MADEVAL

Project-level CLI entrypoint script: shebang, bootstrap and delegation to the framework command handler.

Use when working on Atomic CLI commands, API entrypoints, console input/output, scaffolders, init flows, migrations/queue/scheduler CLI subcommands, or command-facing bootstrap logic.

Use when working on Atomic App layer (Controller, Model, Page, Storage, PluginManager), Auth flows (Auth, GoogleAuth, TelegramAuth, adapters, services), Session (SessionManager, drivers), and app-level models (Meta, Options, MutexLock).

Use when working on Atomic Core: bootstrap, config loading, App class, request/response helpers, routing, middleware, logging channels, error handling, Prefly checks, DB connections, migrations, crypto, guard roles, ID generation, upload, filesystem, and all route-loader behavior.

Use when working on Atomic data layer: Model, Validator, cache drivers, Codes, Enums, Exceptions hierarchy, file exports (PDF/XLS/CSV), and Support helpers.

Use when you need a fast cross-reference of all 44 Atomic Framework documentation files to find which doc covers which subsystem, feature, or integration.

Use when working on Atomic events (dot-notation typed event bus), hooks (WordPress-style add_action/add_filter), shortcodes, i18n localization, mail sending (Mailer, Notifier), or text-extensibility features.

Use when working on Atomic mutex (distributed locking), session lifecycle, session storage drivers, nonces (one-time tokens), or transient cached values.

Master skill for rewriting AI-generated text to sound human-written across 9 languages: English, Russian, Ukrainian, German, French, Spanish, Portuguese, Italian, Polish. Full pipeline: pre-flight → cleanup → specificity → tone → rhythm → proofread. 15 task-specific scenarios. For articles, posts, landing pages, commercial copy, translations, SEO content, emails, press releases, memos, grant proposals, creative writing - any text that currently 'smells like AI.'

Run a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed and works backward to find every reason why. Produces a revised plan with blind spots exposed, likelihood/impact scores on each failure mode, and a concrete committed action. MANDATORY TRIGGERS: 'premortem this', 'premortem my', 'run a premortem', 'what could kill this', 'future-proof this', 'stress test this plan', 'what am i missing here', 'find the blind spots'. STRONG TRIGGERS: 'what could go wrong', 'am i missing anything', 'poke holes in this', 'where will this break', 'devil's advocate this'. Do NOT trigger on simple feedback requests, factual questions, or LLM Council requests. DO trigger when someone has a plan or commitment where the cost of being wrong is high.

Content angle generator for turning dry expert topics into high-engagement infotainment. Applies 7 journalistic angle types (Myth vs Reality, Paradox, Level Error, Price of Solution, Conditions, Hidden Driver, Contrary Thesis) + historical/future lens + news-hook framing. Use when experts need their content to become interesting rather than just informative - blog posts, video scripts, social content, newsletters, landing pages, ad hooks. For any niche: B2B, B2C, services, products, personal brand.

Use when building, reviewing, debugging, packaging, or validating BotBlocker Security add-ons — WordPress anti-bot firewall extensions that ship as Add-on API v2 packages with a bbcs-addon.json manifest. Trigger keywords: BotBlocker add-on, bbcs-addon.json, Add-on API v2, addon lifecycle callback, settings.option sanitizer, traffic_decision_provider, runtime.pre_run, BotBlockerAddons::fileUrl, validate-addon, package-addon. Use ONLY for BotBlocker add-on development; do not use for general WordPress plugins or for editing BotBlocker core itself.