.6 when paywall-related commits are detected. Triggers on "pvt-paywall", "test paywall", "validate paywall".

Focused production validation for the OpenAPI / Swagger macro: insert or open editor, set title, publish, and verify rendered spec viewer in the Forge iframe. Invoked by release-app Step 2.6 when swagger/openapi-related commits are detected. Triggers on "pvt-swagger", "test openapi", "validate swagger macro".

Focused production validation for manual syntax-error repair in code-based diagram editors: syntax error detection, SyntaxErrorBox visibility, direct human correction in the editor, error clearing, preview render, save, and published render. Use this when parser validation, SyntaxErrorBox, editor validation, error-surface, Mermaid/ZenUML/PlantUML/OpenAPI syntax handling, or non-AI repair commits ship. Triggers on "pvt-syntax-repair", "test syntax repair", "validate syntax error repair", "manual syntax repair", or "repair syntax error without AI".

Release ZenUML Forge apps (lite, full, diagramly, and/or asyncapi) to production via the full CI/CD pipeline. Reuses an existing fresh draft release when available (the common case after a recent merge), composes delta-derived release notes (replacing the auto-draft placeholder), publishes it to production, verifies with PVT, then runs a spot check — targeted coverage for what shipped this iteration (not keyword→skill matching alone). Falls back to triggering a fresh build via a changelog push only when no recent draft exists. Use when the user wants to release, deploy, ship, or push the lite, full, diagramly, or asyncapi Forge app to production. Triggers on "release lite", "release full", "release diagramly", "release asyncapi", "deploy to prod", "ship forge app", "push to production", "release forge app", "release app", or any request to promote staging builds to production for the conf-app project.

Ad hoc, AI-driven verification of a specific behavior — not a checked-in E2E test. Use after developing a feature, fixing a bug, validating a branch, or post-release. Drives Playwright MCP for Forge iframe UI, or CLI for backend/analytics signals. Triggers on "spot check", "run a spot check on X", "spot check this fix", "spot check on staging", "spot check zenuml-lite@stg", "verify on staging".

Rendering performance analysis for ZenUML macros. Queries Mixpanel macro_viewed duration_ms percentiles by macro type, compares against baseline, and guides investigation of regressions or improvements. Usage: /rendering-perf Triggers on "rendering performance", "how fast do macros render", "p50 p90 p99", "duration_ms baseline", "render time regression".

Generate or update the user-facing product guide for the ZenUML Confluence Add-on. Reads source components, captures Playwright screenshots from staging, and writes/updates docs/product-guide.md. Use after new features are merged, for release updates, or when the user asks to "update product docs" or "document this feature".

Create a branch, run local validation, create a PR and **merge** on main with staging deployed and draft releases created. Use when the user says "ship", "ship it", "ship this branch", "merge this", or wants to go from local branch to merged in one command. Stops at the first failure. Does NOT deploy to production — use /release-app after shipping.

Push the current branch and create or reuse a PR on ZenUml/conf-app. Use when the user says "submit", "create PR", "push and PR", "open a pull request", "submit branch", or wants to publish their work as a PR without merging. After the PR exists it always babysits CI (via babysit-pr — monitor + auto-fix). Does not merge — use land-pr for that.

[on <site>] [lite|full|diagramly] [macros...] Sites: zenuml-stg (default), zenuml, lite-stg, full-stg, dia-stg, diagramly. Smoke test ZenUML Confluence Cloud macros (ZenUML, PlantUML, Mermaid, Graph/DrawIO, OpenAPI). Uses the Playwright MCP to create a test page, insert macros, publish, and verify rendering. Triggers on "smoke test confluence", "test macros on staging", "verify ZenUML on confluence", "run smoke test on zenuml-stg", "test lite macros", or any macro validation request.

Navigate to the Diagramly admin panel on a Confluence site and interact with admin features (enroll space for demo page, etc.). Triggers on "diagramly admin", "enroll space", "create demo page admin".

Download a Confluence page attachment to local disk. First explains the 5 ways an attachment can be downloaded (so the developer learns the trade-offs), then automates the easiest one. Use when investigating customer issues that require the original PNG/PDF/file backed up against a customContent, recovering source from PNG iTXt embedded metadata, or any time a Confluence attachment needs to land on disk. Triggers on "download the attachment", "get the PNG", "save attachment to disk", "extract iTXt", "pull attachment", or any follow-up step after `find-macros-on-page` reveals a backup attachment.

[lite|full|diagramly|all] — Count Forge app installs per environment (production / staging / development) for any of the three ZenUML conf-app variants, plus delta vs prior snapshots from 1 day and 7 days ago (which sites were added / removed since the last check). Use whenever the user asks "how many installs", "how many tenants", "how many customers have installed [variant]", "install count", "any new installs", "did anyone uninstall", "active sites", "where is [variant] installed", "list installs", "show installed sites" — including bare phrases like "diagramly installs", "lite installs", "full installs". Source-of-truth is Atlassian's Forge platform via `forge install list` — the D1 `ForgeInstallation` mirror has been observed significantly out of sync (e.g. 7 D1 rows vs 49 actual installs for diagramly, and the last D1 row was from Apr 9 despite weeks of new installs since), so always use this skill, not a D1 query, when the user wants accurate counts or recent-install signal.

Run local validation checks on the current branch before shipping. Use when the user says "validate", "check branch", "am I good", "run tests", "preflight", "is this ready", or wants to verify their branch passes all checks before pushing or creating a PR. Also use as a precondition check before invoking submit-branch or ship-branch.

Prepare weekly meeting data — fetches 30-day Marketplace revenue, new/large/lost customers, and updates the "Weekly Meeting Prep" panel at the top of the client profiles homepage (http://localhost:52401/). Use when the user says "weekly meeting", "prep for the meeting", "update the weekly meeting section", or "what's our revenue this week".

E2E test for Confluence's "Make a copy" page action against pages that contain ZenUML macros (sequence, graph/DrawIO, OpenAPI). Verifies that after copy-then-edit, the macro on the new page correctly references a custom content owned by the new page — not the source page's customContent. Drives the test via Playwright MCP and the Confluence REST v2 API. Non-destructive: never purges custom content, only inspects state. Use when the user says "copy macro test", "test page copy", "verify cross-page-copy fix", "run the copy e2e", or whenever they want to validate the cross-page macro writeback behavior (PR #124 / ZEN-1170) on any Forge site.

Run a Forge tunnel to test local code changes on a live Confluence instance. Use when the user wants to test a Forge app locally, run forge tunnel, debug a Forge app on a live site, or verify manifest/config changes before deploying. Triggers on "forge tunnel", "tunnel to confluence", "test locally on confluence", "run tunnel", "test on diagramly", "test on lite-stg", or any request to proxy local Forge app code to a live Atlassian site.

Monitor and fix failing GitHub Actions CI checks on PRs for ZenUml/conf-app. Use when the user says "babysit PR", "check PR status", "fix CI", "PR is failing", "watch this PR", "why is CI red", or when used with /loop to continuously monitor a PR. Also use when staging deploy failures, E2E test flakiness, lint issues, or unit test failures block merging. Triggers on any PR monitoring, CI failure diagnosis, or automated fix-and-retry workflow.

Merge a green PR to main and verify CI succeeds (staging deploy + draft releases). Use when the user says "merge", "land", "land PR", "merge this", or when a PR has passed CI and is ready to merge. This does NOT deploy to production — use /release-app for that.