Structured TDD implementation pipeline: test writer -> implementer -> reviewer with compounding learnings. Callable only — invoke explicitly with /implement or 'use the implement skill'. Never auto-trigger.
Add internationalization to a WordPress plugin — text-domain wiring, locale-variant fallback compatible with WP 6.7+ just-in-time translation loading, composer i18n scripts, phpcs WP.I18n enforcement, CI POT-freshness gate, and a diagnostic for "__() returns the msgid" debugging. Use when adding translations to a WordPress plugin, wrapping strings in __() / esc_html__() / _x(), setting up a text-domain, generating .pot / .po / .mo / JSON files, fixing untranslated strings, or when the user mentions WordPress i18n, internationalization, translation, text domain, gettext, wp_set_script_translations, or load_plugin_textdomain.
Compact the current conversation into a handoff document for another agent to pick up.
WordPress local dev environment CLI tools (wp-local). Manage WordPress sites, run WP-CLI, debug, clone/pull from remote servers. Use when working with WordPress sites in ~/dev/wp-local, running WP-CLI commands, managing local WordPress containers, debugging WordPress, or syncing with remote servers.
Stage changes, create a conventional-commit-formatted git commit, and optionally push. Detects project commitlint config for repo-specific rules. Use when creating git commits, committing changes, or pushing code.
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.
Detect failed GitHub Actions runs, reproduce failures locally, auto-fix code issues, and report actionable steps for infrastructure failures. Use when user says "fix workflow", "fix CI", "fix pipeline", "why did CI fail", "check actions", or wants to investigate failed GitHub Actions runs.
Batch triage Sentry errors and GitHub bug issues — auto-fix clear bugs, flag complex ones. Use when user says "bug sweep", "triage bugs", "sweep errors", "check sentry", or wants to batch-process open bugs from Sentry and GitHub.