skills

agent-browser

Drive web pages with the agent-browser CLI (Playwright engine) - the primary local browser driver. Connect over CDP to the shared browser-profile Chrome (the hands of vd:web-e2e), or run standalone with --profile isolation. Snapshot with @e refs, fill/click, video recording, network mocking, deterministic batch replay. Use when the user says "agent-browser", "record a video of the flow", "mock that API call in the browser", or asks for browser automation with built-in waiting.

API & Backend Listed

apidesign

Design stable, hard-to-misuse interfaces - REST/GraphQL endpoints, module boundaries, type contracts, component props, anything where one piece of code talks to another. Use at design time, before implementing the surface. Triggers: 'design this API', 'API contract', 'endpoint design', 'module boundary', 'interface design', 'should this be one endpoint or two', 'how should this API look'.

astro-airflow

Inspect and debug Airflow on Astronomer (Astro) deployments - fetch DAG runs, task instance logs, container logs, env vars, and deployment state without installing an MCP plugin. Use when the user mentions Astro/Astronomer, asks about DAG runs or task logs on staging/prod, says 'check the deployment', references `astro deployment`, `make airflow`, an Astro deployment ID, or a *.astronomer.run URL. Pairs the official `astro` CLI for platform ops with direct Airflow REST API calls for DAG-level data.

auto-loop

Drive a Claude Code session toward a verifiable goal until done or a hard cap fires - autonomous loop, no user intervention. Use for refactor batches, test-coverage runs, migration loops where success is a check command (tests, lint, custom predicate) plus a fresh-context audit. Hosts the loop intra-session via Stop hook with two-vote completion gate; supports optional Codex /goal delegation.

DevOps & Infrastructure Solid

aws

Operate AWS accounts and services with the AWS CLI using identity-first, read-before-write, evidence-backed workflows. Use for AWS CLI tasks across IAM, STS, Organizations, CloudTrail, EC2, ECS, S3, Lambda, CloudWatch, and related services, including reset-password or --reset-password when an IAM console password must be reset and stored with gopass.

brainstorm

Explore the solution space when the path isn't obvious - invent options, stress-test them, pick one. Use for architecture decisions, design tradeoffs, ambiguous problems, and when the user asks 'how should I approach X?'. Default produces a decision brief; pass `--quick` for chat-only, `--deep` for multi-round adversarial debate with full design doc.

browser-profile

Manage named persistent browser profiles (cookies, localStorage, IndexedDB, cache) that both you and Claude can use against the SAME Chrome window without collisions. Each profile lives in its own `--user-data-dir` and exposes a deterministic `--remote-debugging-port`. Use when the user says "open profile X", "attach to profile X", "log me into staging once and reuse it", or asks to test frontend flows with persistent auth across runs. Pairs with the `agent-browser` CLI (`agent-browser connect <port>`) for the CDP attach step.

browser-trace

Capture a full DevTools-protocol trace of any browser automation - CDP firehose, screenshots, and DOM dumps - then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.

browser

Drive Browserbase cloud browser sessions via the browse CLI when local automation is blocked. Use when a site throws CAPTCHAs (reCAPTCHA, hCaptcha, Turnstile), bot-detection walls, Cloudflare interstitials, HTTP 403/429, or geo blocks - or when the user asks for Browserbase, residential proxies, Browserbase Identity, Verified browsers, automatic CAPTCHA solving, or persistent cloud login via Browserbase contexts. This is the escalation path from the agent-browser skill (the local driver); not for localhost or ordinary local page automation.

cktovd

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 into feature-first .workbench folders under <git-root>/.workbench/features/<feature>/{plans,reports,journals,visuals,state}. Use when the user says 'cktovd', 'migrate to vd', 'migrate plans to .workbench', 'enable the .workbench umbrella', or 'switch this repo off claudekit'.

cli-ts

Build and maintain production TypeScript CLIs. This skill should be used whenever work touches commands, packaging, CI/CD, npm publishing, docs, providers, or agent-friendly output.

cnb-ds-eda

Build evidence-backed exploratory analysis and GitHub-renderable notebook reports in `/Users/vanducng/git/work/cnb/cnb-ds-eda`. Use when the user asks for CNB EDA notebooks, Snowflake-backed analysis, Retell or Transfer AI investigations, data-contract-derived report logic, notebook refreshes, or report artifacts under `notebooks/`.

Show all 54 bundled skills

cnpg

Create and operate CloudNativePG (CNPG) Postgres databases on Kubernetes the GitOps/Flux way - on managed cloud (GKE + GCS via Workload Identity) OR self-hosted (K3s/bare-metal + any S3-compatible store via a credentials secret). Covers Cluster + ScheduledBackup manifests, barman WAL archiving, pgvector, PITR, prod→dev clones, and the NetworkPolicies a default-deny cluster needs. Use when provisioning a new app database, cloning prod into dev, enabling pgvector, wiring backups/PITR, writing CNPG NetworkPolicies, or debugging the silent "WAL archiving failed → PVC fills → Postgres CrashLoop → app can't read data" chain on CloudNativePG.

code-review

Review code with a sharp, encouraging voice - inline GitHub PR comments + a tight summary. Supports PR (default), pending changes, commit hash, and codebase modes. Encodes an opinionated review style: severity-prefixed, concise, actionable, no fluff.

codex-workflow

Run deterministic multi-step agent workflows in Codex - fan-out, parallel, schema-validated structured output - via the codex-workflow MCP orchestrator (run_workflow), with native in-chat fallbacks. Use when you want Claude-Code-Workflow-style orchestration in Codex: 'run a workflow', 'fan out subagents', 'review each file in parallel', 'orchestrate these steps'. Triggers: 'codex-workflow', 'run_workflow', 'orchestrate in codex'.

computer-clean

Audit and reclaim disk space on macOS. Discovers cache hogs, dev caches, dead app data, old Downloads, dup installers, and obsolete container/VM images. Use when user says 'clean disk', 'free up space', 'computer-clean', 'cleanup mac', 'disk full', or shows ≥85% disk usage.

cook

Execute a plan (or a small task) phase-by-phase: implement → verify → test → review → update status. Use after `vd:plan` to ship the plan, or directly for tight tasks (`--quick`). Default stops at review gates between phases; pass `--auto` to run straight through, `--quick` for sub-plan tasks, `--tdd` for tests-first.

copywriting

Conversion copywriting formulas, headline templates, email copy patterns, landing page structures, CTA optimization, and writing style extraction. Use for high-converting copy, headlines, email campaigns, landing pages, social posts, product copy, CTA variants, or applying custom writing styles from an assets/writing-styles directory.

API & Backend Listed

dbdesign

Design and review production database schemas, data models, ERDs, migration plans, and storage patterns. Use for OLTP schema design, OLAP/star-schema modeling, fact/dimension tables, indexes, constraints, partitioning, multi-tenant data models, CSV/JSON-to-table design, schema review, migration risk review, and database design documents across PostgreSQL, MySQL, SQLite/D1, BigQuery, and MongoDB. Does not execute DDL by default.

debug

Debug systematically across software, data pipelines, infrastructure, and analytics. Find root cause before fixing - for bugs, test failures, CI/CD breakage, K8s/Cloud incidents, dbt/Airflow pipeline failures, schema drift, freshness violations, dashboard wrong-numbers, and performance issues. Validates at every layer; verifies with fresh evidence before claiming done.

devlog

Turn recent engineering work into build-in-public devlogs for X/Twitter. Use when the user asks to draft or write a devlog/post, create a vault post and cover, start today's dev log on x.com, publish a ship/debug/lesson thread, or turn recent commits into a public update.

DevOps & Infrastructure Listed

devops

Deployment and infrastructure operations. Use when writing or debugging a Dockerfile, docker build/run, docker compose; running terraform plan/apply/destroy or editing .tf files and modules; using kubectl, debugging pods (CrashLoopBackOff, ImagePullBackOff, OOMKilled), applying manifests, or writing Helm charts; deploying to GKE/EKS/AKS, Cloud Run, or App Engine; GitOps with Argo CD or Flux; writing GitHub Actions CI/CD workflows; or deploying Cloudflare Workers/Pages/R2/D1. Triggers on: dockerfile, docker compose, terraform, tofu, kubectl, k8s, helm, gcloud, eksctl, argocd, wrangler, github actions, ci/cd pipeline, container, cluster, rollout, image scan.

diagram

Generate modern reviewable diagrams (system architecture, workflow, data flow, sequence, ER, state-machine, C4) via OpenRouter image-gen or LLM-emitted SVG. Auto-classifies diagram type from prompt; --type to override. Default scratch output goes to the resolved workbench visuals path; --versioned writes git-trackable specs and variants under docs/diagrams/.

docs

Manage project documentation in ./docs/ - initialize, update, check, or record an ADR (architecture decision record). Canonical set is intentionally small: development guidelines, system architecture, tech stack, deployment; plus append-only decision history under docs/decisions/. Scouts the codebase, delegates writing to the docs-manager subagent (or stays inline with --inline).

ego-browser

ego-browser (ego-lite) is a Chromium-based browser designed from the ground up to be friendly to both human users and AI Agents. AI Agents work in their own isolated space, reusing the user's login state without competing for the browser. Use this skill whenever the user needs to interact with a website opening pages, filling forms, clicking buttons, taking screenshots, extracting page data, testing web apps, logging into sites, automating browser operations, or any other browser automation task. Triggers include requests to "open a website", "visit a URL", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "extract content from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also used for exploratory testing, dogfooding, QA, bug hunting, or reviewing app quality. Prefer ego-browser over any built-in browser automation, web fetch, or other web tools.

excalidraw

MANDATORY prerequisite for ALL Excalidraw MCP tool usage. Read BEFORE calling any Excalidraw tool (batch_create_elements, create_element, update_element, etc.). Without the sizing formulas, two-batch ordering (shapes-then-arrows), compact legends, domain styling presets, and write-check-review cycle in this skill, diagrams have invisible arrows, truncated text, and inconsistent colors. Use whenever the user asks to draw, sketch, visualize, or diagram anything technical - system architecture, microservices topology, C4 diagrams, data pipelines / ETL flows / lakehouse, sequence diagrams, ER diagrams, deployment / Kubernetes diagrams, network topology, flowcharts, decision trees. Includes ready-to-apply color palettes for software engineering, system architecture, and data solutions.

fastreact

Scaffold and build a full-stack web app: FastAPI backend (Python, uv, SQLModel, Postgres, Alembic, JWT + Google OAuth, boto3/S3) + React frontend (Vite, TypeScript, shadcn/ui + Tailwind, TanStack Router/Query/Table, Zod, Axios), wired with Docker Compose. Use this skill whenever the user wants to spin up, bootstrap, create, or design a new full-stack webapp; an API-first backend + SPA frontend; an admin/portal/dashboard app; file upload + S3; RBAC / role-based auth with seeded test users; local docker dev; or asks for a 'FastAPI + React' / 'Python + React' project. Runs mockup-first: marketing-design (brand/logo raster) + opendesign (HTML page mockups) before code, then ports the design to Tailwind/shadcn. Covers project structure, local setup, auth/RBAC, S3 uploads, and the gotchas that break these stacks.

file-browser

Local HTTP server that renders markdown, code, text, JSON, CSV/TSV/XLSX tables, HTML, PDF, images, video, and audio in the browser. Persistent left tree sidebar with vim keybindings (j/k/h/l/gg/G/Enter/o), filter (/), theme toggle (T), and folder open/collapse persistence per tab. Markdown dispatches to a novel-theme reader (Mermaid, plan nav, ToC scroll-spy); code/text dispatches to a highlight.js view with line numbers + copy button; CSV/TSV/XLSX dispatches to a tabular view; HTML renders in a sandboxed iframe; PDF dispatches to a custom minimal viewer built on the pdfjs-dist PDFViewer component (toolbar: prev/next, page input, zoom, search, download); images/video/audio get a gallery + single-view with Range-aware streaming. One server, one port, one CLI.

DevOps & Infrastructure Listed

fix

Fix issues end-to-end across data pipelines (Airflow/dbt), app stack (backend/frontend), and infra (CI/CD, Terraform, K8s). Scout → diagnose → apply at root cause → verify with fresh evidence → add regression guard. Use for failing DAGs, dbt test failures, 5xx, UI regressions, GH Actions failures, terraform drift, CrashLoopBackOff, lint/type errors. Stops after 3 failed attempts to question architecture.

git

Granular git operations with conventional commits - stage, commit, push, PR, merge. Auto-splits commits by type/scope, blocks on secrets, delegates verbose work to git-manager subagent. Use when you want explicit control; for full ship-it pipeline use vd:ship.

golang

Idiomatic Go guidance for writing and reviewing Go code - style, naming, MixedCaps, GoDoc comments, error handling (%w, errors.Is/As, sentinel errors), goroutines/channels/select/context, safety (nil maps, append aliasing, type assertions), structs/interfaces, generics, table-driven tests, testify, golangci-lint, go.mod dependency management, project layout, slog/Prometheus/OpenTelemetry observability, and gRPC. Use when writing, reviewing, or refactoring Go (.go) code, editing go.mod/go.sum, running go test or golangci-lint, debugging goroutine leaks or races, or making Go design decisions. For the samber/* library stack (lo, oops, do, mo, slog-*, hot, ro) use gostack instead.

gopass

Retrieve credentials (API keys, tokens, passwords) from the local gopass password store. Use when a task needs a secret that the user has stored in gopass - instead of asking the user to paste it, search the store and read the value with `gopass find` / `gopass show -o`. Also covers inserting, generating, listing, searching, syncing, and TOTP.

gostack

My curated Go stack reference - opinionated guide to Sam Berthe's libraries (lo Lodash helpers, oops structured errors, do v2 DI, mo monads, slog logging ecosystem, hot in-memory cache pre-1.0, ro reactive streams pre-1.0). Use when writing or reviewing Go code that imports github.com/samber/*, when deciding between these libraries and the stdlib, when adopting or upgrading any of them, or when scaffolding a new Go service and considering this ecosystem.

graphify

Use for any question about a codebase, its architecture, file relationships, or project content - especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.

gws

Manage Google Workspace from the CLI: Gmail, Drive, Calendar, Sheets, Docs, Tasks, Chat, and Workspace Admin for vanducng.dev via the official `gws` command. Use when the user mentions gmail, drive, calendar, sheets, docs, workspace, gws, vanducng.dev, email, files, events, or Workspace users/groups.

herd-worktree

Set up an isolated git worktree for a Laravel project served by Laravel Herd (Pro-aware). Composes vd:worktree for the worktree/.env/port mechanics, then adds the Herd layer: link + scheme-correct site (HTTPS via herd secure when the source is secured), .env rewrite (APP_URL, SESSION_DOMAIN, Sanctum - only when present), opt-in per-worktree database isolation, Vite TLS/CORS, then hands finishing to vd:ship / vd:git. Triggers: 'herd-worktree', 'herd worktree', 'laravel herd worktree', 'isolate a Laravel feature branch', 'work on this Laravel branch with Herd'.

herdr

Control Herdr, the terminal multiplexer for coding agents. Use when the user mentions Herdr or another skill delegates pane control, including concise pane naming, inspection, commands, and agents. Integrates with vd:worktree, vd:codex-workflow, and vd:ultracook. Requires HERDR_ENV=1.

jira

Manage Jira issues via CLI. View, create, update, transition, assign, comment, sprint ops. Use when user mentions issue keys (PROJ-123), tickets, sprints, or keywords like jira/ticket/backlog.

journal

Write a focused engineering journal entry - retrospective on what just shipped or post-mortem on what just broke. Use after vd:ship, vd:cook, or right after an incident while context is fresh. Saves to the injected Journals path (personal dev log, not project docs).

marketing-design

Marketing brand-asset generation (raster images via AI): logo design (55 styles, 30 palettes, 25 industries), corporate identity / CIP mockups (50 deliverables - business card, letterhead, signage, packaging, apparel), banner design (22 styles, social/ads/web/print), SVG icon design (15 styles), social photos (multi-platform), and model-agnostic poster prompts. Default image engine is Codex gpt-image-2 (ChatGPT subscription via `codex login`), attaching the brand logo as a reference image for CIP compositing; falls back to Gemini Nano Banana (GEMINI_API_KEY, same key as omnimedia). Actions: design logo, create CIP / brand identity, generate mockups, design banner, generate icon, create social photos, design poster, social media images. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads. For HTML/web pages, dashboards, and slide decks, use opendesign instead.

miucr

Review code/diffs/PRs with the owned `miucr` CLI (miu-cr, a pure-Go AI code reviewer). Use when asked to review staged changes, a commit, a ref range, or a GitHub PR; to run/parse a gated review; compare reviewer quality with eval; to drive reviews over MCP; or to run the serve webhook/poll daemon or GitHub Action. Output is the stable `miucr.cli/v1` JSON envelope; parse it, don't grep prose.

API & Backend Listed

miudb

Query, inspect, and manage saved database connections through the Go `miudb` CLI. Use when the user asks to run SQL, list schemas, add native connections, smoke-test connections, inspect tunnel-backed databases, or produce agent-readable JSON from SQLite, Postgres, MySQL, Snowflake, or BigQuery.

omnimedia

Multimodal AI - Gemini for analysis (vision/transcribe/OCR/extract); image generation via Codex (ChatGPT subscription), Gemini/Imagen, OpenRouter, MiniMax; video, speech, music via Gemini + MiniMax.

opendesign

Generate polished single-file HTML design artifacts using the nexu-io/open-design catalog of production skills and brand-grade design systems. Use when the user asks to design, mock up, prototype, draft, build, or render a visual web artifact, chooses a brand/style direction, requests a deck/PPT, hero, section, component, marketing page, dashboard, email, doc page, or GitHub README/repo banner. Auto-opens the result for review. Produces editable HTML/CSS; use vd:marketing-design for AI-generated raster brand imagery.

optimize-loop

Autonomous metric-optimization loop - run N bounded iterations against a mechanical metric, commit each attempt, auto keep/discard on the number, revert regressions. Use to improve a measurable metric: test coverage, bundle size, lint/type-error count, p95 latency, LOC. Triggers: 'drive coverage up', 'reduce bundle size', 'get lint errors to zero', 'optimize <metric> over iterations', 'keep/discard loop'.

plan-audit

Audit a vd:plan output for gaps, inconsistencies, missing scaffolding, and codebase drift using an independent clean-context subagent. Use after vd:plan (or any time after manual edits to phase files) when stakes warrant verification beyond same-context red-team. Auto-fires at end of vd:plan --deep.

plan

Turn a chosen approach into a phased implementation plan with concrete steps, file changes, and success criteria. Use after `vd:brainstorm` (or any decided design) when you need to sequence the work before building. Default produces plan.md + phase files; pass `--quick` for a single-file plan, `--deep` for research dispatch + red-team review.

py2go

Migrate Python projects to idiomatic Go end-to-end. Branches into 6 project-type playbooks (CLI, TUI, HTTP backend, data pipeline, async worker, library) with the right stack defaults (Gin, pgx, sqlc, slog, etc.) and pinned library versions. Default strategy: LLM module-by-module rewrite with golden-file parity tests; --strangler for live-traffic gradual cutover; --spec-first for OpenAPI/proto-driven regeneration. Use when porting a Python codebase to Go, when scaffolding a Go rewrite of a Python service, or when generating CLAUDE.md/MIGRATION.md for an AI-driven migration.

research

Deep technical research with multi-option evaluation. Use for technology selection, architecture decisions, library/framework comparison, security and performance analysis. Default mode is thorough; pass `--deep` for exhaustive coverage with expanded comparison matrices and edge-case analysis.

rule-miner

Mine your Claude Code sessions and code-review history for the corrections you keep repeating, cluster them, adversarially verify each candidate, and distill the survivors into CLAUDE.md rules - or check that existing rules still hold. Uses a dynamic Workflow harness with one verifier per rule to avoid false positives. Use when the user says 'mine my sessions for rules', 'what corrections do I keep making', 'turn my repeated feedback into CLAUDE.md rules', 'audit my CLAUDE.md rules', or 'why does Claude keep missing X'.

scenario

Generate comprehensive edge cases and test scenarios by decomposing a feature or file across 12 risk dimensions. Use for pre-implementation risk discovery, QA planning, regression design, and exhaustive edge-case enumeration. Triggers: 'edge cases for X', 'what could break', 'test scenarios', 'QA plan', 'risk discovery', 'enumerate failure modes'.

scout

Fast, parallel codebase scouting across software, data-engineering, devops, and analytics surfaces. Use to locate files, dbt models, dashboards, IaC, pipeline DAGs, K8s manifests, secrets, and CI workflows before changes. Supports internal (Explore subagents) and external (Gemini/OpenCode CLI) modes.

security

Threat-modeled security audit using STRIDE + OWASP (incl. the OWASP LLM Top-10 lens for AI/agent code), scanning code from multiple attacker perspectives, with optional red-team discovery loop and an autoresearch-style fix loop. Use for defensive security review, vulnerability discovery, threat modeling, prompt-injection / LLM security, and authorized remediation. Triggers: 'security audit', 'STRIDE', 'OWASP', 'find vulnerabilities', 'threat model', 'red-team this', 'is this secure', 'prompt injection', 'LLM security'.

ship

Ship a feature branch end-to-end: merge target → test → review → version/changelog → commit → push → PR, then drive CI green and hand off the PR. Use when ready to land a branch on main/master (official) or dev/beta (beta). Merge is opt-in — a bare ship stops at a green PR; it merges only with --auto or --merge. Stops on test failures, critical review issues, or major version bumps.