Showing 34081–34110 of 77202 skills
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".
ZenUml/conf-app
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".
ZenUml/conf-app
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".
ZenUml/conf-app
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".
ZenUml/conf-app
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".
ZenUml/conf-app
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".
ZenUml/conf-app
Guard-rails for deriving aggregate claims ("X% of diagrams are abandoned", "cross-space duplication is rare") from stored product data — D1 CustomContent bodies, Mixpanel events, any bulk store. Use when analyzing diagram content at scale, counting defaults/templates/unused content, measuring duplication or reuse, joining content to tenants, or whenever a percentage derived from a LIKE/GROUP BY query is about to drive a roadmap decision. Triggers on "analyze the data", "how many diagrams", "what fraction", "abandoned", "unedited defaults", "cross-space", "duplicate content", "query CustomContent".
ZenUml/conf-app
Mark a conf-app PR Ready for Review after validating its current E2E decision, or run its approved E2E scope while keeping it Draft.
ZenUml/conf-app
Release one named ZenUML Forge variant (lite, full, diagramly/dia, asyncapi/async/api) to production. The script selects the draft, enforces the canary gate, publishes, and waits for production smoke. Use when the user asks to release, deploy, ship, or promote a named variant, or asks for `release-app preflight`.
ZenUml/conf-app
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".
ZenUml/conf-app
Reproduce a bug in the conf-app. Extract the bug from the current conversation or user prompt, then try to reproduce it in the simplest available environment. Use when the user says "repro", "reproduce", "can you repro this", "reproduce the bug", "verify this bug", or describes a bug they want confirmed. Try environments in strict order: local dev server first, then conf-stg-lite.zenuml.com, then conf-lite.zenuml.com, then real Confluence as last resort.
ZenUml/conf-app
When the user wants to add, fix, or optimize schema markup and structured data on their site. Also use when the user mentions "schema markup," "structured data," "JSON-LD," "rich snippets," "schema.org," "FAQ schema," "product schema," "review schema," "breadcrumb schema," "Google rich results," "knowledge panel," "star ratings in search," or "add structured data." Use this whenever someone wants their pages to show enhanced results in Google. For broader SEO issues, see seo-audit. For AI search optimization, see ai-seo.
ZenUml/conf-app
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 agent-browser 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".
ZenUml/conf-app
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. Classify its E2E scope with pr-labeling, then babysit executable CI; unresolved scope enters manual test triage. Does not merge — use land-pr for that.
ZenUml/conf-app
Read and triage the ZEN service-desk queue on zenuml.atlassian.net — what tickets are open, who is waiting on a reply, which granted extensions are about to expire. Use for any QUEUE-shaped question: "any new tickets", "who is waiting on me", "did this tenant ever file a ticket", "what came in since a given date", "工单", "谁在等回复", "有没有新工单", or when a paywall/churn analysis needs the support-ticket signal. Read-only. To FULFIL a specific request (write the KV licence, draft the reply) use `extend-space-license` instead. Discriminator, one rule: the question names a specific ticket or hands over a request to fulfil uses `extend-space-license`; the question is about the queue, a time window, "anything new", or who is waiting uses this skill.
ZenUml/conf-app
Look up verified Confluence tenant seat counts (Marketplace license users), product, license, payment, contact and pricing facts. Use for one site or a batch whenever the request asks for seats, license users, user count, site size or license tier (席位、座席、用户数), and for tenant profiles, paid status, trials or potential annual value. Reuses Marketplace exports and the separate Lite KV layer; customer-followup owns action decisions.
ZenUml/conf-app
Test PDF and Word export of ZenUML diagrams on a live Confluence site. Logs into the target site, triggers export, downloads the file, and verifies diagram images are embedded. Also checks Forge logs for errors. Use when the user says "test pdf export", "verify pdf", "check export", "test export", "does pdf work", "export test", or after deploying export function changes. Triggers on any PDF/Word export verification request.
ZenUml/conf-app
Test the space license admin API and verify it lifts macro restrictions on a live Confluence instance. Use when the user says "test space license", "test licensing", "verify space license", or wants to validate the Enterprise Bundle licensing flow end-to-end. Runs API CRUD tests + Confluence E2E verification.
ZenUml/conf-app
Autonomous feature development using a Planner-Generator-Evaluator architecture inspired by GANs. Use when the user says "harness", "three-agent", "build feature autonomously", "plan-build-test loop", or wants a complete feature implemented end-to-end with AI-driven QA. Takes a brief prompt and delivers a tested, working feature through iterative sprints.
ZenUml/conf-app
Run ordered local and staging validation 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 before pushing or creating a PR. Also use as a precondition check before invoking submit-branch or land-branch.
ZenUml/conf-app
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".
ZenUml/conf-app
Automate Blender scenes with the bpy Python API, build Geometry Nodes workflows, configure Cycles or EEVEE renders, and troubleshoot headless batch jobs.
alivirgo/Major-AI-Skills
Script Cinema 4D scenes with c4dpy and the Maxon API, wire MoGraph/Fields systems, and debug Redshift GPU renders, AOVs, and headless Commandline farm jobs agents routinely miss.
alivirgo/Major-AI-Skills
Build Godot 4 scenes and GDScript workflows, inspect physics behavior, and configure headless project exports.
alivirgo/Major-AI-Skills
Automate Houdini with VEX and hou/hython, cook PDG/TOPs graphs, tune Vellum/FLIP/Pyro solvers, and debug Solaris/Karma XPU renders agents routinely miss.
alivirgo/Major-AI-Skills
Automate Substance 3D Painter texturing with the Python API, bake mesh maps safely, pack PBR exports for Unreal/Unity, and debug UDIM, TDR, and color-space failures agents routinely miss.
alivirgo/Major-AI-Skills
Automate Unity editor and runtime workflows with C#, Addressables, render pipelines, and batch builds.
alivirgo/Major-AI-Skills
Build Unreal Engine workflows with Blueprints, C++, editor Python, and Unreal Automation Tool build or packaging jobs.
alivirgo/Major-AI-Skills
Automate ZBrush with ZScript macros, run ZRemesher and Decimation Master safely, extract 32-bit displacement/normals, and debug GoZ and multi-million-poly viewport failures agents routinely miss.
alivirgo/Major-AI-Skills
Test authorized agents against indirect prompt injection in retrieved docs and tool outputs using paired clean/poison fixtures, synthetic canaries, and sandboxed tools. Evidence for these cases—not a claim injection is solved.
alivirgo/Major-AI-Skills