Publish articles to Zhihu (知乎专栏) via automated browser. Triggers on "发知乎", "post to zhihu", "知乎专栏", "zhihu publish", "发布知乎", "知乎文章".
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against be — from…
Run axe-core / Pa11y / Lighthouse against changed pages and classify findings by WCAG level (A / AA / AAA)
Validate code against accessibility standards: WCAG 2.1 Level AA, EN 301 549, and the European Accessibility Act (EAA / Directive EU 2019/882).
Use when: writing, rewriting, or auditing acceptance criteria, definition-of-done lists, or user-story AC for quality: testable, observable, single, scoped, and…
Regression check — diff a live page's web accessibility (a11y) violations against a baseline. By default it compares your uncommitted changes (stash-based); pass `--branch…
One page, hands-on manual tier — drive a live page through the web accessibility (a11y) checks a rule engine can't decide: keyboard operation and focus order, screen-reader names,…
Run a WCAG 2.1 AA accessibility audit on a design or page. Trigger with "audit accessibility", "check a11y", "is this accessible?", or when reviewing a design for color c — from…
Prüft Websites und Web-Applikationen (insbesondere React und Angular) auf Barrierefreiheit nach WCAG-Standard.
One page, automated tier — run the web accessibility (a11y) rule engine against a live page and locate every violation it can detect mechanically.
Add a runtime gated feature flag (AppConfig-backed on prod, secret fallback off-prod), gated by org id, user id, or admin
Use this skill to add planned work discovered during execution to the end of the current milestone in the roadmap.
Mutate a card's status (open / active / blocked / disproved / superseded — everything except `done`).
Maquina de design UI/UX. 67 estilos, 96 paletas, 57 font pairings, 13 stacks. Design system, componentes, landing pages, dashboards. Integra com shadcn, Figma, v0.
Maquina autonoma de teste final. QAT textual, UX-QAT visual, benchmark comparativo, ciclo test-fix-retest, E2E batch — PDCA convergente com scores.
Adversarial review: tenta quebrar o design antes do build. Analisa SPEC/PRD e lista top 5 formas de quebrar, suposicoes implicitas, edge cases nao cobertos.
Avalia qualidade UX de um projeto comparando screenshots reais contra a Design Library (24 solucoes + design system).
Captura tela e controla mouse/teclado em apps nativos macOS via router 3-tier: macos-use (Accessibility tree, semantico — preferido) -> macos-automator (AppleScript/JXA) ->…
[INTERNAL — invocada via ag-4-teste-final] Cria cenarios UX-QAT de alta qualidade. Mapeia telas, seleciona rubrics visuais, define interacoes criticas, captura golden screenshots…
Executa incorporacao de um modulo seguindo o roadmap e task_plan. Implementa ACL, migrations, sync, UI adapters. Um modulo por vez.
Cria roadmap de incorporacao com fases, milestones, feature flags e task_plan. Transforma mapa de integracao em plano executavel.
UX-QAT PDCA Orchestrator — executa Visual Quality Acceptance Testing com ciclo Plan-Do-Check-Act. Captura screenshots por breakpoint/tema, avalia com AI Judge multimodal,…
Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance.
Designs AI features with provider abstraction, mock provider, schemas, fallback behavior, validation, privacy, and tests.
Fast, token-efficient codebase reconnaissance. Given a task, a set of changed files, or a question, it finds the relevant files, their dependents/callers, related tests, and any…
Create or update a project roadmap with major milestones. Generates the configured roadmap artifact (default .ai-factory/ROADMAP.md) — a strategic checklist of high-level goals.
Vet an open-source product for air-gap readiness BEFORE adoption. Answers eight questions — telemetry, does-opt-out-actually-work, proxy-in-disguise over a hosted API, runtime…
Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or…
Build a competitive positioning matrix and strategy canvas when the user asks to analyze competitors, compare products, or assess competitive landscape
Generate design graph nodes (UserJourney, Flow, Page, Component) from any input: Jira ticket, plain-text description, scenario references, or Figma wireframes.
TOGAF-style architecture gap analysis: traces Baseline (AS IS) and Target (TO BE) architectures, builds a Transition plan via TDD, and produces a Gap Matrix with risks — all…
Archive root-level planning files (`task_plan.md`, `findings.md`, and `progress.md`) into a timestamped `.plannings/` directory for the current feature.
Use when session-end potrzebuje sprawdzić retencję tematów narracyjnych (L2) z articulation bank, lub gdy Jakub prosi "zadaj mi pytania z banku", "sprawdź mnie z X tematów",…
Mint an identifier or a name of a requested type out of a free-text hint: a UUID, a SHA-1 digest, a NanoId-style hash, a constant, variable, function, or class identifier, a path…
Strategic ASO planning with category-specific templates. 4-phase roadmap, keyword strategy design, metadata roadmap, visual improvement plan.
Hunt for one previously-undocumented defect, derivation gap, doc drift, missing test or wrong concept. Also architectural ugliness, code smells and inconsistencies.
Create or update product briefs through guided or autonomous discovery. Use when the user requests to 'create a product brief', 'help me create a project brief', or 'update my…
Use ONLY when the user explicitly asks to orchestrate parallel external agents (Codex or Claude Code) in tmux sessions via tp (tmux-pilot).
Produces production-ready briefs for app onboarding, App Store preview, and feature-demo videos from supplied UI screenshots.
Designs the in-product interface from a validated map-user-flow — screen inventory, a reusable component system, DESIGN-token application, per-state visual treatments,…
Zero-dependency live-preview server providing an agent↔browser bidirectional companion. Watches a content directory, wraps HTML fragments in a frame template, broadcasts…
Take a PRD and build a dark factory around it - a repository that takes work in as an issue and ships validated code out with nobody at the keyboard - one component at a time,…
Hands-on implementation partner for creating tools, scripts, dashboards, and prototypes. Use when the user wants to build something tangible — apps, scripts, automations, or…
META-DISCOVERY ONLY — answers the question "what cap-table tools or commands exist?" when the user is lost about what's available.
Code review of a diff, branch, or PR, with findings posted as anchored PR comments. Use when the user asks to review a diff, branch, or PR, asks to check a change against its…
Triggers: 当你在 Codex 收到 `$cc-master-distill [--asset-type ] [--apply pr|draft] [--out-branch ]`…
Build a throwaway prototype to answer how something should work, feel, or read. Use when committing the wrong answer would be expensive to unravel and a cheap sketch cannot settle…
Create or maintain STRATEGY.md - the product's target problem, approach, users, key metrics, and tracks of work.
Create a change management request with impact analysis and rollback plan. Use when proposing a system or process change that needs approval, preparing a change record for CAB…
Analyze and validate forms on web pages. Use when users ask to check form accessibility, verify form labels, audit input fields, check form validation, or analyze form UX.
Analyze and validate images on web pages. Use when users ask to check image alt tags, verify image accessibility, find missing alt attributes, audit image SEO, or check image…
Plan implementations, design architectures, create technical roadmaps with detailed phases. Use for feature planning, system design, solution architecture, implementation…
Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component — from…
Migrate from claudekit (ck) to the vd-cli control plane — install clean-room hooks, convert .ck.json to .vd.json, audit CK_*→VD_* env consumers, and move a repo's plans/ artifacts…
Use when brainstorming product names, company names, or brand names. Based on David Placek's Lexicon Branding methodology (Vercel, Swiffer, Sonos, Azure, BlackBerry).
Audit + groom `docs/forsvn/artifacts/` — classify every file (KEEP/STALE/ORPHAN/LEGACY/EPHEMERAL), surface references + risk.
When overwriting existing content, write only the intended replacement — never leave traces of the correction process.
Audit + clean a developer's machine — dotfolders, caches, language toolchains, package globals — with per-target classification, risk surfacing (auth, processes, side effects),…
Clean up git worktrees created by Claude Code background agents. Commits dirty state, merges to target branch, removes worktrees, and purges stale remnant directories from…
Remove stale agent worktree directories and their orphaned branches. Run after parallel agent work or when .claude/worktrees/ accumulates cruft.