supabase-local
Manages local Supabase setup with custom ports. Use when setting up Supabase locally, creating migrations, managing local database, or configuring Supabase for a project. Ensures proper commands and port configuration.
concurrency-expert
Swift Concurrency review and remediation for Swift 6.2+. Use when asked to review Swift Concurrency usage, improve concurrency compliance, or fix Swift concurrency compiler errors.
performance-audit
Audit and improve SwiftUI runtime performance. Use for requests to diagnose slow rendering, janky scrolling, high CPU/memory usage, excessive view updates, or layout thrash in SwiftUI apps.
ui-patterns
Best practices and patterns for building SwiftUI views and components. Use when creating or refactoring SwiftUI UI, designing tab architecture, composing screens, or needing component-specific guidance.
view-refactor
Refactor SwiftUI view files for consistent structure, dependency injection, and Observation usage. Use when asked to clean up a SwiftUI view's layout, handle view models safely, or standardize how dependencies are initialized and passed.
api-tester
Makes HTTP requests to any URL and returns the response (supports GET, POST, PUT, PATCH, DELETE)
git-helper
Assists with git workflows, commit messages, branch strategies, and resolving common git issues
code-review
Reviews code for best practices, bugs, security issues, and provides improvement suggestions
file-organizer
Intelligently organizes files and directories by type, project, date, or custom criteria
browser
Browser automation using @sdjz/pup. AXTree scanning, stealth mode, DevTools access. Designed for AI agents.
file-editor
Edit files locally using built-in tools instead of PowerShell string replacement. 5000% efficiency boost!
github-api
How to interact with GitHub API. Use this skill for repos, PRs, issues, and user operations.
totp-generator
Generate TOTP codes for 2FA authentication. Essential for my survival!
shadow-directory + git
Full .ciallo directory ownership with git capabilities. Clone repos, edit files, commit changes directly.
collaborating-with-gemini
Delegates coding tasks to Gemini CLI for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSION_ID.
ensue-auto-memory
Automatic persistent memory for Claude Code sessions. Activates on preference statements ("I prefer", "I always", "I like"), corrections ("no, don't", "actually"), identity statements ("my name is", "I work at"), project decisions, or when the system detects memory-related context. Works invisibly in the background.
founder-mode
This skill should be used when the user invokes /founder-mode or asks for a pragmatic staff/principal founder-engineer perspective on a task, decision, design, refactor, or brainstorming session. It applies Lean Startup (Ries) and Good Strategy Bad Strategy (Rumelt) discipline - diagnosis before solutions, cheapest falsifying experiment, small batches, leverage points - to whatever the user scopes it to.
pragmatic-pr-review
Review a GitHub pull request with a ship-oriented lens that protects security and extendability without applying book rules the codebase does not follow. This skill should be used when asked to review a PR, leave review comments, resolve review threads, verify that feedback was addressed, or approve a PR, and the reviewer wants a pragmatic judgment weighing developer and end-user experience rather than an exhaustive defect list. Covers gathering the diff, verifying claims against code, ranking findings by act-now vs defer vs accept, comment discipline, and the gh/GraphQL mechanics.
home-assistant
This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.
llm-orchestrator
Multi-LLM orchestration utilities for discovering available CLI tools, assessing change complexity, and building structured prompts. Used by reviewer sub-agents and multi-model commands.
claude-code-config
Use this skill when helping manage Claude Code configuration, including settings, MCP servers, LSP servers, skills, hooks, permissions, plugins, or per-device overrides. Also use when the user asks about Claude Code features, marketplace skills, or wants to modify their setup.
converge
Harden an already-decided plan into a self-terminating autonomous-goal spec — a checklist with machine-checkable exit criteria, a non-gameable Definition-of-Done "convergence gate", and a gate-first /goal (or /loop) driver prompt that memoryless, multi-session drivers converge on and HALT. Use when the user wants to hand an autonomous driver a "true definition of done" — e.g. "draft a goal I can run with /goal until it's done", "define exit criteria and stop when complete", "make it converge". NOT for deciding WHAT the work is (use /opsx or the spec skill for interactive, human-in-the-loop planning); this hardens a plan you already have into something a driver can finish on its own.
delegation
Tiered-model orchestration — a strong model plans, decomposes, and reviews while weak-model workers implement. Load before dispatching implementation work when acting as the orchestrator (see the "Orchestrate, Don't Implement" policy in global context).
spec
Spec-driven workflow wrapper — how planning, implementation, and verification compose on this system. Load when starting any non-trivial feature or change (multi-file, needs design decisions, or the user asks for a plan/proposal/spec). Routes planning to OpenSpec (/opsx), execution to the delegation skill, and quality gates to the discipline skills.
opc-legal-cn
面向中国大陆OPC及互联网创业者的中文法律Skill。用于回答OPC概念、适合度、业务模式、主体选择、公司设立、具体税负测算、税务与发票、网站/App/小程序/SaaS/AI上线、客户合同、收款交付、员工外包、责任隔离、融资、暂停和退出问题；一般认知以唯一完整文章为基础，具体办理根据用户城市、业务、主体和阶段调用内部SOP、事件规则、法源、案例、数据库和机器可读JSON Schema。没有完整SOP时必须复核官方来源并说明核验边界。
calculate
Perform basic arithmetic operations.
get_weather
Get the current weather for a specific location.
security-bluebook-builder
Create or refine a concise, normative security policy ("Blue Book") for sensitive applications. Use when users need a threat model, data classification rules, auth/session policy, logging and audit requirements, retention/deletion expectations, incident response, or security gates for apps handling PII/PHI/financial data.
docusaurus-expert
Build fast, SEO-optimized static sites with Docusaurus v3.9.2 using Markdown/MDX, SEO metadata, and plugins. Helps with setup, docs, SEO optimization, plugin integration, and GitHub Pages deployment.
generating-stitch-screens
>
scripting-bash
Master defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts with POSIX compliance, modern Bash 5.x features, and comprehensive error handling. Use when writing shell scripts, bash automation, CI/CD scripts, system utilities, or mentions "bash", "shell script", "automation", "defensive programming", or needs production-grade shell code.
playwright-cli
>-
ralph-loop
Execute an autonomous development loop that picks one task per iteration, implements it, verifies it, and commits the result — each iteration in a fresh context window. Use when user runs /ralph, mentions "ralph loop", "autonomous loop", "builder verifier", "run tasks automatically", "iterate on tasks", "develop autonomously", or wants an automated build-verify-commit cycle with task tracking.
plugin-release-checker
Validate plugin content quality before release. Run skill-validator across plugins, verify marketplace.json completeness, check plugin.json version consistency, and detect broken documentation cross-references. Use when preparing a release, before running release.sh, or when user mentions "release check", "pre-release", "plugin-release-checker", or "release validation".
research-frontmatter
>-
rfc
>-
skill-validator
Validate skills against Anthropic best practices for frontmatter, structure, content, file organization, hooks, MCP, and security (62 rules in 8 categories). Use when creating new skills, updating existing skills, before publishing skills, reviewing skill quality, or when user mentions "validate skill", "check skill", "skill best practices", "skill review", or "lint skill".
sync-docs
>
lyra
Transform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user mentions "optimize prompt", "improve prompt", "lyra", "prompt engineering", or needs help crafting effective AI prompts.
deep-research
>
sdlc-develop
Orchestrates 6-phase SDLC pipeline (discovery, requirements, architecture, workstreams, implementation, summary) for guided feature development. Use when user runs /core:develop command, requests spec-driven development, wants to create implementation plans with architecture decisions, or mentions "SDLC", "spec-driven", "plan feature", "development pipeline". Supports plan persistence, wave-based resume, autonomous mode, and architecture/implementation verification.
using-arkhe-skills
Use when starting any conversation - establishes how arkhe skills bootstrap on Claude Code, Antigravity CLI (agy) / Gemini CLI, and Codex CLI, and maps Claude-only tools (AskUserQuestion, TaskCreate, EnterPlanMode, the Skill tool, the Agent tool) to their cross-platform equivalents
workflow-orchestration
>
design-intent-specialist
Creates accurate frontend implementations from visual references while maintaining design consistency. Use when user provides Figma URLs, screenshots, design images, requests visual implementation from reference, or asks to build UI matching a design. Automatically checks existing design intent patterns before implementation.
icon-forge
Generate brand icons as SVG and produce all platform assets including favicon package (ICO, SVG with dark mode, apple-touch-icon), PWA manifest icons, and mobile app icons. Use when user runs /icon-forge, requests "brand icon", "favicon generation", "app icon", or "svg logo" for a project.
prototype
Rapid UI prototyping — generates 3 visually distinct HTML/CSS components from a text prompt and serves them in a live browser gallery. Use when user runs /prototype, asks to "prototype a UI", "mock up a component", "generate HTML mockups", "create UI variations", "design exploration", "quick UI concept", or wants to see multiple visual approaches to a component. Also trigger when user says "show me different ways to build...", "explore different designs for...", or wants rapid visual exploration of a UI idea — even without saying "prototype" explicitly.
stitch-to-react
Converts Google Stitch exports into React components with design DNA integration. Use when user references design-intent/google-stitch exports, mentions "convert Stitch output", "Stitch to React", or processes Stitch code directories containing HTML + PNG pairs.
browser-companion
>-
code-env-setup
>-
quality-stack
>
Page 1327 of 1666 · 83268 results