adityaarsharma

Polylang compatibility audit — pll_register_string, pll_current_language, custom-post-type translation, language switcher hooks, REST + WP-CLI integration. Polylang has free + Pro versions; covers both. Use when the user says "Polylang compat", "Polylang translate", "WPML alternative", or coexisting with Polylang.

WPML compatibility audit — translatable strings via icl_t / wpml_register_string, custom-post-type translation, taxonomy translation, language switcher hooks, current-language detection, sitemap-per-language, and the wpml-config.xml registration file. Use when the user says "WPML compat", "WPML translate strings", "translation plugin", or before customer asks "does this work with WPML?".

Run the full Orbit gauntlet — 11 sequential checks on a WordPress plugin (PHP lint, PHPCS, PHPStan, asset weight, i18n, Playwright, Lighthouse, DB profile, competitor compare, UI perf, AI skill audits, PM UX). Three modes — `quick` (3-5 min, dev loop), `full` (30-45 min, RC pass), `release` (45-60 min, WP.org submission). Use when the user says "run gauntlet", "audit my plugin", "full QA", "before release", or any unscoped "check my plugin" request.

PHP↔JS label parity audit — verifies every label key consumed by JS via `wp_localize_script` / `wp_set_script_translations` is actually emitted from PHP. Catches the silent-English-fallback bug where JS reads `myObject.someLabel` but PHP never put `someLabel` into the localized object. Use when the user says "JS label", "wp_localize_script", "Elementor editor label", "Gutenberg block label", "missing translation in JS", or before any release that touches block editor / Elementor / admin JS.

Runtime i18n correctness audit — catches the non-Latin data corruption bugs that gettext-style audits miss. Scans every wp_json_encode / json_encode call in paths that store post_meta, options, REST output, or LLM/external-API request bodies; flags any missing JSON_UNESCAPED_UNICODE | JSON_UNESCAPED_SLASHES flag. Also verifies Content-Type charset=utf-8 on REST responses. Use when the user says "i18n runtime", "Unicode encoding", "non-Latin characters", "Turkish broken", "CJK garbage", "data corruption on save", or before any release that ships to non-English locales.

Translator .po file currency audit — for every shipped /languages/<plugin>-<locale>.po file, runs `msgmerge` against the current .pot and reports the percentage of msgids that are missing, fuzzy, or obsolete vs the current source code. Catches the silent-English-fallback bug where a translator delivered 100% translation against an OLD pot, but new strings shipped since. Use when the user says "translator currency", "stale po", "translation drift", "translator delivered translation", "ship translations", or before any release that has shipped .po/.mo files.

Code-quality reviewer for WordPress plugins — finds dead code, complexity hotspots, error-handling gaps, type-safety issues, AI-hallucination risks (made-up WP function names, wrong sanitize choice, missing nonce, class-name case drift, method API drift), AND the WordPress runtime traps that only break on a live install (Settings API cross-nulling, DISABLE_WP_CRON assumptions, conditional add_rewrite_rule, bulk option restore wipes, %currentyear% literals in third-party SEO plugin meta, Gutenberg block-comment false-positive text checks, tab/router slug mismatch, Pro/Free shadow-class conflicts, cross-plugin filter timing). Use when the user says "code quality", "vibe code review", "review AI-generated code", "find dead code", "complexity audit", "why didn't Orbit find this", or after merging a Cursor/Copilot-assisted PR.

Auto-draft release notes for a WordPress plugin from CHANGELOG.md + git diff + visual regression diffs. Generates user-facing announcement (blog post, email, in-plugin notice), readme.txt changelog, GitHub release notes, and a tweet-thread. Use when the user says "release notes", "draft announcement", "changelog → blog post", "what to write for v2.4".

Pickle for ClickUp — scans every ClickUp channel, DM, and group DM you follow for a given time window. Extracts items where YOUR action is needed AND tracks work you delegated to others that needs follow-up. Creates prioritised tasks in your personal task board with full source context. Usage: /pickle-clickup [time] [followup] — e.g. /pickle-clickup 24h | /pickle-clickup 7d followup

Pickle for Slack — scans every Slack channel, DM, and group DM you're in for a given time window. Extracts messages where YOUR action is needed AND tracks work you delegated to others that needs follow-up. Creates entries in a dedicated Slack List (or Canvas fallback) + sets Slack reminders — all kept SEPARATE from any other tool. Usage: /pickle-slack [time] [followup] — e.g. /pickle-slack 24h | /pickle-slack 7d followup

Pickle for Microsoft Teams — scans all your Teams channels, chats (1:1, group, meetings), and DMs for a given time window. Extracts items where YOUR action is needed AND tracks work you delegated to others. Creates tasks in Microsoft To Do. Usage: /pickle-teams [time] [followup] — e.g. /pickle-teams 24h | /pickle-teams 7d followup

[DEPRECATED in v1.2.0] Pickle no longer ships a client-side updater. Updates flow server-side automatically. This skill prints a migration notice and exits.

YouTube Marketing MCP — 21-command suite for YouTube creators. Covers SEO, scripts, hooks, thumbnails, analytics, content calendar, Shorts, batch updates, WordPress publishing, and plugin demo workflows. Triggers on any /youtube command or YouTube-related marketing request. Always pull live data before generating recommendations.

Server intelligence layer for RunCloud-managed Linux servers. Use when the user mentions Perch, /perch_*, RunCloud, nginx-rc, server intelligence, server diagnosis, WordPress site auditing, plugin vulnerability scanning, or any time they want to investigate, monitor, or heal a server they own.