smk-labs
OrganizationOne marketplace for everything I have built for Claude Code: plugins, skills, commands, and agents, organized by category.
Categories
Indexed Skills (34)
web-animation-engine
Build code-driven animated web sections, scenes, and explainers using a tiny bundled React + SVG runtime (Stage / Sprite / playhead). Use this skill whenever the user wants to *create* an animation from scratch — animated heroes, motion graphics, diagrammatic explainers, animated dashboards, scrubable scene compositions, or "bring this SVG to life" requests. Output is runnable HTML (CDN React + Babel, no npm) embeddable in any website or used standalone in presentations. Pairs with /frontend-design for visual polish; differs from UI-micro-interaction skills which polish *existing* UIs rather than compose new animated content.
connect
Report or change where the readable card server is registered across this machine's Claude profiles. Use FIRST when cards stop rendering or show raw HTML. Triggers: "connect readable", "turn cards on", «کارتها رندر نمیشن».
gouya
سبک نوشتن فارسی: ساده, کوتاه, مرتب, آدموار; نه ترجمهزده, نه اداری. روی هر جواب فارسی اعمال شود. Persian only; does not apply to other languages.
copy-writing-fa
Write Persian web copy (blog articles, product descriptions, landing pages, category text, microcopy, meta titles and descriptions) using Cursor workers, so the writing runs on the Cursor subscription's quota instead of Claude's. Use when the user asks for Persian content for a site, says "متن فارسی بنویس", "مقاله بنویس", "توضیح محصول بنویس", "کپیرایتینگ فارسی", "محتوای سئو", "copy for the site in Persian", or wants blog/product/landing copy generated at volume. Also use to edit, proofread, or de-AI existing Persian copy. Claude writes the brief and accepts the result; Cursor writes and lints.
cursor-delegate
Delegate a coding or research task to the Cursor CLI (cursor-agent) so it runs on the Cursor subscription's quota instead of Claude's, with Claude still orchestrating. Use when the user says "delegate to cursor", "run this with cursor-agent", "offload to cursor", "spend the cursor quota", "have cursor do it", or wants to hand a heavy self-contained slice of a larger job to a second agent. Works with the user's default Cursor login; an optional account name targets a specific seat.
mkprompt-goal
پرامپتساز هدفمحور و پیشفرض: هدف یک سطح بالاتر, راه تأیید کار, شرط توقف عینی. Triggers: «پرامپت بساز», «پرامپت بده», «پرامپت هدفمحور», "write me a prompt for". برای گاردریل سفت از mkprompt-classic استفاده کن.
swarm-qa
کارزار کامل «سوارم کیوای» روی یک محصول زنده با متد چهار فازی: ممیزی استاتیک سوارمی کد، کیوای عمیق زنده، سوارم فیکس، و کیوای تأیید نهایی. با چکپوینت روی دیسک و گزارش تاریخدار. Use when the user says "سوارم کیوای", "سوارم", "swarm qa", "/swarm-qa", "کیوای کامل بزن", or asks for a full multi-agent QA campaign over a live stack. Not for a quick single-page check.
decode
کدبیس رو مثل یه سینیور برای مدیر محصول قصه میکنه: قصهٔ دو دقیقهای از بالا، درخت فایل قابلگشتن مثل VS Code با وزندهی اهمیت، کانواس خلاصه برای هر فایل، درسهای کوچیک مهندسی برای مسیر PM به دولوپر، و ترجمهٔ دیف یا PR مثل ریلیز نوت. Use when the user says «دیکد», «decode», «/decode», «قصهٔ کدبیس», «این فایل چی کار میکنه», «این کد رو به زبان ساده توضیح بده», «برای پیام توضیح بده», «به زبان محصول», «اطلس کدبیس», «نقشهٔ کدبیس», «این تغییرات یعنی چی», "explain this file for a PM", "what does this code do in product terms", "codebase tour", "codebase atlas", "product-language changelog".
fig
Make a fig. A single looping animated SVG, one self-contained HTML file you can drop in an email or a slide. Use it when an idea moves (flows, loops, retries, queues, fan-outs). Faster than a paragraph, livelier than a static diagram. No player, no deck.
learn
The way into learnable and the way back. If a course already exists here it continues from exactly where the learner stopped, next lesson, next chapter, no re-planning. If nothing exists yet it asks whether to measure their level first or go straight to building a course. Use when the user says they want to learn, study, continue, resume, keep going, "ادامه", "درس بعدی", "بریم یاد بگیریم", "شروع کنیم", "continue the course", "next lesson", "where were we", or invokes /learnable:learn. Also the right entry point when someone mentions learnable without naming a specific step.
new-course
Build a whole course on a subject, from scratch, on disk. A light survey of the domain, then the placement-quiz decision, then a deep multi-agent research pass that becomes an ordered taxonomy, a table of contents grouped into books and chapters, and a course folder that teaches itself. Use when the user asks for a course, curriculum, syllabus, study plan, roadmap or taxonomy on a topic, says "دوره بساز", "کورس جدید", "برنامه درسی", "نقشه یادگیری", "build me a course on X", "I want to learn X properly", or invokes /learnable:new-course. Run once per subject; use /learnable:new-book afterwards for each book of chapters.
self-assess
Placement quiz that finds someone's real level in a subject and writes it to PROFILE.md. Scenario questions in small batches, never definitions, with neutral options that cannot be eliminated by tone, plus self-report checks that separate knowing a word from being able to act on it. Use when the user asks to measure their level, wants a placement, diagnostic or self assessment, says "تعیین سطح", "آزمون بگیر", "سطحم رو بسنج", "خودارزیابی", "test my level", "where am I in X", "assess me on X", or invokes /learnable:self-assess. Also invoked by /learnable:new-course before it designs a curriculum, and re-run later to measure progress against the earlier profile.
gitlab-helm-deploy
Generate a GitLab CI/CD pipeline and Helm chart that builds the current project with kaniko, pushes to the GitLab Container Registry, and deploys to a Kubernetes namespace via a kubeconfig CI variable. Use when the user asks to set up CI/CD, create a GitLab pipeline, write a Helm chart, containerize and deploy an app to Kubernetes/GKE, or wire up "push to deploy". Also generates a Dockerfile tailored to the detected runtime when one is missing, handles backend + frontend split repos, and covers both ingress-nginx and Gateway API routing.
k8s-rightsize
Right-size Kubernetes pod CPU/memory requests from real Prometheus usage data (per-pod p95 CPU, p98 memory over 7 days), compute how many nodes the cluster needs, and tune KEDA queue-based autoscaling. Use when the user asks to rightsize workloads, fix over/under-provisioned requests, cut node count or cloud cost, size Celery or background workers, tune KEDA listLength or HPA settings, or answer "how many nodes do we need". Works for any namespace with kube-prometheus and cAdvisor metrics.
owasp-security
Deep OWASP reference for security reviews and secure implementation. Covers OWASP Top 10:2025, ASVS 5.0 levels, secure code patterns (injection, auth, error handling, fail-closed), language-specific security quirks for 20 languages, OWASP LLM Top 10 (2025), and Agentic AI security (2026). Use when reviewing code for security vulnerabilities, implementing authentication/authorization, handling user input, hardening an LLM or AI-agent application, or discussing web application security in depth.
secure-coding
Apply a baseline of secure-coding standards to code being written or reviewed. Covers auth, secrets management, input validation, injection prevention, password hashing, PII handling, dependency hygiene, rate limiting, CORS, security headers, HTTPS, error/logging discipline, and infra hardening. Use proactively whenever the user writes or edits authentication/authorization logic, login/session/token code, API endpoints, database queries, file uploads or external input handling, credential storage, secret/config loading, CORS or header configuration, error handlers, logging, or any Dockerfile/k8s/IAM config. Also trigger on explicit asks like "security review", "is this safe", "audit this", "check for vulnerabilities", or mentions of OWASP, injection, XSS, CSRF, or SSRF. Even if the user doesn't ask for a security check, flag clear violations in code they're touching.
principles-first
Apply first-principles thinking and design-thinking to product, architecture, and communication decisions. Use this skill whenever the user is framing a problem, choosing between alternatives, debating a tradeoff, questioning a design, adding scope, or saying "should we…" / "that's how it's always done." Also trigger when about to add complexity, recommend a feature, or pick a default — those are where principle drift happens. Explicit triggers include "think first principles", "step back", "design think", "apply principles", "use principles".
brand
Give THIS project its own readable brand - after this, every chat card and /report in the project renders in the project's palette, logo, and font. Detects the identity from the repo (design tokens, tailwind config, DESIGN.md, logos) or interviews the user when none exists, then writes a committable .readable/ layer. Use when the user asks to "brand readable", "brand the cards/reports", "make reports match our brand", "رنگ و لوگوی خودمون روی کارتها/گزارشها", or invokes /readable:brand.
report
Export a reply or chat card as a standalone styled HTML report file, in the exact readable card template (Persian RTL with Vazirmatn, or English LTR with Inter). Use ONLY when the user explicitly asks to save, export, file, or extend THE CURRENT widget/card ("همین کارت رو ذخیره کن", "کاملترش رو بهصورت فایل بساز", "save this card as a report") or invokes /readable:report directly. NEVER auto-trigger on generic report-writing requests ("گزارش بساز", "write a report") that do not mention saving a file or this template.
spring-clean
Deep-clean and simplify a whole repo or codebase, then leave guardrails so it stays clean. Delete dead surfaces, gitignore build artifacts, relocate dev docs, notes, clones and dumps to the project's workspace repo (the assistant-dev home base), split oversized files and functions, unify duplicated logic, draw package boundaries, run a clean-code pass (naming, function size, DRY, KISS, magic numbers, linter-warning burn-down), and encode the rules as architecture tests. Use when the user asks to clean up, declutter, tidy, simplify, restructure, or modularize a repo, asks for clean code or SOLID, wants dev docs moved out of the code tree, says "spring clean", "housekeeping", "خونه تکونی", "تمیزکاری", "کلین کد", "سادهسازی کدبیس", "ریپو رو مرتب کن", complains that the repo is a mess or a file is huge, or wants dead code removed and LoC reduced. Repo-scale work on the whole tree or a subtree, not a single diff.
mkprompt-classic
پرامپتساز تشریحی با نقش, کانتکست, گاردریل و فرمت گزارش, برای قید سفت. Triggers: «پرامپت کامل», «پرامپت تشریحی», «با گاردریل», "classic". برای پرامپت معمولی از mkprompt-goal استفاده کن.
workspace-rules
Give a repo its house rules at the cheapest layer: what the workspace tells a session up front, plus what turns the build red afterwards (linter setting, architecture test, hook). Triggers: "house rules", "write a CLAUDE.md", "set up .claude", "turn this rule into a test", «قانون بذار», «قوانین پروژه».
mkprompt-redesign
پرامپتساز بازطراحی چندراندی که نمیگذارد راندها به رنگ و فاصله تنزل کند. Triggers: «پرامپت بازطراحی», «این طراحی رو بهتر کن», "redesign prompt", "iterate on this design". برای پرامپت معمولی از mkprompt-goal استفاده کن.
cursor-orchestrate
Run a fleet of Cursor CLI workers on a large multi-part job while Claude does architecture, decomposition and review. Triggers: "orchestrate with cursor", "cursor fleet", "fan out to cursor agents", or a delegation too big for one worker.
getpix
Find and fetch free licensed stock photos (Pexels, Unsplash, Openverse, Wikimedia): add optimized WebP to a site, or show a photo in chat. Triggers: "find an image of X", «عکس پیدا کن», «عکس بذار». Not AI generation; for a whole site use photo-pass.
photo-pass
End-to-end art-direction photo pass over a whole site: audit where photos earn their place, set one visual language, source, integrate, verify both themes, record credits. Triggers: "photo pass", "add photos to the site", «به سایت عکس بده». For one image use getpix.
new-book
Write the next book of a learnable course, every chapter and lesson, researching only where a chapter needs it. Triggers: «کتاب بعدی», «درسهای بعدی رو بنویس», "write the next book", a missing chapter file. Needs a course from new-course.
open-design-guide
Local Open Design library: real tokens for 151 design systems, 71 design skills, 114 render templates. Use only on an explicit ask: "open design", "od", "DESIGN.md", "brand contract", or naming a bundled system.
mini-research
تحقیق سبک و سریع چندایجنتی (mini research؛ عمداً نه deep research) روی یک موضوع. ورودیها: موضوع، و اختیاری: مدل ایجنتها (haiku یا sonnet یا opus)، نکات ویژهٔ تمرکز، تعداد ایجنت، ذخیرهٔ خروجی. Use when the user says "mini-research", "/mini-research", "تحقیق سبک", "یه ریسرچ کوچیک", "چند ایجنت بگرد", "با چند ایجنت هایکو بگرد", "با ایجنتهای اپوس بگرد", "mini research on X".
publish
گزارش را با readable بساز، بعد از تأیید روی پورتال صفحهاش کن، و آخرش یک ایمیل کوتاه به لحن خودم با لینک همان صفحه بده. Use when the user says "منتشر کن", "بذار روی پورتال", "صفحهاش کن", "لینکش کن", "publish this", "put it on the portal", "share this as a page", "/publish".
steps
دستورالعمل گامبهگام به زبان ساده برای انجام یک کار: گرفتن کلید API، راهاندازی یک سرویس یا ابزار، کار اداری، هر روال چندمرحلهای. فقط گامهایی که خود کاربر باید انجام دهد. Use when the user says "چطور", "چه جوری", "دستورالعمل بده", "گام به گام بگو", "steps", "/steps", "how do I get/set up X", "step by step instructions".
visualize
Turn an answer into a light visual (flowchart, timeline, comparison, architecture sketch), in any language. Trigger ONLY when the user explicitly asks to see something visual, e.g. "show me", "visualize this", "show it as a diagram", "draw it", "با شکل نشون بده", "شماتیکش رو بکش", "تصویریش کن". Never auto-trigger just because content is flow-shaped. Uses the widget tool with minimal, theme-aware SVG.
mkprompt
پرامپتساز: از روی موضوعی که کاربر میدهد، یک پرامپت کامل و آماده برای ایجنت یا سشن مستقل میسازد و آن را خام در متن چت میفرستد تا همانجا کپی شود. Use when the user says "پرامپت بساز", "یه پرامپت آماده کن برای", "پرامپت بده", "پرامپت کامل", "mkprompt", "/mkprompt", "write me a prompt for", or asks to prepare a standalone prompt to hand to another agent or session.
go
وضعیت فوقخلاصه + ادامهٔ خودکار کار ناتمام. وقتی سشن وسط کار قطع شده یا کاربر میگوید «ادامه», «ادامه بده», «وضعیت چیه», «چه خبر», «go», «/go», or wants to resume after a disconnect: سه سطر وضعیت بده و بلافاصله از همان نقطه ادامه بده. Never restart from scratch.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.