subinium

Thin slash-command wrapper around the i18n-nfc-auditor agent — audits Korean/CJK string handling for NFC/NFD Unicode normalization mismatches across filenames, URLs, attachments, and DB paths. Use when "한글 파일 깨짐", "Supabase 첨부 안 됨", "한글 파일명 문제", or after…

Thin slash-command wrapper around the migration-reviewer agent — audits SQL/Prisma/Supabase/sqlx/Drizzle migration files for data loss, lock contention, missing indexes, and rollback safety. Use before db push, before Supabase deploy, or "마이그레이션 리뷰", "DB 스키마…

Audit and curate the per-project memory system at ~/.claude/projects/<encoded-cwd>/memory/ — finds duplicates, stale entries, missing-pointer files, oversized MEMORY.md, and entries that violate the user/feedback/project/reference taxonomy. Use when memory…

Traces all references to a feature flag/gate across the codebase and produces a removal PR draft. Use when ramping up a flag, removing a kill switch, or "feature flag 정리", "플래그 제거", "킬스위치 제거". Auto-detects flag system (GrowthBook, LaunchDarkly, env vars,…

Performance triage entry point — bundle analysis, build profiling, Lighthouse CI, Next.js Cache Components inspection. Use when asked "why is X slow", "perf 분석", "번들 사이즈 확인", "Lighthouse 점수", "빌드 시간 측정". Delegates deep root-cause analysis to perf-researcher…

Scaffolds a Claude Code plugin with .claude-plugin/marketplace.json + plugin.json + a starter skill/agent/hook + GitHub Actions validator — codifies the vibesubin maintenance pattern. Use when creating a new plugin, publishing to a marketplace, or "플러그인…

Extracts a structured PRD.md and tactical implementation plan from the current conversation — captures goals, non-goals, scope, risks, and acceptance criteria. Use when ending a brainstorm before implementation, before invoking the architect agent, or "PRD…

Instantly load project context and suggest actionable next steps. Use at session start instead of open-ended greetings

Opinionated defaults and full lifecycle playbook for secrets and environment variables. Decides where a secret or env-specific value lives (constant, .env, CI secret, env var), scaffolds .env.example and .gitignore, and manages the lifecycle end to end — add,…

Opinionated defaults for the lower-stakes structural conventions every project has to pick — branch strategy, directory layout, dependency pinning, path portability. The companion to manage-secrets-env (which owns the high-stakes secrets/env slice). Picks…

Proves a behavior-preserving code change (refactor, rename, split, merge, extract, inline, or delete of confirmed-dead code) is actually complete. Plans the change as a dependency tree, executes it from the leaves up, and after each step proves 1:1 semantic…

Issue-driven development orchestrator. Turns improvement intent into a well-specified, bilingual issue set; clusters issues into milestones that map 1:1 to semver versions; enforces branch, commit, and PR conventions (GitHub Flow — `<type>/<issue-N>-<slug>`,…

Runs a deliberately small, hand-curated security sweep across a repo. Finds secrets committed to git, SQL/shell injection patterns, XSS sinks, path traversal, dangerous deserialization, missing cookie flags, wildcard CORS, and tracked credential files.…

Post-edit loop that invokes `/codex:rescue` for a second-model review of the current branch, collects the findings, and hands them off to `refactor-verify`'s review-driven fix mode for triage, verification, and committed resolution. A thin host-specific…

Finds what's rotting in a repo and returns a prioritized diagnosis — dead code first, then god files / hotspots / hardcoded paths / stale TODOs / lopsided import graphs. Dead-code candidates are tagged HIGH / MEDIUM / LOW confidence so the operator can delete…

Finds oversized files, binary bloat, and accidental artifact commits in a repo — large files currently tracked, large blobs hiding in git history, LFS migration candidates, asset directories growing without a policy, duplicate binaries. Pure diagnosis — never…

Migrate Rust TUIs from ratatui (or cursive, Python textual) to SuperLightTUI v0.23. Use when porting an existing TUI codebase to SLT, or when the user asks "how do I do X from ratatui in SLT". Korean triggers "ratatui 마이그레이션", "SLT로 포팅", "이걸 SLT로".

Build Rust TUI apps with SuperLightTUI v0.23 (immediate-mode terminal UI). Use this skill when the user asks to create, modify, or debug terminal UI code in this repo, or asks "how do I X in SLT / TUI / terminal", or types Korean triggers like "터미널 UI", "TUI…

Migrate Rust TUIs from ratatui (or cursive, Python textual) to SuperLightTUI v0.20. Use when porting an existing TUI codebase to SLT, or when the user asks "how do I do X from ratatui in SLT". Korean triggers "ratatui 마이그레이션", "SLT로 포팅", "이걸 SLT로".

Build Rust TUI apps with SuperLightTUI v0.20 (immediate-mode terminal UI). Use this skill when the user asks to create, modify, or debug terminal UI code in this repo, or asks "how do I X in SLT / TUI / terminal", or types Korean triggers like "터미널 UI", "TUI…

When solving a task that needs multiple tool calls in sequence (e.g., fetch -> parse -> fetch -> store), prefer code.execute to chain them in one inference call.

When you've just solved a non-trivial multi-step task that you might be asked to repeat, consider calling learning.proposeSkill to save the recipe.

Vercel account hardening and incident response. Use when the user mentions a Vercel breach/incident, asks to audit or rotate Vercel environment variables, mark env vars sensitive, or respond to leaked Vercel tokens. Scope is Vercel only (not…

Create mathematical animations in 3Blue1Brown style using Manim