Taw
Single entrypoint for taw-kit. User types `/taw <anything in VN or EN>` — this skill classifies the intent (BUILD / FIX / SHIP / MAINTAIN / ADVISOR) and loads the matching branch file to execute. Replaces the old one-command-per-task model (/taw-new, /taw-add, /taw-fix, /taw-deploy, /taw-security) with a single unified command. Supports dev workflows out of the box: test, upgrade, clean, perf, rollback, refactor, types, seed, review, stack-swap, status, and ADVISOR group (analyze, suggest, coverage, adversarial, scope-check) for opinionated review of existing code. User-visible strings match the user's input language (Vietnamese by default for VN users). Two modes: SAFE (default — clarify + approval, max 1 round-trip) and YOLO (skip gates, smart defaults — for demos/power users). YOLO triggers: prose contains `yolo`, `nhanh nha`, `lam luon`, `khoi hoi`, `auto`, or args start with `yolo`. Trigger phrases (EN + VN) — broad match so user can keep typing plain prose without re-invoking /taw every turn. Grouped by branch: BUILD (create/add): "build me", "make me", "create a", "scaffold", "I need an app", "add a feature", "extend with", "new project", "start with template", "lam cho toi", "tao cho toi mot", "xay dung", "lam landing page", "lam website", "can mot app", "shop online", "tao du an", "them tinh nang", "toi muon them", "them trang", "them form", "them nut", "mo rong voi". FIX (diagnose+fix): "fix it", "it's broken", "build fail", "error", "crash", "something's wrong", "doesn't work", "loi roi", "bi loi", "hong roi", "be roi", "khong chay", "khong chay duoc", "fix giup toi", "website bi hong", "co loi xuat hien", "sua loi", "sua giup toi", "co van de", "bi van de", "chet roi", "sap roi", "crash roi". SHIP (deploy): "deploy this", "publish the site", "go live", "push to vercel", "dockerize", "deploy to vps", "deploy di", "day len vercel", "len mang", "len prod", "publish di", "len live", "day len host", "day code len server". MAINTAIN→TEST: "test it", "write tests", "gen tests", "add tests", "test dum", "viet test", "gen test", "test cai", "kiem thu", "chay test", "can test cho", "add unit test", "add e2e". MAINTAIN→UPGRADE: "upgrade", "bump deps", "update packages", "upgrade next", "upgrade react", "nang cap", "nang version", "len phien ban moi", "bump", "cap nhat deps", "update all", "upgrade latest". MAINTAIN→CLEAN: "clean up", "remove dead code", "unused deps", "tidy", "don code", "don rac", "xoa rac", "don file thua", "remove unused", "loai bo thua", "dep nha", "gom lai cho gon". MAINTAIN→PERF: "it's slow", "optimize", "bundle too big", "lighthouse", "n+1", "cham qua", "lag", "chay lau", "nang", "toi uu toc do", "web chay lau", "bi dung", "bi cham", "lam sao cho nhanh". MAINTAIN→ROLLBACK: "rollback", "revert", "undo", "go back", "previous version", "lui lai", "quay lai", "ban truoc", "ban cu", "huy thay doi", "revert commit", "quay ve hom qua", "rollback deploy". MAINTAIN→REFACTOR: "rename", "extract", "split file", "move file", "refactor", "doi ten", "tach file", "chia file", "di chuyen file", "tach component", "extract ra component", "clean this up without behaviour change". MAINTAIN→TYPES: "sync types", "gen types", "regen types", "supabase types", "dong bo type", "gen type supabase", "lam lai type", "api types". MAINTAIN→SEED: "seed data", "fake data", "sample data", "dummy data", "tao data test", "seed dum", "data gia", "fake data vao db", "data mau". MAINTAIN→REVIEW: "review before push", "pre-push check", "self review", "tu review", "kiem tra truoc khi push", "lint+type+test", "check het truoc". MAINTAIN→SECURITY: "check security", "audit", "security scan", "is it safe", "kiem tra bao mat", "quet bao mat", "audit du an", "co an toan khong", "scan bao mat", "check p0", "xem co lo khong". MAINTAIN→STACK-SWAP: "swap X for Y", "replace X with Y", "migrate from X to Y", "doi X sang Y", "thay X bang Y", "doi polar sang stripe", "chuyen supabase sang drizzle", "bo shadcn dung radix". MAINTAIN→STATUS: "status", "dashboard", "health check", "project overview", "trang thai", "tong quan", "xem tinh hinh", "du an the nao", "check status", "report du an", "/taw status". MAINTAIN→MEMORY: "memory", "claude.md", "claude md", "agents.md", "bo nho", "bộ nhớ dự án", "gen claude.md", "init memory", "refresh memory", "update claude.md", "nest claude", "luu context", "lưu context du an", "nho nghiep vu", "check drift claude". ADVISOR→ANALYZE: "analyze", "phan tich", "review code", "review feature", "doc code roi noi", "code quality review", "review kien truc", "opinion ve", "check auth flow", "review 1 feature", "feedback ve code". ADVISOR→SUGGEST: "suggest feature", "de xuat tinh nang", "goi y tinh nang", "goi y feature", "nen build gi tiep", "them gi", "ideas for app", "what should i add", "recommend next feature", "feature mới", "tính năng mới". ADVISOR→COVERAGE: "coverage", "test coverage", "da test du chua", "code path", "user flow coverage", "gaps in tests", "xem coverage". ADVISOR→ADVERSARIAL: "adversarial", "red team", "attack", "tim lo hong", "break code", "find bugs deeper", "stress test code", "security adversarial". ADVISOR→SCOPE-CHECK: "scope check", "scope creep", "built dung chua", "intent vs diff", "missing requirement", "check PR scope", "PR too big".
Security AStatic scan found no risk patternsHow grading works ›
From the source SKILL.md
You are /taw. User gives you free-form prose in any language (VN, EN, mixed). You classify the intent, load exactly ONE branch file, and follow it. You do NOT execute the full orchestration yourself — the branch file contains the step-by-step logic for that intent.
What this skill does
Taw is a community-contributed Claude Code skill in the security-misc sub-category. It ships as a SKILL.md file that Claude Code auto-discovers under ~/.claude/skills/taw/ and loads when your prompt matches the skill's trigger.
Who uses this skill
The Taw Claude Code skill is built for security engineers, penetration testers, DevSecOps practitioners, and development teams hardening codebases and infrastructure. It's part of ClaudSkills (also referred to as Claude Skills or Claude Code Skills) — the open community-curated registry of 153,000+ SKILL.md files for Anthropic's Claude Code agent and the wider Claude ecosystem (Claude API, Claude Agent SDK).
How to install
Free
Manual install (2 steps)
mkdir -p ~/.claude/skills/taw
curl -L https://claudskills.com/skills/taw/SKILL.md \
-o ~/.claude/skills/taw/SKILL.md
Or just download SKILL.md directly and drop it into ~/.claude/skills/taw/. Claude Code auto-discovers it on next session.
Skills live at ~/.claude/skills/taw/SKILL.md on macOS/Linux, or %USERPROFILE%\.claude\skills\taw\SKILL.md on Windows. See the full install guide for step-by-step instructions.
Telegram
📱 Install from your phone or desktop Telegram
Open @claudskills_bot on Telegram, tap Open Desktop App, and the desktop app installs this skill for you. Or share the bot link with a colleague — they get the same one-tap install. Learn more →
Pro
One-click install via the desktop app
The ClaudSkills desktop app installs any skill directly into ~/.claude/skills/ with one click — no terminal required. Pro starts at $9/mo or $149 lifetime.
Pro
For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.
Frequently asked questions
How do I install the Taw Claude Code skill?
Install via the ClaudSkills desktop app (one click) or copy
SKILL.md from the source repository to
~/.claude/skills/taw/SKILL.md and restart Claude Code. Both flows are detailed at
claudskills.com/install/.
What does the Taw skill do?
Single entrypoint for taw-kit. User types `/taw <anything in VN or EN>` — this skill classifies the intent (BUILD / FIX / SHIP / MAINTAIN / ADVISOR) and loads the matching branch file to execute. Replaces the old one-command-per-task model (/taw-new, /taw-add, /taw-fix, /taw-deploy, /taw-security) with a single unified command. Supports dev workflows out of the box: test, upgrade, clean, perf, rollback, refactor, types, seed, review, stack-swap, status, and ADVISOR group (analyze, suggest, coverage, adversarial, scope-check) for opinionated review of existing code. User-visible strings match the user's input language (Vietnamese by default for VN users). Two modes: SAFE (default — clarify + approval, max 1 round-trip) and YOLO (skip gates, smart defaults — for demos/power users). YOLO triggers: prose contains `yolo`, `nhanh nha`, `lam luon`, `khoi hoi`, `auto`, or args start with `yolo`. Trigger phrases (EN + VN) — broad match so user can keep typing plain prose without re-invoking /taw every turn. Grouped by branch: BUILD (create/add): "build me", "make me", "create a", "scaffold", "I need an app", "add a feature", "extend with", "new project", "start with template", "lam cho toi", "tao cho toi mot", "xay dung", "lam landing page", "lam website", "can mot app", "shop online", "tao du an", "them tinh nang", "toi muon them", "them trang", "them form", "them nut", "mo rong voi". FIX (diagnose+fix): "fix it", "it's broken", "build fail", "error", "crash", "something's wrong", "doesn't work", "loi roi", "bi loi", "hong roi", "be roi", "khong chay", "khong chay duoc", "fix giup toi", "website bi hong", "co loi xuat hien", "sua loi", "sua giup toi", "co van de", "bi van de", "chet roi", "sap roi", "crash roi". SHIP (deploy): "deploy this", "publish the site", "go live", "push to vercel", "dockerize", "deploy to vps", "deploy di", "day len vercel", "len mang", "len prod", "publish di", "len live", "day len host", "day code len server". MAINTAIN→TEST: "test it", "write tests", "gen tests", "add tests", "test dum", "viet test", "gen test", "test cai", "kiem thu", "chay test", "can test cho", "add unit test", "add e2e". MAINTAIN→UPGRADE: "upgrade", "bump deps", "update packages", "upgrade next", "upgrade react", "nang cap", "nang version", "len phien ban moi", "bump", "cap nhat deps", "update all", "upgrade latest". MAINTAIN→CLEAN: "clean up", "remove dead code", "unused deps", "tidy", "don code", "don rac", "xoa rac", "don file thua", "remove unused", "loai bo thua", "dep nha", "gom lai cho gon". MAINTAIN→PERF: "it's slow", "optimize", "bundle too big", "lighthouse", "n+1", "cham qua", "lag", "chay lau", "nang", "toi uu toc do", "web chay lau", "bi dung", "bi cham", "lam sao cho nhanh". MAINTAIN→ROLLBACK: "rollback", "revert", "undo", "go back", "previous version", "lui lai", "quay lai", "ban truoc", "ban cu", "huy thay doi", "revert commit", "quay ve hom qua", "rollback deploy". MAINTAIN→REFACTOR: "rename", "extract", "split file", "move file", "refactor", "doi ten", "tach file", "chia file", "di chuyen file", "tach component", "extract ra component", "clean this up without behaviour change". MAINTAIN→TYPES: "sync types", "gen types", "regen types", "supabase types", "dong bo type", "gen type supabase", "lam lai type", "api types". MAINTAIN→SEED: "seed data", "fake data", "sample data", "dummy data", "tao data test", "seed dum", "data gia", "fake data vao db", "data mau". MAINTAIN→REVIEW: "review before push", "pre-push check", "self review", "tu review", "kiem tra truoc khi push", "lint+type+test", "check het truoc". MAINTAIN→SECURITY: "check security", "audit", "security scan", "is it safe", "kiem tra bao mat", "quet bao mat", "audit du an", "co an toan khong", "scan bao mat", "check p0", "xem co lo khong". MAINTAIN→STACK-SWAP: "swap X for Y", "replace X with Y", "migrate from X to Y", "doi X sang Y", "thay X bang Y", "doi polar sang stripe", "chuyen supabase sang drizzle", "bo shadcn dung radix". MAINTAIN→STATUS: "status", "dashboard", "health check", "project overview", "trang thai", "tong quan", "xem tinh hinh", "du an the nao", "check status", "report du an", "/taw status". MAINTAIN→MEMORY: "memory", "claude.md", "claude md", "agents.md", "bo nho", "bộ nhớ dự án", "gen claude.md", "init memory", "refresh memory", "update claude.md", "nest claude", "luu context", "lưu context du an", "nho nghiep vu", "check drift claude". ADVISOR→ANALYZE: "analyze", "phan tich", "review code", "review feature", "doc code roi noi", "code quality review", "review kien truc", "opinion ve", "check auth flow", "review 1 feature", "feedback ve code". ADVISOR→SUGGEST: "suggest feature", "de xuat tinh nang", "goi y tinh nang", "goi y feature", "nen build gi tiep", "them gi", "ideas for app", "what should i add", "recommend next feature", "feature mới", "tính năng mới". ADVISOR→COVERAGE: "coverage", "test coverage", "da test du chua", "code path", "user flow coverage", "gaps in tests", "xem coverage". ADVISOR→ADVERSARIAL: "adversarial", "red team", "attack", "tim lo hong", "break code", "find bugs deeper", "stress test code", "security adversarial". ADVISOR→SCOPE-CHECK: "scope check", "scope creep", "built dung chua", "intent vs diff", "missing requirement", "check PR scope", "PR too big".
Is this skill free to install?
Yes. ClaudSkills is an open registry — every skill keeps its source repository's license, and manual install via copy is free. ClaudSkills Pro ($9/mo, $79/yr, or $149 one-time) adds one-click install via the desktop app and a multi-signal Quality Score.
When should I use the Taw skill?
Use Taw when your Claude Code task falls under the Security category — specifically in the security misc area. Claude Code auto-discovers installed skills and invokes the right one based on the task description, so you can also ask Claude directly (e.g. "use Taw" or describe the task and let Claude pick). Browse related skills at
/category/security/.
What is a Claude Code skill and how does the Taw skill fit in?
A Claude Code skill is a
SKILL.md file that lives under
~/.claude/skills/<name>/ and tells the Claude Code CLI agent how to perform a specific task (instructions, prompts, allowed tools). Skills are auto-discovered at session start. Taw is one of 67,000+ skills indexed in the open ClaudSkills catalog, classified under the Security category. Learn more at
/learn/what-is-a-claude-skill/.
Cite this skill
If you reference this skill in a blog post, paper, or documentation, you can cite it as:
APA
ClaudSkills. (2026). Taw [Claude Code skill]. ClaudSkills. https://claudskills.com/skills/taw/
BibTeX
@misc{taw-2026,
author = {ClaudSkills},
title = {Taw [Claude Code skill]},
year = {2026},
publisher = {ClaudSkills},
url = {https://claudskills.com/skills/taw/}
}
Embed this skill
Promote, attribute, or link this skill from your own README, blog post, or documentation. All three snippets are free to use — no sign-up, no API key. More distribution surfaces →
Badge
[](https://claudskills.com/skills/taw/?utm_source=badge&utm_medium=readme&utm_campaign=skill_badge)
<script>
<script src="https://claudskills.com/embed/taw.js" async></script>
<iframe>
<iframe src="https://claudskills.com/embed/taw.html" width="100%" height="160" frameborder="0" loading="lazy" title="ClaudSkills: Taw"></iframe>
Security scan
Grade A · scanned 2026-07-18 — free static scan against the OWASP Agentic Skills Top 10.
No risk patterns were found in any of the ten OWASP-aligned categories. How grading works ›
- ✓ Prompt injection
- ✓ Data exfiltration
- ✓ Supply chain
- ✓ Reverse shell
- ✓ Credentials
- ✓ Execution
- ✓ Filesystem
- ✓ Persistence
- ✓ Obfuscation
- ✓ Network
Show this grade on your repo (click to copy):
[](https://claudskills.com/skills/taw/#security)
More Security skills
Browse all Security skills in the ClaudSkills registry, or explore these other picks from the same category:
Part of Acreator Store — Adam Lankamer's AI tools:
PerfectStudio ·
Ucaption ·
UTagger ·
AutoXPoster ·
TestYourSkills ·
AutomationFlows ·
Au Naturel ·
Telegram @acreatorstore