svyatov
UserPersonal agent toolkit — reusable skills and plugins for Claude Code, Cursor, Codex, and Gemini CLI
Categories
Indexed Skills (14)
commit
Git commit workflow with conventional commits, branch creation, push, and PR support. Use when the user asks to commit, save changes, push, ship it, open a PR, send a PR, or says "/commit". Also triggers on short aliases: "cp" (commit and push), "cb" (commit to new branch), "cpr" (commit and PR). Trigger phrases: "commit", "commit and push", "commit new branch", "commit to new branch", "commit and pr", "commit push pr", "commit pr", "cp", "cb", "cpr", "push this up", "save my changes", "ship it".
astro
Skill for building with the Astro web framework (v6+). Covers component authoring, islands architecture (client and server islands), content collections with loaders, actions, sessions, view transitions, middleware, on-demand rendering (SSR), adapters, and project configuration. Use when the user works with Astro, mentions .astro files, asks about static site generation (SSG), islands architecture, content collections, server islands, actions, view transitions, deploying an Astro project, or upgrading Astro.
browser-bugs
Audit frontend code for 50 known cross-browser bugs and mobile compatibility pitfalls documented in 'Fifty Problems with Standard Web APIs in 2025.' Scans HTML, CSS, and JavaScript/TypeScript for patterns that break on Safari iOS, Firefox iOS, Chrome, and mobile browsers — then produces a severity-ranked report with specific fixes. Use this skill when the user asks to check for browser bugs, audit cross-browser compatibility, review mobile compatibility, check Safari issues, find iOS bugs in their code, or asks why something doesn't work on mobile/Safari/Firefox. Also trigger when the user mentions viewport units breaking, audio not playing on iOS, drag-and-drop not working on mobile, fullscreen issues, or touch interaction problems.
command-creator
Guides creation of Claude Code slash commands. Use when users ask to "create a command", "make a slash command", "add a command", want to automate a repetitive workflow ("I keep doing X, can we make a command for it?"), or want to document a consistent process as a reusable slash command — project-level or global.
generate-cicd
Generate CI/CD workflows (GitHub Actions) through interactive conversation by analyzing repository structure and user preferences. Use when the user asks to: (1) set up CI/CD for a project, (2) create GitHub Actions workflows, (3) add automated testing/building/deployment pipelines, (4) improve or review existing CI/CD configuration. Also use when the user mentions automating tests, running checks on PRs, or deploying on merge — even without explicitly saying "CI/CD". Triggers on: "CI/CD", "CI", "GitHub Actions", "workflow", "pipeline", "continuous integration", "continuous deployment", ".github/workflows", "automate tests", "run checks on PRs", "deploy on merge".
generate-dockerfile
Generate optimized, secure, multi-stage Dockerfiles and .dockerignore files for any project. Use when the user asks to: (1) containerize a project, (2) create or generate a Dockerfile, (3) improve or optimize an existing Dockerfile, (4) add Docker support to a project, (5) review a Dockerfile for best practices. Also use when the user wants to make something deployable, set up containers, or ship an app — even without mentioning Docker explicitly. Triggers on: "Dockerfile", "dockerize", "containerize", "Docker build", "docker image", ".dockerignore", "make this deployable", "container setup", "production-ready setup", "ship this app".
generate-favicon
Generate a minimal, modern favicon set from an SVG source — ICO, SVG with dark mode, Apple Touch Icon, PWA icons, manifest, and HTML tags. Use when the user asks to create favicons, set up site icons, add a favicon to their project, generate PWA icons, or mentions needing apple-touch-icon, manifest icons, or favicon.ico files.
humanizer
Remove signs of AI-generated writing from text — specifically tuned for Claude output. Use when editing, reviewing, or polishing any text to make it sound more natural and human-written. Trigger this skill when the user asks to humanize, de-AI, clean up, or improve the tone of written content — blog posts, docs, PR descriptions, READMEs, emails, articles, or any prose that reads like it was generated by an LLM. Also use when reviewing text and noticing AI patterns like markdown overuse, AI vocabulary, sycophantic openers, post-action summaries, vague attributions, significance inflation, or em dash overuse.
import-skill
Import skills from GitHub repositories into the local toolkit. Supports copying a single skill from a GitHub directory URL or merging multiple skills into one. Also accepts pasted skill content. Use when the user asks to: (1) import, add, or copy a skill from GitHub, (2) merge multiple skills into one, (3) paste skill content to create a new local skill. Triggers on: "import skill", "add skill from", "copy skill", "merge skills", "fetch skill", "grab skill", "skill from GitHub".
improve-architecture
Explore a codebase to find architectural improvement opportunities with an assessment gate that stops if architecture is already healthy. Prevents god objects through cohesion checks and includes mandatory test writing for new module boundaries. Use when user wants to improve architecture, consolidate tightly-coupled modules, simplify module boundaries, deepen shallow modules, or improve testability. Also triggers on: 'clean up the architecture', 'too many small files', 'these modules are tangled', 'hard to test', 'refactor for testability'.
refactor
ALWAYS use this skill before refactoring any code. It prevents over-refactoring and wrong refactoring by requiring an assessment first — catching code that is already clean, problems that are architectural rather than code-level, and missing test coverage that must exist before touching business logic. Trigger on: refactor, clean up, simplify, reduce complexity, code smells, messy code, break up function, reduce nesting, remove dead code, file too big, extract method, too many parameters, duplicated code, cognitive complexity, god class, magic numbers. Also trigger when a linter or static analysis tool flags complexity issues. Language-agnostic.
taskwarrior
Taskwarrior CLI reference for managing tasks, bugs, and work items from the terminal. This skill contains the correct syntax for filters, dates, recurrence, UDAs, urgency tuning, custom reports, contexts, and hooks that you CANNOT reliably produce from memory alone — Taskwarrior's syntax is unusual (attribute:value, +tag, virtual tags like +OVERDUE) and easy to get wrong. ALWAYS use this skill when the user: (1) runs or asks about any `task` command, (2) wants to add, modify, complete, delete, or list tasks, (3) asks what's due, overdue, or what to work on next, (4) wants to track bugs or work items from the command line, (5) mentions priorities, projects, tags, filters, recurring tasks, or contexts, (6) wants a custom report, UDA, hook script, or urgency tuning, (7) mentions Taskwarrior by name. Do NOT skip this skill just because the request sounds simple — even basic operations like `task add` have non-obvious attribute syntax that differs from other CLI tools.
writing-clearly-and-concisely
Use when writing any prose humans will read — documentation, README files, commit messages, error messages, PR descriptions, UI copy, help text, reports, summaries, or explanations. Applies Strunk's timeless rules for clearer, stronger, more professional writing. Use this even for short text like error messages, log messages, or inline comments. If you're writing sentences for a human to read, use this skill.
grill-me
Interview the user relentlessly about a plan, design, or idea until reaching shared understanding, walking each branch of the decision tree one decision at a time. Domain-agnostic — works for software, writing, business, or life decisions. Use to stress-test plans, brainstorm rigorously, or when user says "grill me".
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.