All Skills

Global style component that syncs theme styles to document.body. Invoke when user needs to apply global theme styles like background color and font family to the entire page.

Accept the recommendation from the most recent A/B/C option set and execute it without re-asking. Use when the user says "按你推荐的来" / "go with your pick" — they glanced at the options, the recommendation looked right, they don't want to re-read all of them.

End-of-session documentation sync — updates TODO.md and PROGRESS.md only (run /commit after to commit everything)

Autonomous discovery of concepts, methods, and vocabulary we have NOT heard of yet — sweeps broadly, diffs against a known-concepts ledger, and reports only what is genuinely new plus whether it names a gap in this stack. Built because 'graph engineering' had to arrive by word of mouth: a fixed topic list can only refresh what you already named, so it can never surface the thing you did not know to look for. Use for periodic/scheduled discovery, 'what's new in agent engineering', 'what are we missing', 'anything we haven't heard of'. Triggers: radar, discover, what's new, unknown unknowns, 新概念, 我们没听过的, 有什么没跟上的 — NOT for researching a topic you can already name (use /research), NOT for model releases (use /model-research), NOT for internal priorities (use /next).

Show a provider-neutral, freshness-aware snapshot of active Agent work, Git delivery, execution identity, and usage limits. Use for “what's going on right now”, what is running, progress updates, active runtime/provider/model, or stuck-work checks.

A/B test design and experiment planning for paid advertising. Structured hypothesis framework, statistical significance calculator, test duration estimator, sample size calculator, and platform-specific experiment setup guides (Meta Experiments, Google Experiments, LinkedIn A/B). Use when user says A/B test, split test, experiment design, test hypothesis, statistical significance, sample size, or test duration.

Inspect or select a Clade execution connection while keeping agent runtime, inference provider, wire protocol, and model distinct. Use for Claude/Codex runtime selection, Anthropic/OpenAI/MiniMax/Kimi/custom gateways, model routing, or connection troubleshooting.

Review an exact PR head in isolation using trusted-base instructions and execution evidence

Amazon Ads deep analysis covering Sponsored Products, Sponsored Brands (incl. Sponsored Brands Video), Sponsored Display (audiences + contextual), and basic Amazon DSP. Evaluates campaign structure, ACOS/TACOS targets, search-term harvesting, negative keyword discipline, Brand Analytics signals, day-parting, bid management, auto vs manual campaign mix, ASIN targeting, and DSP retargeting. Use when user says Amazon Ads, Amazon advertising, Amazon PPC, Amazon search ads, Sponsored Products, Sponsored Brands, Sponsored Display, Amazon DSP, ACOS, TACOS, retail media audit, Amazon Marketing Services, AMS, or Amazon seller advertising.

Show Codex rate-limit usage and pace, or configure the native Codex status line

SERP-based semantic topic clustering for content architecture planning. Groups keywords by actual Google SERP overlap (not text similarity), designs hub-and-spoke content clusters with internal link matrices, and generates interactive visualizations. Optionally executes content creation if claude-blog is installed. Use when user says "topic cluster", "content cluster", "semantic clustering", "pillar page", "hub and spoke", "content architecture", "keyword grouping", or "cluster plan".

Start-of-session context pickup. Reads the latest handoff file and resumes work where the last session left off. Run this at the start of a new session if a handoff file exists.

Translate existing blog posts into one or more target languages with SEO-optimized localization. Produces native-quality translations that preserve markdown structure, frontmatter, schema JSON-LD, image and chart embeds, and citation capsules. Localizes keywords, meta tags, numbers, dates, currencies, and quote styles per locale. Flags machine-translation artifacts for review. Run BEFORE blog-localize: this handles language conversion; localize handles cultural adaptation after translation completes. Use when user says "translate blog", "blog translate", "uebersetzen", "traduire", "traducir", "translate post", "blog auf Deutsch", "blog en espanol".

Cross-platform attribution health audit covering AdAttributionKit (iOS view-through 24h post-impression, WWDC 2025 configurable windows), GA4 attribution models (data-driven vs last-click), Consent Mode V2 enforcement, server-side attribution stitching, MMP integration health, and cross-device / cross-platform attribution. Use when user says attribution audit, attribution model, AdAttributionKit, AAK, view-through attribution, GA4 attribution, Consent Mode V2, conversion window, attribution window, MMP audit, AppsFlyer audit, Adjust audit, Branch audit, Singular audit, cross-device attribution, or cross-platform attribution.

Generate competitive SEO content briefs with per-section word counts, competitor scoring, keyword density guidance, and page-type templates. Supports both new page briefs and improve-existing-page briefs. Use when user says "content brief", "write a brief", "content outline", "blog brief", "service page brief", "brief for", "writing brief", "content plan", or "outline for".

Start, stop, or manage Clade autonomous coding loops remotely

Wydruki i raporty w Soneta (enova365, Triva) — pliki .repx (DevExpress XtraReports, serializowany XML). Sięgaj przy KAŻDYM zadaniu z wydrukiem/raportem: faktura, dokument, deklaracja, lista, zestawienie; utworzenie, przeróbka lub poprawa .repx (też z załącznika); pytanie „jak w wydruku zrobić X”. Typowe X: podpięcie danych (lista, dokument z pozycjami, master-detail, podraport), podział stron, kolumna Lp, tabele, grupowanie i sumy, formatowanie warunkowe, kwoty, nakładanie wartości na skan formularza, nagłówek/stopka/podpisy, arkusz stylów (.repss), rejestracja wydruku. Wyzwalają też pojęcia: XtraReportsLayoutSerializer, StyleSheetSerializer, pasma (DetailBand/DetailReportBand/GroupHeaderBand/SubBand), kontrolki (XRLabel/XRTable/AmountLabel), BusinessDataSource/DataKind, ReportContext, ExpressionBindings/Summary/CalculatedFields/FilterString, [assembly: DxReport], ReportSnippet/[DxBind]. Wystarczy „wydruk”, „raport” lub „.repx” w kontekście Soneta. NIE dla: business.xml, form.xml, SQL, Excel, Word .dotx.

REJESTR KONFIGURACJI (ConfigReg) platformy Soneta (enova365, Triva) od strony kodu C#: drzewo węzłów, providery `IConfigRegProvider` (Root/Module/Table/Row/SubRow/SubTable/Storage/Addins), atrybut `[ConfigReg(Hide/Ignore/Include/ChildrenType)]`, format `*.reg.json`, potok Loader → Differ/Merger → SessionUpdater. Używaj ZAWSZE gdy użytkownik: (1) pyta o rejestr konfiguracji, ConfigReg, `Soneta.Config.Reg`, tabelę `ConfigRegistry` lub menu „Zarządzanie konfiguracją"; (2) chce włączyć/wyłączyć tabelę, kolumnę lub węzeł z rejestru (`Ignore`, `Hide`, `Include`, `ChildrenType`); (3) pisze provider rejestru, obsługę zapisu (`SaveChild`, `delayed`), porównywanie (`ConfigRegDiffer`), scalanie (`ConfigRegMerger`), serializację (`RegConfigJsonConverter`); (4) buduje lub debuguje `*.reg.json` — sigile `$strict`, `$v`, `#klucz`, `@atrybut`, `$blob`, ścieżki `Business/FeatureDefs/Name=CECHA`; (5) przenosi ustawienia między bazami przez rejestr. Import/eksport przez XML (`dbinit.xml`) to INNY mechanizm → /soneta-config.

Tworzenie i konfiguracja definicji elementów wynagrodzenia na platformie Soneta przez MCP soneta_ui. Algorytmy naliczania (kreator, edytor C#, wbudowane), wzorce algorytmiczne, receptury kodu C# dla elementów płacowych, konfiguracja PIT/ZUS/nieobecności. Używaj gdy użytkownik: (1) chce utworzyć/skonfigurować definicję elementu wynagrodzenia (zakładki Ogólne, Deklaracje, Nieobecności, Algorytm); (2) pyta o algorytm naliczania (kreator, edytor, kod C#); (3) potrzebuje kodu C# do edytora algorytmu (_Param, _Wylicz, _Wartość1h); (4) pyta o wzorce dla dodatków, nieobecności, zasiłków; (5) wspomina 'definicja elementu', 'element wynagrodzenia', 'algorytm płacowy', 'WypSkladnik', 'WypElement', 'premia procentowa', 'dodatek stażowy', 'zasiłek chorobowy', 'ekwiwalent za urlop'; (6) pisze recepturę kodu płacowego (staż pracy, wymiar etatu, czas pracy, wskaźniki, cechy pracownika).

Grill the user relentlessly about a plan, decision, or idea — one question at a time — until shared understanding is reached. Use when the user says "grill me", "stress-test this plan", "interview me about this", "poke holes in this", "challenge my thinking", or before committing to a non-trivial design.

Audit and fix internationalisation for any web or mobile app. Use when asked to "audit i18n", "fix translations", "add locale", "natural language", "translation quality", "hardcoded strings", "localisation", or "the Japanese feels like Google Translate".

Write clear, developer-friendly documentation — READMEs, API references, code comments, and changelog entries — tailored to the audience and the project's voice. Use when the user says "write docs", "document this API", "update the README", "add code comments", "changelog entry", or "explain this for contributors".

Design and implement transactional and marketing email templates. Use when asked to "build an email template", "transactional email", "welcome email", "password reset email", "email design", "React Email", "MJML", "dark mode email", or "email copy review". Inbox / SPF / spam → enhance-email-deliverability.

Wire ETL, ingestion, cron, edge-function, and queue jobs correctly. Use for "build a pipeline", "sync X into Y", "nightly aggregation", "cron double-counts", "dedupe", "backfill", "the numbers are wrong after a retry". Bakes in idempotency, atomic writes, data contracts, dead-letter, and observability.

Co-author structured documents (specs, PRDs, RFCs) through a 3-stage workflow: context gathering, drafting, and reader testing. Use when writing proposals, technical specs, or similar structured content. Repo decision-memory system (INDEX.md, rejected alternatives, agent rules) → docs-adr.

Static OWASP review of app code (injection, headers, deps). Use when "review security" or "check vulnerabilities". Session/route×gate/getSession → audit-auth-flows. Plan-only burndown → plan-security-audit. Table RLS → plan-rls-audit. LLM attacks → audit-llm-security.

Audit whether a project can actually recover from data loss — not just whether backups exist — then emit a phased DR plan. Use when "can we recover if the DB dies", "audit our backups", "what's our RPO/RTO", or "disaster recovery". Plan only. Destructive-op gates stay on plan-data-integrity.

Audit a full-stack app against the RealWorld ("Conduit") reference — its formal API spec, shared Bruno/Hurl E2E suite, and closest-stack reference implementation — to find what is. Use when "audit against realworld", "compare my app to realworld", "conduit conformance", "is my full-stack app complete", "full-stack gap.

Apply-now consolidation of accreted CI gates, ratchets, and hooks into one aggregator required check. Use after audit-gate-logic, or when "clean up our CI checks", "we have three lint jobs", "make one quality gate". Audit-only → audit-gate-logic. Pipeline cost → audit-cicd.

Read-only audit of CI gate logic — silent bypass, ratchet gaming, conflicting conditions, required checks that are not, and accreted duplicate gates. Use when "can CI be bypassed", "why did a regression pass CI", "we have too many overlapping checks". Cost/speed → audit-cicd. Consolidation → housekeep-gates.

Implement real-time features using WebSockets, Supabase Realtime, Server-Sent Events, and live data. Use when user wants "real-time", "live updates", "WebSocket", "notifications", "chat", "collaborative", "presence", "live data", or "instant sync".

First-contact orientation for an unfamiliar codebase. Use when "I'm new to this repo", "orient me", "explain this codebase", "what does this do?", "onboard me", "first day on this project", or "catch me up on the codebase".

Cross-page UX audit for user stories, task completion, and information architecture — the layer audit-ux (per-page heuristics) skips. Use when "audit user flows", "IA audit", "can users find X", "navigation audit", or "funnel drop-off". Full DS burndown → plan-uiux-unification.

Guide for refactoring code to improve quality without changing behavior. Use when refactoring, cleaning up code, reducing duplication, improving readability, or restructuring code. Integrates Firecrawl for researching modern patterns before refactoring, and codebase-aware dependency analysis to avoid breaking changes.

Run a PDCA quality audit on LLM/AI features: traces, prompts, costs, evals, grounding, hallucination. Use for "audit LLM quality", "check Langfuse", "audit prompts", "check AI quality", "audit AI costs", "check traces". Jailbreak/OWASP LLM → audit-llm-security. Token caps → plan-llm-cost-guardrails.

Audit the working tree and git history for exposed credentials and mis-scoped keys, then a rotate-vs-relocate plan. Use when "hardcoded secrets", "did I commit a key", "secret scan", "is my .env safe", or "rotate keys". Do not fire for "RLS audit" or generic "security burndown".