jackneil
UserHit a Claude Code usage limit and jacked switches accounts for you. Multi-account manager and skills suite for Claude Code and Codex: live 5h/7d usage tracking, auto account-switching, a menu-bar app on macOS and system tray on Windows/Linux, plus 30 slash commands, 28 skills and 10 review agents from a web dashboard.
Categories
Indexed Skills (28)
clone-website
Reverse-engineer and clone one or more websites in one shot: extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in worktrees as it goes. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy a website they own or are authorized to reproduce. Also triggers on phrases like "make a copy of this site", "rebuild this page", "pixel-perfect clone". Provide one or more target URLs as arguments.
review-animations
Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
aesthetic-dogfood-audit
Use to dogfood and evaluate the SHIT out of a running web app end-to-end — drive it in a browser as EACH real user persona through EVERY workflow (login → core jobs → the nitty-gritty), catching both how it WORKS and how it LOOKS. Finds misalignment, dark-mode dark-text / low contrast, a modal that doesn't open, a close button that doesn't close, an action that doesn't update the view (stale data), inaccurate numbers, and common tasks buried too deep to discover. Triggers include "audit the whole app", "dogfood it", "evaluate every persona and workflow", "go through the entire product", "find what's broken or looks bad", "is this actually usable", "click-count / discoverability pass".
animation-vocabulary
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.
chain-of-command
Lock in the session model-dispatch policy - the main loop (Fable, or best available) does ALL strategy, planning, understanding, judging, and verification; every dispatched subagent that writes code or reviews from an established plan runs on Opus; pure locate/sweep hunts run on Haiku or Sonnet. Use when the user invokes /chain-of-command or says "chain of command", "fable plans, opus codes", "use the model split", "minimize fable usage", or "opus for the grunt work". Applies from invocation until the session ends or the user revokes it.
checkpoint
Save and resume working state checkpoints. Captures git state, decisions, research, session context, and remaining work so a new session can pick up exactly where you left off. Use when asked to "checkpoint", "save progress", "where was I", "resume", "what was I working on", or "pick up where I left off".
claude-md-optimizer
Use when CLAUDE.md feels bloated or too long, when starting a new project, or when optimizing documentation for token efficiency. Audits content quality, extracts reference material to sub-docs, and enforces a token budget.
coverage-matrix
Use when asked to analyze product completeness, find gaps, figure out what to build next for best-in-class coverage, audit feature depth across user types, or create a prioritized roadmap for a product. Triggers on "what's missing", "gap analysis", "10/10", "best-in-class", "coverage audit", "feature completeness", "what should we build", "is it actually easy to use", "workflow friction", "how automated are we really".
deploy-to-railway
Use when deploying a project to Railway from scratch — provisioning a Postgres database, one or more app services (a full-stack monolith OR separate frontend/backend), an S3-compatible bucket, sharing credentials + env vars between services, wiring GitHub auto-deploy on merge to main, and adding auth (Google SSO or Cloudflare Zero Trust in front). Triggers on "deploy this to Railway", "get it live on Railway", "set up Railway with a database + auto deploy", "split front/back end services on Railway", "add an S3 bucket on Railway", "share env vars between Railway services". Carries the hard-won gotchas (NIXPACKS Node version, npm-version lockfile skew, RLS-safe DATABASE_URL, DB-role password rotation, GitHub App authorization) that turn a 6-hour debug into a 20-minute deploy.
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
jack-it-up
Use when starting any significant feature or non-trivial task that deserves a thorough development cycle. Triggers on "jack it up", "do this right", "full cycle", "build this properly", or when the user wants quality-first development over speed.
launch-post
Use when the user wants to announce, launch, promote, ship, or showcase a project, repo, feature, demo, or release on X (Twitter) — including deciding what to highlight, creating the media, and publishing the post + replies. LinkedIn support planned.
logo-forge
Use when designing or upgrading a brand logo, favicon/app icon, or social link-preview cards (Open Graph / Twitter cards that unfurl in iMessage, Slack, X/Twitter) for a repo or product. Triggers on "design a logo", "make me a logo", "better logo / favicon", "brand mark", "app icon", "social card", "og image", "link preview", "iMessage preview", "twitter card", or being pointed at a repo that needs branding. Generates real logos via Higgsfield image models, builds the full favicon + social-card set with ImageMagick, and deploys them into the target repo (Next.js or static; branch+PR; worktree-safe alongside a live session).
memory-librarian
Groom the jacked memory vault for a group. Dedupe notes, reconcile contradictions newest-wins-with-a-trail, review candidate auto-captures, archive stale hot entries, validate frontmatter, and re-sync the index. Use when the SessionStart brief nudges "memory drift is high", when asked to "groom the vault", "tidy memory", "clean up notes", "reconcile the vault", or after a burst of captures has piled up unreviewed notes.
night-shift
Use when the user wants a product continuously driven forward without them steering each step — an autonomous session (overnight or daytime) that discovers, builds, verifies, and lands improvements across every lens (user types, UX, security, compliance, reliability, DX, product strategy). Triggers on "night shift", "run the night shift", "drive this product forward", "keep improving this while I'm away", "work the queue overnight", "make this best-in-class across the board", "put the army on it". Accepts a steer argument ("night-shift focus security", "night-shift billing UX") which prioritizes that lens or area. Accepts an auto-merge argument ("night-shift auto-merge") which lands each verified improvement to main behind green checks on pre-production repos. NOT for a single decided feature (/goal-maker), a one-off QA pass (/qa), read-only scoring (coverage-matrix), or driving the coverage matrix cell-by-cell (/bhag).
recover
Use when a Claude Code session in this folder crashed or was lost mid-work (computer died, terminal closed, Claude broke) and the user reopened Claude without a checkpoint and does not know the session ID — rebuild the last session for THIS folder from its on-disk transcript and continue. Any request to recover, restore, or resume a crashed or dead session qualifies. NOT for transient API/rate-limit errors mid-turn (use retry), NOT for deliberately saved state (use /checkpoint resume), NOT for finding an old session by topic across machines (use /jacked).
recursive-10-10-product-hardening
Use when asked to harden a product to verified 10/10 by first deriving its expected behavior FROM the code and then closing the gap between what the code does and what it should do — inventory every feature, write each feature's code-grounded expected behavior into a canonical behavior-spec workbook, dogfood it in a browser, fix the defects at the source, and loop test→fix→retest until every feature is evidence-verified. Triggers on "harden to 10/10", "drive it to verified 10/10", "behavior spec from the code", "derive expected behavior from the code", "spec the product from its code", "production-hardening pass", "dogfood and fix to 10/10", "build a behavior/feature workbook and verify every row". Also triggers with an auto-merge argument ("$recursive-10-10-product-hardening auto-merge", "with auto-merge") which lands each verified batch to master behind green checks. NOT for read-only scoring or gap-analysis (use coverage-matrix), a single-change QA pass (/qa or /ux), or auto-merging the whole coverage matr
qa
Use when testing UI changes for visual correctness, interactions, console errors, and edge cases. Performs browser-based QA and returns a detailed issue list for planning fixes.
demo-video
Use to produce a polished, narrated product DEMO / walkthrough / how-to video for documentation and education — teaching a feature or capability to end users, to embed in docs, a README, a release note, or onboarding. NOT for bug/regression evidence (that's /qa-video). Triggers include "make a demo video", "record a walkthrough", "feature walkthrough for the docs", "how-to video", "show this feature off", "onboarding video", "educational clip for new users".
qa-video
Use when you want a playable video recording of a QA/test session plus a synced narrated journey — not just screenshots. For regression evidence, "it worked" proof, bug reproduction with motion, or a recorded walkthrough. Pass a URL as argument, or let it auto-detect the running app.
dcr
Parallel recursive review — selects relevant lenses, spawns focused reviewers per wave until all selected lenses pass clean. (repo)
docs-sync
Sync docs with code changes — diffs branch, maps to affected docs, spawns parallel update agents. (repo)
lockdown
Use when auditing or hardening a repository against software supply-chain attacks — including dependency lockfile integrity, CVE scanning, malware/typosquat detection, GitHub Actions SHA pinning, secrets scanning, provenance/signing, and SLSA/HIPAA control mapping. Triggers on phrases like "lock down dependencies", "supply chain audit", "is this repo secure", "dependency poisoning", "typosquat", "harden actions", "pin actions", "audit deps", or any concern about consuming or shipping third-party code safely.
swarm-research
Use when approaching non-trivial planning — architectural decisions, major features, system design, or any decision with multiple viable approaches.
ux
Parallel browser-based UX checks — spawns focused agents to test different UX aspects simultaneously. (repo)
whats-next
Roadmap advisor — weighs a coverage-matrix read plus plans, issues, commits, and lifecycle to decide the single highest-leverage initiative and forge a ready-to-run /goal brief. (repo)
release
Use when ready to cut a release. Detects how THIS repo actually ships (PyPI, npm, changesets, CalVer, Cargo, Go tag, or PR-to-main deploy), suggests the semver bump, gates on the repo's OWN build+test before anything irreversible, then publishes/deploys the way that repo really ships and verifies it landed.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.