Menu
Skills in this repository
SkillsMP has collected 116 skills from trungdo9/ClauKit. Open a skill to review its source and details.
trungdo9/ClauKitShowing 40 of 116 collected skills.
XML sitemap analysis and generation — validate an existing sitemap against Google's real rules (50k/50MB caps, lastmod accuracy, extension subtypes), or generate a new one (with index splitting) for a site being built out. Feeds the technical-SEO audit and…
Claude-SEO engine root — the orchestrator behind `/mk:seo audit|keywords|ai|programmatic|schema`. Detects business type (SaaS, local, e-commerce, publisher, agency) from homepage signals, dispatches the 24 sibling seo-* skills/agents in parallel, and…
Search Experience Optimization — reads the SERP backwards to catch page-type mismatches (a blog post competing against product pages), derives user stories from PAA/ads/related-searches, and scores the page from 4-7 SERP-derived personas…
Technical SEO audit across 9 categories — crawlability, indexability, security, URL structure, mobile/page experience, Core Web Vitals, structured-data detection, JavaScript rendering, and IndexNow. Also covers agent-friendly-page auditing (accessibility…
Signup and registration flow optimization — field reduction, social/SSO auth, single vs multi-step, email verification, error and validation UX, drop-off diagnosis, activation handoff. Use when the user says "signup conversions", "registration friction",…
SMS and MMS marketing — opt-in mechanics, TCPA/carrier compliance, flow design (welcome, abandoned cart, post-purchase, win-back, replenishment), segment/character budgeting, cadence and frequency caps, platform selection, and revenue-per-send measurement.…
Write and optimize platform-native social posts — LinkedIn posts and document carousels, X threads, Instagram carousels and Reels, TikTok and Shorts scripts, hooks, hashtags, and character limits. Use for "LinkedIn post", "Twitter thread", "tweet ideas",…
Post-signup activation and first-run experience — aha moment definition, minimum path to value, onboarding checklists, empty states, guided tours, drop-off diagnosis, stalled-user recovery. Use when the user says "onboarding flow", "activation rate", "user…
Market sizing — TAM/SAM/SOM built bottom-up from addressable accounts x realistic ACV, cross-checked against cited published figures, with every number sourced or marked [NEEDS DATA]. Use for "market sizing", "TAM", "SAM", "SOM", "how big is this market",…
In-product paywalls and upgrade moments — feature gates, usage-limit screens, trial-expiration flows, upsell modals, in-app pricing. Use when the user says "paywall", "upgrade screen", "upgrade modal", "upsell", "feature gate", "limit reached", "trial…
Token-efficient headless browser automation for AI agents using a snapshot+refs model (~93% less context than traditional tools)
Answer technical and architectural questions about the codebase with researched, in-depth, context-aware responses (not superficial replies). Reads relevant code files, references specific files + line numbers, and explains architectural decisions / patterns…
Use when brainstorming software solutions, evaluating architectural approaches, debating technical decisions, or exploring feature ideas before implementation. Acts as a senior architect — challenges assumptions, presents 2-3 viable alternatives with…
Puppeteer-based browser automation via single-purpose CLI scripts with persistent sessions and structured JSON output
Use when reviewing a branch, a PR, or work-in-progress changes ("review since X"), when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before…
All testing layers — Vitest unit, Playwright E2E deep-dive (configs, page objects, debugging, traces), Cucumber BDD, mobile (Appium/Detox), API (Supertest/Newman), k6 load, CI/CD integration, credential management. Use when writing or fixing tests, setting up…
Controllable re-creation of Claude Code's dynamic-workflow model on ClauKit's own primitives — markdown recipes + Agent-tool fan-out/pipeline over the 30 existing agents, with 4-axis inheritance and hard gates. Use when a task needs deterministic large-ish…
Use when you need to plan technical solutions that are scalable, secure, and maintainable.
Create presentations and slide decks (Marp, reveal.js, Quarto) from markdown or notebooks
Use when you need to research, analyze, and plan technical solutions that are scalable, secure, and maintainable.
Design real-world test scenarios — user journeys, role-based flows, recovery paths — independent of execution tool (pytest, Playwright, Postman, etc.).
Complete security suite — expert mindset + active code scanner. Covers OWASP 2025, supply chain, L1-L4 data flow analysis, 21 vulnerability rules with a cost-tiered default pass, TINY/SMALL/LARGE scan modes, bilingual output (vi/en). Use when scanning code…
Red-green test-driven discipline — NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST. Use for bug fixes (default), regression-prone changes, or when asked to "write tests first" / "TDD this". Covers red → verify-red → green → verify-green → refactor, the…
Break a plan, spec, or the current conversation into vertical tracer-bullet tickets, each declaring the tickets that block it — written as one file per ticket under plans/<plan-dir>/tickets/, or published as issue-tracker sub-tasks under a parent issue on…
Drive a feature from spec to production through hard-gated stages — plan, code, test, docs, deploy — with verification at each gate. Infrastructure-agnostic methodology.
Comprehensive Python development skills covering FastAPI, Django, Flask, data/ML integration, and best practices. Use when building Python backends, APIs, data pipelines, or ML applications.
Design, debug, and optimize AI agent systems when context limits hinder performance — diagnose context degradation, apply Write/Select/Compress/Isolate strategies, and build multi-agent architectures that maximize reasoning quality per token.
Git operations with conventional commits (cm, cp, pr, merge, finish) — scoped commits from the claim registry, finish-branch protocol with draft-default PRs + paste-ready auth fallback, and declared delivery-tail execution semantics
Use when the user needs to CREATE, VERIFY, ANALYZE, or REFACTOR a CLAUDE.md file (the project-instructions file Claude Code loads every session). Triggers on "/ck:claude-md", "write CLAUDE.md", "audit CLAUDE.md", "verify CLAUDE.md", "CLAUDE.md too long",…
Systematic debugging framework ensuring root cause investigation before fixes. Includes four-phase debugging process, backward call stack tracing, multi-layer validation, and verification protocols. Use when encountering bugs, test failures, unexpected…
Create aesthetically beautiful interfaces following proven design principles. Use when building UI/UX, analyzing designs from inspiration sites, generating design images with ai-multimodal, implementing visual hierarchy and color theory, adding…
Initialize projects from scratch with modular scaffolds (Next.js, Vite, Svelte, Python, etc.)
Port and refactor a feature from a public GitHub repo into the local codebase. Use when user wants to copy/adapt an existing implementation (auth flow, payment integration, UI component, algorithm, etc.) from another repo rather than build from scratch.…
Durable per-plan run ledger (STATE.md) so a killed multi-phase run resumes with zero re-implementation. Use for any multi-phase run (/ck:cook, /ck:flow, /ck:fix, /ck:refactor), when resuming an interrupted run, after a spend/session kill, or after context…
Orchestrate parallel multi-session collaboration with independent Claude Code teammates. CK-native (v2.1.0) engine that spawns independent Claude Code sessions as teammates — each with own context window, task ownership, and persistent cross-session memory.…
PostgreSQL database guide — SQL queries, JOINs, CTEs, window functions, indexing, EXPLAIN/ANALYZE, user management, backups, replication, psql CLI. Use when writing SQL queries, designing schemas, optimizing performance, or administering PostgreSQL databases.…
Use when the user needs a LARGE MECHANICAL change across the codebase — rename a symbol everywhere, extract a module, migrate an API surface, run a codemod, convert patterns (e.g. class→hooks, callbacks→async/await). Distinct from `/ck:cook` (feature work)…
Falsify a plan's factual claims before implementing against them. Use before executing any plan written in another session (/ck:cook --from-plan), via /ck:plan verify <path>, or whenever a plan asserts existing-behaviour facts (a root cause, "X currently does…
Convert an existing codebase into a CLI + MCP server so AI agents can invoke its functions as tools — picking what to expose, defining schemas, handling auth and side effects.
Organize directory layout, naming, and module boundaries in an existing or growing codebase — monorepo vs polyrepo, src-vs-flat layouts, conventions that scale past 1000 files.