all publishers

vanducng

@vanducng source repo

104 published skills · page 1 of 2

  1. ▌
    Obsidian Vault · vanducng
    Capture ideas and notes into the personal Obsidian PARA vault (markdown on disk). Use notesmd-cli when installed, else write files. Activates when the user says 'add an idea', 'capture this', 'vault note', 'inbox this', 'log this in Obsidian', 'keep track of this idea', or asks to file something in PARA. Not for the engineering journal (vd:journal) or Structured.app tasks.
    8 repo stars
  2. ▌
    Openrig Workspace · vanducng bundle
    Work inside the org/project/task projects workspace (`$PROJECTS_ROOT`) across harnesses and fleet hosts. Use whenever the cwd is under it or a task touches a project, mission, slice, task dir, worktree, rig or seat there, such as rig kind (`--kind feature --profile low|medium|high`, `--kind bugfix|sop|content`), slice and worktree names, starting or finishing a task, restarting or moving a rig, seat effort and quota, captain-signed messages, a seat treating a one-turn classifier refusal as a ban, Rex server upgrades on rig hosts, and workspace sync across macOS and Linux ('sync fleet', 'fleet sync'). Also owns resources.yaml and contacts.yaml ('update resources.yaml', 'collect resources for <project>', 'add this channel/thread/person', 'refresh contacts', 'who do we talk to about <topic>') and tracking boards ('track this on a board'). Defers OpenRig itself to `rig context get openrig-skills`, worktrees to the repo's command or vd:worktree, artifacts to vd:workbench, panes to Rex's rex skill.
    8 repo stars
  3. ▌
    Mac Resource Triage · vanducng bundle
    Diagnose and relieve an overloaded macOS workstation: high load average, memory pressure and swap, CPU-hungry helper processes, idle agent sessions and dev containers, file indexers and system scans, plus slow new-terminal / zsh startup. Read-only snapshot first, actions ranked by expected gain, explicit confirmation before stopping anything, then a before/after re-check. Activates when the user says 'it is so busy now', 'check the current resources', 'my mac is slow', 'what is eating CPU', 'load average is high', 'memory pressure', 'swap is full', 'too many agents running', 'terminal takes long to open', or 'shell startup is slow'. Do not use for disk space cleanup (computer-clean) or web page performance (web-perf).
    8 repo stars
  4. ▌
    Custom MCP Connector · vanducng bundle
    Files the admin request that registers a remote MCP on the team Claude Desktop app. Activates when the user says 'custom mcp', 'custom connector', 'add connector', 'Claude Desktop connector', or asks to add an MCP to the team Claude account. Instance host, tracker, and credential-store names come from $HOME/.config/vd/mcp-connector.md. Do not use for implementing an MCP server, local stdio MCP config, or a one-seat Claude Code smoke test.
    8 repo stars
  5. ▌
    Verify Shop · vanducng
    Boots, checks and tests shop so a change can be proved on its parent and its head. Use when verifying, QA-ing or proving a change to shop.
    8 repo stars
  6. ▌
    Changelog · vanducng
    Keeps CHANGELOG.md current. Use when the user says 'update the changelog' or 'add a changelog entry'.
    8 repo stars
  7. ▌
    Structured · vanducng bundle
    Operate the Structured day planner through the structured CLI: read a day or the inbox, show the plan to a person as a text timeline, and, with explicit authorization, create, edit, complete, or delete tasks and their subtasks. Use when the user mentions Structured tasks, their day plan, subtasks or checklists in Structured, the Structured TUI, or a structured CLI error. Reads are safe. Writes need explicit user authorization.
    8 repo stars
  8. ▌
    Onepassword · vanducng bundle
    Operate 1Password CLI (`op`) for desktop-app or service-account auth, vault/item discovery, secret references (`op://…`), `op read` / `op run` / `op inject`, TOTP, and shell-plugin auth - without printing secrets into chat. Use when the user mentions 1Password, `op`, secret references, `op://`, biometric CLI unlock, or loading env/config from 1Password. Prefer `vd:gopass` only for the local gopass store.
    8 repo stars
  9. ▌
    Create Skill · vanducng bundle
    Writes, tests and fixes agent skills with evals first: a skill is evals/ (3+ scenarios with deterministic pass checks, one clean case) plus a short SKILL.md plus scripts for fragile steps, and a repeated failure is fixed at the highest layer (architecture, types, script, lint, test, then prose). Use when the user says 'create a skill', 'write a skill for X', 'make this a skill', 'my skill never triggers', 'this skill keeps failing', 'fix this skill' or 'does this deserve a skill'. Not for scaffolding, vendoring or releases (vd:skill-management) or usage stats (vd:skill-audit).
    8 repo stars
  10. ▌
    Jump Desktop · vanducng bundle
    Check and set up Jump Desktop remote access from the terminal on macOS and Linux hosts. Read a host's Jump Desktop Connect state (service, device id, real TCC grants, viewer Local Network grant, connection audit log), link a machine to an account with a Connect Code, and manage viewer connections as version-controlled .jump JSON files for RDP/VNC fallbacks. Use when the user mentions Jump Desktop, Jump Desktop Connect, JumpConnect, Fluid remote desktop, .jump or .jdz files, asks whether this machine is reachable remotely, why a remote connection failed (for example error 2.50), wants to add a machine to Jump, or wants an agent to see or control a remote machine through Jump (jump-cli and its MCP server).
    8 repo stars
  11. ▌
    Browser Skill · vanducng bundle
    Drive the user's real logged-in Chromium through Tencent BrowserSkill's `bsk` CLI + extension - agent work runs in an isolated Agent Window, user tabs are borrowed with explicit on-page confirmation and returned at session stop, and CAPTCHA/login/OTP steps hand back to the human via `bsk request-help`. Use when the user says "browser-skill", "bsk", "agent window", "borrow that tab", or asks for logged-in browser automation that stays isolated from their own tabs. Do not use as the default local driver (that's vd:agent-browser), or for isolated task-space browsing (vd:ego-browser).
    8 repo stars
  12. ▌
    Bi Dash · vanducng bundle
    Builds a BI dashboard the way it gets trusted: a question sheet before any chart, an HTML mockup on synthetic data signed off by the asker, a field map that flags missing fields and columns with two candidates, every KPI reconciled to a reference within a stated tolerance, then the build in the repo's BI tool skill, UAT and a metric glossary. Tool-neutral. Use when the user says 'build a dashboard', 'new dashboard for', 'BI dashboard', 'KPI dashboard', 'reporting dashboard', 'mock up the dashboard', 'do we have the data for this dashboard', 'check the dashboard numbers' or 'is the dashboard ready to publish'. Not for a one-off number (answer it with a query), the tool's own chart syntax (the repo's BI tool skill) or modeling pipelines (data engineering).
    8 repo stars
  13. ▌
    Asciinema · vanducng bundle
    Record a scripted terminal demo of a CLI or TUI with asciinema: hidden fixture setup, commands typed on screen, TUI keys driven through tmux, a leak gate on the cast, scene-by-scene proof by replaying the cast, an agg GIF for the README, and upload to asciinema.org. Activates when the user says 'asciinema', 'record a terminal demo', 'screencast the CLI', 'record the TUI', 'add a demo GIF to the README', 'make a cast', or 'upload to asciinema'. Do not use for browser recordings (agent-browser) or produced motion video (video).
    8 repo stars
  14. ▌
    Better UI · vanducng bundle
    Applies exact UI polish values: concentric border radius, optical alignment, layered surface shadows, neutral image outlines, a 0.96 press scale, icon cross-fades, and theme-switch transition suppression. Activates when editing component CSS or Tailwind, when an interface looks slightly off, or when the user says 'polish the UI', 'better UI', 'concentric radius', 'optical alignment', 'shadow instead of border', or 'icon transition'. Do not use for design-system choice, accessibility audits, or building the page - that is vd:uiuxdesign. Do not use for posting a PR review - that is vd:code-review.
    8 repo stars
  15. ▌
    Design Eng · vanducng bundle
    Decides whether UI motion should exist, then picks easing, duration, origin, and gesture behavior. Covers frequency limits, springs, popover origin, tooltips, clip-path reveals, drag dismissal, and reduced motion. Activates when adding a transition, popover, drawer, toast, or drag gesture, or when the user says 'design engineering', 'should this animate', 'easing', 'spring', 'popover origin', or 'emil'. Do not use for concentric radius, surface shadows, the 0.96 press scale, or icon cross-fades - that is vd:better-ui. Do not use for design-system choice, page implementation, or accessibility audits - that is vd:uiuxdesign.
    8 repo stars
  16. ▌
    Statechart · vanducng bundle
    Checks a TLA+ model of something that moves between states (a checkout, an upload, a protocol, a job with retries) with the TLC model checker and draws it as a Mermaid statechart in the reader's words, marking each state that breaks a rule and the shortest path to it. Use when asked to 'draw the states', 'chart how this flow works', 'statechart', 'can this ever happen', 'check this flow keeps the rule', 'model the lifecycle', or to show a bug about order, duplicates, retries or late events as a path through states. Declines work with no states, such as a pure function. Not for architecture or sequence diagrams (vd:archify, vd:diagram-design).
    8 repo stars
  17. ▌
    Para · vanducng bundle
    Apply Tiago Forte's PARA method (Projects, Areas, Resources, Archives) as canonically defined to any store: a file system, cloud drive, notes app or Obsidian vault, or a markdown knowledge base that agents read and write. Use to classify items by actionability, decide project vs area vs resource vs archive, set up or audit a PARA structure, plan a reorganization or migration, run a weekly or monthly PARA review, or design agent memory on PARA without rot. Triggers: 'PARA', 'is this a project or an area', 'organize by actionability', 'set up PARA', 'PARA audit', 'archive finished projects', 'weekly review'. Not for capturing one note into the personal vault (vd:obsidian-vault) or the engineering journal (vd:journal).
    8 repo stars
  18. ▌
    Alter · vanducng bundle
    Inspect and safely change Alter, the native macOS AI assistant from alterhq.com, without going through its GUI. Audit its global hotkeys, find and resolve collisions with launchers and capture tools, move an action off a chord, and document its app-data locations without reading private content. Use when the user mentions Alter, asks why an Alter shortcut stopped firing, wants to free a keyboard chord an Alter action is holding, or needs a macOS global hotkey conflict audit. Alter's meeting transcripts and conversation history are off limits to this skill.
    8 repo stars
  19. ▌
    Kaneo · vanducng bundle
    Operate Kaneo project tracking over its REST API or built-in HTTP MCP - list workspaces, projects, tasks, comments, labels, and columns; create or update tasks and related records. Use when the user says kaneo, Kaneo ticket, log this in Kaneo, or asks to create or update a Kaneo task.
    8 repo stars
  20. ▌
    Retro · vanducng bundle
    Learns from finished or failed work and fixes the cause at the highest layer that holds: architecture or types, then a script or lint, then a test, and prose last. Runs only on a trigger: slice close (one retro line), an escape after merge, a finding class seen twice, a review past round 3, or the weekly rollup. Counts review outcomes from the verdict files. Use when asked to 'retro', 'what did we learn', 'post-mortem', 'why did this escape', 'close the slice', 'weekly rollup' or 'journal this'. One finding seen once is a note, never a rule.
    8 repo stars
  21. ▌
    Shape · vanducng bundle
    Shapes a work item's record before it is built: the intent in plain words, numbered mini-requirements anyone can check, and a checkbox proof contract, in the record's SPEC.md. A thin router: --grill walks an existing plan one question at a time; --options lays out two or three approaches and picks one. Use when asked to 'shape this', 'spec this', 'write the requirements', 'what is the proof contract', 'grill me', 'stress-test this plan', 'what are our options', 'how should we approach this', or 'plan the build'. Long multi-session decision maps stay with vd:interview --wayfinder.
    8 repo stars
  22. ▌
    Video · vanducng
    Make, edit, or render videos with HyperFrames (HTML to deterministic MP4), tuned to this toolchain: PR and release videos after ship, product promos from a URL or show-off page, concept explainers, and short motion graphics for X devlog posts. Front door for HyperFrames - read this before the hyperframes skill: it bootstraps the upstream skills, pre-selects the workflow, sets media and output defaults without a HeyGen account, and hands the MP4 to devlog/twitter. Use when the user asks to make, create, or render a video, PR or changelog video, release reel, launch promo, demo clip, motion graphic, or explainer, or mentions hyperframes. Not for AI-generated footage or text-to-video clips (vd:omnimedia), slide decks (vd:opendesign), recording a browser session (vd:agent-browser), still images (vd:marketing-design), or a video the user wants built in Remotion (porting Remotion source to HyperFrames is in scope).
    8 repo stars
  23. ▌
    Intake · vanducng bundle
    Turns an incoming ask into a work item before anyone builds: names its work type (bug fix, investigation, refactor, SOP and the rest; single source: `contract.cjs --list`), restates the intent, and writes the record's SPEC.md with that type's proof contract. Use when a new request, ticket, bug report or question arrives: 'take this', 'new task', 'triage this', 'what kind of work is this', 'start a record for', 'open a slice for'. Not for sharpening a record that already has its intent and contract (vd:shape).
    8 repo stars
  24. ▌
    Verify · vanducng bundle
    Proves a change by running the same proof command on the parent commit and the head, each in a clean checkout, into an evidence manifest (fixed, regressed, same-pass, same-fail). Writes and ages verify-<app> skills: one app's boot, health and test commands. Use when asked to 'verify this change', 'prove the fix', 'run it before and after', 'QA this', 'does it actually work', 'make a verify skill for <app>', or 'is verify-<app> stale'. Not for reading the diff (vd:code-review).
    8 repo stars
  25. ▌
    Jira · vanducng bundle
    Manage Jira issues via CLI and REST. View, create, update, transition, assign, comment, and run sprint ops, including evidence follow-ups, native mentions, inline images, structured ADF comments, and board-column moves. Use when user mentions issue keys (PROJ-123), tickets, follow-ups, sprints, or keywords like jira/ticket/backlog.
    8 repo stars
  26. ▌
    Plan · vanducng bundle
    Turn a chosen approach into a phased implementation plan with concrete steps, file changes, and success criteria. Use after `vd:interview` and `vd:brainstorm` (or a cleared `vd:interview --wayfinder` chunk, 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, `--audit` to independently check an existing plan. Do not use while the approach is still foggy across multiple fronts - that's vd:interview --wayfinder.
    8 repo stars
  27. ▌
    Ship · vanducng bundle
    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 after `vd:cook` when the branch is implemented and tested, ready to land on main/master (official), staging/uat (staging), 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.
    8 repo stars
  28. ▌
    Braze · vanducng bundle
    Operate the Braze platform through braze-cli category commands for campaigns, Canvas, catalogs, analytics, messaging, SMS, subscriptions, users, templates, and content blocks. Use when the user asks to inspect Braze data, diagnose permissions, change opt-in or opt-out state, or validate and ship the Braze CLI.
    8 repo stars
  29. ▌
    Debug · vanducng bundle
    Debug systematically across software, data pipelines, infrastructure, and analytics. Find root cause and produce verified evidence - for bugs, test failures, CI/CD breakage, K8s/Cloud incidents, dbt/Airflow pipeline failures, schema drift, freshness violations, dashboard wrong-numbers, and performance issues. Diagnoses and hands the fix to vd:fix; validates at every layer and verifies with fresh evidence before claiming a cause.
    8 repo stars
  30. ▌
    Guide · vanducng
    Catalog front door. Map an ask to the right vd: skill and the next hand-off so agents and humans do not memorize the catalog. Use when the user asks 'which skill', 'how do I start', 'what should I run', 'guide me', 'router', or when several skills could apply (review lenses, browser ladder, diagram picker, get-it-done paths).
    8 repo stars
  31. ▌
    Herdr · vanducng
    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.
    8 repo stars
  32. ▌
    Miucr · vanducng
    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; to run the serve webhook/poll daemon or GitHub Action; or to diagnose/upgrade miucr itself (over/under-approving, webhook/poll host issues, its docker-compose stack, binary version). Output is the stable `miucr.cli/v1` JSON envelope; parse it, don't grep prose. For an authored, opinionated PR review via gh, use vd:code-review.
    8 repo stars
  33. ▌
    Miudb · vanducng
    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.
    8 repo stars
  34. ▌
    Py2go · vanducng bundle
    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.
    8 repo stars
  35. ▌
    Scout · vanducng bundle
    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.
    8 repo stars
  36. ▌
    CLI TS · vanducng bundle
    Build and maintain production TypeScript CLIs as stable public APIs - command contracts, packed-artifact correctness, npm publishing, CI/CD, docs, providers, and agent-friendly output. Use when the user asks to scaffold or build a TypeScript CLI, add commands or flags, package or publish to npm, wire CI/CD, or make CLI output automation-friendly.
    8 repo stars
  37. ▌
    Devlog · vanducng bundle
    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.
    8 repo stars
  38. ▌
    Devops · vanducng bundle
    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.
    8 repo stars
  39. ▌
    Golang · vanducng bundle
    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.
    8 repo stars
  40. ▌
    Gopass · vanducng
    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.
    8 repo stars
  41. ▌
    Unslop · vanducng
    Cut AI tells from prose and add a human voice - PR bodies, docs, READMEs, blog/devlog posts, release notes, review summaries, commit messages, any text a person will read. Use when the user says 'unslop', 'de-AI this', 'remove AI tells', 'humanize this', 'this sounds like AI', or as the final pass whenever another skill produces prose. Do not use for conversion copy structure (vd:copywriting), doc structure (vd:docs, incl. its site mode), or code slop (vd:code-review --refactor).
    8 repo stars
  42. ▌
    Vd CLI · vanducng
    Manage coding-agent skills and observe agent behavior through the Go `vd` CLI. Use when the user asks to vendor/sync/build skills across Claude Code and Codex, inspect agent sessions, tokens, or API-equivalent cost, find which skills or tools are erroring, or run the self-heal loop over `vd obs health --json` to diagnose and fix a failing skill from evidence. The repo's skill-catalog lifecycle wrapper is vd:skill-management.
    8 repo stars
  43. ▌
    Browser · vanducng bundle
    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.
    8 repo stars
  44. ▌
    Diagram · vanducng bundle
    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/.
    8 repo stars
  45. ▌
    Gostack · vanducng bundle
    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.
    8 repo stars
  46. ▌
    Journal · vanducng
    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).
    8 repo stars
  47. ▌
    Show Me · vanducng
    Show Me
    8 repo stars
  48. ▌
    Twitter · vanducng bundle
    Read and post on X/Twitter from the CLI - fetch tweets, timelines, and search; post tweets, replies, threads, and media. Cookie-based auth via twikit, bootstrapped from the local Dia browser session, secrets stored in gopass. Auto-falls back to agent-browser when twikit hits internal-API drift or X's "looks automated" Error 226. Use whenever the user asks to read a tweet/profile/search, post/reply/thread, delete a tweet, or run `twitter doctor` / `import-from-dia` / `login` to manage credentials.
    8 repo stars
  49. ▌
    Web E2e · vanducng bundle
    Full end-to-end browser testing for local web apps with a persistent logged-in session. Log in once into a named Chrome profile, then drive real flows with trace evidence against your locally served app - Laravel/Herd, docker compose, FastAPI+SPA, Vite. Adds per-project orchestration via .e2e/config.json - boot + health checks, process checks (queue workers), auth-state probing, flow files, pass/fail reports. Use when the user says "e2e test", "end-to-end test the app", "test this flow in the browser", "open the app logged in", or wants browser tests that remember credentials and cookies across runs.
    8 repo stars
  50. ▌
    Dbdesign · vanducng bundle
    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.
    8 repo stars
  51. ▌
    Graphify · vanducng bundle
    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.
    8 repo stars
  52. ▌
    Research · vanducng
    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. For inventing and stress-testing options without external evidence, use vd:brainstorm.
    8 repo stars
  53. ▌
    Scenario · vanducng bundle
    Generate comprehensive edge cases and test scenarios by decomposing a feature or file across 12 risk dimensions, or blast-radius review a change with --diff: what breaks beyond the diff, proven by running real code. Use for pre-implementation risk discovery, QA planning, regression design, exhaustive edge-case enumeration, and change-safety review. Triggers: 'edge cases for X', 'what could break', 'blast radius', 'what could this break beyond the diff', 'test scenarios', 'QA plan', 'risk discovery', 'enumerate failure modes'.
    8 repo stars
  54. ▌
    Security · vanducng bundle
    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'.
    8 repo stars
  55. ▌
    Show Off · vanducng bundle
    Create polished self-contained HTML showcase pages and section screenshots for demos, launch posts, social media, article illustrations, and visual presentations. Use when the user wants to turn a project, feature, case study, markdown brief, or prompt into a bilingual scrollable showcase with reusable promo images.
    8 repo stars
  56. ▌
    Simplify · vanducng bundle
    Reduce the complexity of existing code without changing behavior - deep nesting, long functions, dead code, unclear names, the wrong abstraction. Use after a feature works but reads heavier than it should, or to clean up code written under time pressure. Pass `--aggressive` to reshape a working feature into the form it should have had from day one (delete proven-dead compatibility paths). `--scan` lists aggressive candidates only. Triggers: 'simplify this', 'clean up this code', 'reduce complexity', 'zero tech debt', 'remove the compat layer', 'rebuild this as if from scratch'.
    8 repo stars
  57. ▌
    Web Perf · vanducng bundle
    Measure Core Web Vitals (LCP, CLS, INP, FCP, TTFB), JS heap, and record DevTools performance traces against a running Chrome - attaches to vd:browser-profile's deterministic CDP ports, no Puppeteer, no separate browser. Use when the user says "why is this page slow", "measure web vitals", "check LCP/CLS/INP", "record a performance trace", "profile page load", or wants performance evidence in an e2e run.
    8 repo stars
  58. ▌
    Worktree · vanducng bundle
    Create, inspect, and clean isolated git worktrees for parallel feature development. Standardizes worktrees under a top-level .worktrees/ dir, auto-copies .env files (nested included), assigns each worktree a deterministic port block, trusts mise configs in the new worktree when present, and runs lifecycle hooks for DB seed/teardown. Use for feature isolation, parallel-agent workflows, worktree health audits, stale cleanup, port conflicts, and monorepo or submodule setups. Hands Laravel Herd projects to herd-worktree for site/env/database setup. Runtime-agnostic: works in Claude Code, Codex CLI, and plain shell.
    8 repo stars
  59. ▌
    Apidesign · vanducng bundle
    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'.
    8 repo stars
  60. ▌
    Auto Loop · vanducng bundle
    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-suite green-up 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. For numeric-metric keep/discard loops, use vd:optimize-loop.
    8 repo stars
  61. ▌
    Fastreact · vanducng bundle
    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.
    8 repo stars
  62. ▌
    Interview · vanducng bundle
    Extracts what the user actually wants before any options, plan, or code. One question at a time with a stated hypothesis until an explicit yes on a restated intent (outcome, user, success, constraint, out of scope). Use when the ask is underspecified, missing who/why/success/constraint, or the user says 'interview me', 'grill me', 'before we start', 'are we sure', 'align first'. Pass --grill to walk an existing plan or idea. Pass --wayfinder (or 'chart this', 'work the map', 'this is huge', 'we'll be at this for a while') when the deciding will not fit one session - a shared map of decision tickets. Do not use for unambiguous mechanical edits, pure info questions, or solution-space exploration (vd:brainstorm).
    8 repo stars
  63. ▌
    Omnimedia · vanducng bundle
    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. Use when the user asks to analyze, transcribe, OCR, or describe an image/audio/video/document, or to generate an image, video, voiceover, or music.
    8 repo stars
  64. ▌
    Ultracook · vanducng bundle
    Open workflow conductor. Classifies a coding task and runs the smallest viable path - direct, a pipeline of named skills with checkable done-when gates, or parallel fan-out - then resumes from on-disk state. Use when the user types ultracook, asks to orchestrate, run the whole pipeline, drive a feature or fix end-to-end, or split work across agents. Composes vd: skills by name; does not reimplement them.
    8 repo stars
  65. ▌
    Workbench · vanducng bundle
    Manage the feature-first .workbench umbrella - create, resolve, switch, list, archive, and gc per-feature folders ({ticket}-{slug}) that group plans/reports/visuals/journals/state. Use when the user says "workbench new", "list features", "archive feature", "switch feature", "what feature am I on", "clean up .workbench", or needs to organize agent artifacts under .workbench/features/.
    8 repo stars
  66. ▌
    Brainstorm · vanducng bundle
    Explore the solution space when the path isn't obvious - invent options, stress-test them, pick one. Use for architecture decisions, design tradeoffs, 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. Do not use when want is unconfirmed (vd:interview), when the user says 'grill me' (vd:interview --grill), or when the deciding will not fit one session (vd:interview --wayfinder).
    8 repo stars
  67. ▌
    Excalidraw · vanducng bundle
    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.
    8 repo stars
  68. ▌
    Opendesign · vanducng bundle
    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.
    8 repo stars
  69. ▌
    Rule Miner · vanducng bundle
    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'.
    8 repo stars
  70. ▌
    Smartsheet · vanducng bundle
    Operate the `smartsheet` CLI for bounded sheet discovery and reads, explicitly authorized bulk row additions or updates, structured JSON automation, and verified write workflows. Use when the user says "smartsheet", asks to list sheets, read or add/update rows, or script Smartsheet through its JSON contract.
    8 repo stars
  71. ▌
    Uiuxdesign · vanducng bundle
    UI/UX design quality across interfaces - visual design, UX review, accessibility audits, design systems, and design critique - plus modern web frontend implementation. Use for design-quality scoring and refactor loops, design reviews, style selection (40+ named styles), color palettes and font pairing by product type, shadcn/ui and Tailwind theming, responsive UI, visual polish, design tokens, Next.js or React implementation, TanStack Router/Query/Form/Table/Start, Playwright/Vitest web testing, Core Web Vitals, dashboards, forms, data tables, charts, landing pages, product pages, and optional Three.js/WebGL/WebGPU scenes.
    8 repo stars
  72. ▌
    Code Review · vanducng bundle
    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. Pass `--refactor` for the local reuse/slop lens (never posts). For the owned deterministic `miucr` CLI (gated reviews, webhooks, MCP), use vd:miucr.
    8 repo stars
  73. ▌
    Copywriting · vanducng bundle
    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.
    8 repo stars
  74. ▌
    Dag Factory · vanducng
    Author Airflow DAGs from dag-factory YAML. Use when creating or editing YAML DAG configs, loaders, callbacks, custom operators in YAML, dynamic mapping, datasets, or validating dag-factory files. Covers both map-style tasks (task_id as YAML key) used by in-repo plugins and the PyPI dag-factory v1 list format. Not for remote run/log inspection (vd:astro-airflow) or local astro dev lifecycle (vd:managing-astro-local-env).
    8 repo stars
  75. ▌
    Ego Browser · vanducng bundle
    ego-browser (ego-lite) is a Chromium-based browser designed 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, or automating browser operations. Triggers include "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 programmatic web interaction. Also used for exploratory testing, dogfooding, QA, bug hunting, or reviewing app quality. Prefer ego-browser over plain web-fetch/screenshot tools; for Playwright-style automation against the shared browser-profile Chrome, use vd:agent-browser.
    8 repo stars
  76. ▌
    Skill Audit · vanducng bundle
    Mine your Claude Code and Codex session history for how your skills actually get used - invocations, coverage, tool-error rates, corrections, interrupts, tokens - attributed per invocation rather than per session, then turn the aggregates into a reviewed report. Use when the user says 'audit my skills', 'which skills do I actually use', 'skill usage stats', 'are my skills working', 'mine my session history', or asks which skills to keep, merge, or drop.
    8 repo stars
  77. ▌
    Voice Agent · vanducng bundle
    Operate the `vac` CLI for Retell voice AI - bounded reads and explicitly authorized writes over agents, prompts, tools, tests, calls, transcripts, chats, phone numbers, voices, flows, knowledge bases, and exports. Use when the user mentions `vac` or Retell, asks to list/create/update voice agents, numbers, or flows, diagnose a call or transcription, or export call data.
    8 repo stars
  78. ▌
    File Browser · vanducng bundle
    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.
    8 repo stars
  79. ▌
    Skill Evolve · vanducng
    Mine the CURRENT session for how the agent skills were actually used - friction hit, commands corrected, recipes discovered, docs found stale - distill only the SELECTIVE, generalizable improvements, apply them to the relevant SKILL.md / reference files in ~/skills, and ship via vd:ship. Conservative by design: high bar, evidence-backed, no scope creep. Use when the user says 'evolve the skills', 'skill-evolve', 'improve the skills from this session', 'capture what we learned into the skills', 'update ~/skills based on this session', or runs an end-of-session skill retro. Routes standing-behavior corrections to vd:rule-miner and project/task facts to memory - it only touches skill content.
    8 repo stars
  80. ▌
    Superwhisper · vanducng
    Operate the official Superwhisper CLI and MCP to search or read dictation history, diagnose pronunciation and raw-versus-processed transcription errors, detect unwanted expansion of short utterances, inspect usage, build standups or commitment reviews, and manage vocabulary or snippets with approval. Use when the user asks what they said, why a word or acronym was transcribed incorrectly, why processed text contains extra instructions, or wants to inspect, export, or maintain Superwhisper data.
    8 repo stars
  81. ▌
    Text Diagram · vanducng bundle
    Draw reliable, well-aligned text/ASCII architecture diagrams with nested boxes, arrows, and connectors. Use when user asks to draw/create text diagrams, ASCII art diagrams, box diagrams, or architecture diagrams in plain text. For rendered image artifacts (PNG/SVG), use vd:diagram instead.
    8 repo stars
  82. ▌
    Agent Browser · vanducng
    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.
    8 repo stars
  83. ▌
    Astro Airflow · vanducng bundle
    Inspect and debug Airflow on Astronomer (Astro) deployments - DAG runs, task logs, container logs, env vars, and deployment state. Use when the user mentions Astro/Astronomer, asks about DAG runs or task logs on staging/prod, says 'check the deployment', references `astro deployment`, an Astro deployment ID, or a *.astronomer.run URL. Prefers the `af` CLI for DAG-level data and `astro` CLI for platform ops; curl is the fallback. Local astro dev -> vd:managing-astro-local-env. YAML DAG authoring -> vd:dag-factory. 'use Otto' / Airflow 2→3 upgrades -> vd:delegating-to-otto.
    8 repo stars
  84. ▌
    Browser Trace · vanducng bundle
    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.
    8 repo stars
  85. ▌
    Herd Worktree · vanducng
    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'.
    8 repo stars
  86. ▌
    Issue Invoice · vanducng bundle
    Fill a monthly hourly invoice on Google Sheets from GitHub PRs and Jira tickets, one tab per month per client. Use when the user mentions an invoice, timesheet, billable hours, logging monthly work, rolling over an invoice month, or reconciling PRs and tickets to hours.
    8 repo stars
  87. ▌
    Optimize Loop · vanducng bundle
    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'.
    8 repo stars
  88. ▌
    Skill Creator · vanducng bundle
    Authors the CONTENT of a brand-new agent skill for any stack or agent runtime - turns a vague capability request into a routable SKILL.md with a trigger-rich description, hard rules, and a verification loop, and repairs a skill that never activates. Activates when the user says 'create a skill', 'write a skill for X', 'make this a skill', 'turn this into a skill', 'my skill never triggers', 'why doesn't my skill activate', or asks to extract a repeated workflow into something reusable. Owns authoring and routing repair; defers to vd:skill-management for scaffolding, vendoring, versioning and release mechanics, vd:skill-evolve for improving skills that already exist, vd:skill-audit for usage statistics, and vd:rule-miner for standing CLAUDE.md rules.
    8 repo stars
  89. ▌
    Codex Workflow · vanducng bundle
    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'.
    8 repo stars
  90. ▌
    Computer Clean · vanducng
    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.
    8 repo stars
  91. ▌
    Diagram Design · vanducng bundle
    Create polished, accessible, self-contained HTML/SVG diagrams for architecture, workflows, data flows, sequences, state machines, ER models, timelines, swimlanes, charts, security views, and other editorial visual types. Redraw Mermaid and draw.io sources into a fresh layout, apply optional brand tokens, and verify geometry, accessibility, motion, and single-file safety. Use when the output should be an editable HTML/SVG artifact rather than an ASCII sketch, generated raster image, or editable whiteboard canvas.
    8 repo stars
  92. ▌
    Agent Readiness · vanducng bundle
    Scores how ready a repository is for AI coding agents to work in it effectively, then remediates the gaps - grades agent instruction files, verifiable feedback loops, onboarding reproducibility, and codebase navigability against a fixed 30-signal rubric, stack-agnostic across TypeScript, Python, Go, Rust, Ruby, Java, C#, and PHP/Laravel. Activates when the user says 'is this repo agent-ready', 'readiness report', 'readiness score', 'agent readiness', 'audit this repo for AI agents', 'why do agents struggle in this codebase', 'make this repo agent-friendly', 'audit our agent instruction files', or 'score our agent readiness'. Owns the scoring and the remediation plan; defers the writing of ./docs content to vd:docs, locating code to vd:scout, public documentation sites to vd:docs site, refactoring a change toward its intended architecture to vd:simplify --aggressive, and authoring instruction files and skills to vd:skill-creator.
    8 repo stars
  93. ▌
    Browser Profile · vanducng bundle
    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.
    8 repo stars
  94. ▌
    Marketing Design · vanducng bundle
    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.
    8 repo stars
  95. ▌
    Skill Management · vanducng
    Manage the lifecycle of agent skills in this repo - create new skills via skill-creator, pull/sync upstream skills with the `vd` CLI, validate frontmatter, bump versions, and ship releases through conventional commits. Use when the user says 'create a skill', 'add a skill', 'sync skills', 'release vd', 'bump version', 'update tracked skills', 'validate skills', or asks how to publish a new vd version. The underlying `vd` CLI reference (incl. `vd obs` observability) is vd:vd-cli.
    8 repo stars
  96. ▌
    Delegating To Otto · vanducng
    Drive Astronomer's Otto agent (`astro otto`) as a delegated sub-agent for Airflow, dbt, and data-engineering work. Use when the user says 'use Otto', 'ask Otto', 'delegate to Otto', or 'run this through Otto'. Also offer Otto for Airflow 2→3 migrations even when not named. Covers headless invocation, session continuity, permission modes, tool allowlists, model/provider selection, and structured output. Do not load this skill if you are Otto.
    8 repo stars
  97. ▌
    Managing Astro Local Env · vanducng
    Manage a local Astronomer/Airflow environment with Astro CLI. Use when the user says astro dev start/stop/restart, local scheduler, astro dev parse, astro dev pytest, local task logs, localhost Airflow UI, or Makefile wrappers like make airflow / make scheduler-restart. Not for staging/prod inspection (vd:astro-airflow) and not for YAML DAG authoring (vd:dag-factory).
    8 repo stars
  98. ▌
    AWS · vanducng bundle
    Operate AWS accounts and services with the AWS CLI using identity-first, read-before-write, evidence-backed workflows. Use for AWS CLI inspection, incident diagnosis, deployment verification, and explicitly authorized changes across IAM, STS, Organizations, CloudTrail, CloudWatch, S3, Lambda, API Gateway, SQS, Route 53, ALB/ELBv2, EC2, EBS, SSM, ECS, and related services, including reset-password or --reset-password when an IAM console password must be reset and stored with gopass.
    8 repo stars
  99. ▌
    Fix · vanducng bundle
    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.
    8 repo stars
  100. ▌
    Git · vanducng bundle
    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. GitHub CLI conventions: --body-file for PR bodies, treat gh pr checks exit 8 (pending) as retry not failure, guard run-id assignment before gh run view. Use when you want explicit control; for full ship-it pipeline use vd:ship.
    8 repo stars