otrebu
@otrebu
Public Skills
gemini-research
by otrebu
Web research via Gemini CLI with Google Search grounding. Generates markdown report. Claude MUST append analysis section after. Use for real-time data: news, docs, code examples, fact verification.
parallel-search
by otrebu
Comprehensive web research via Parallel Search API. Use when user requests parallel search for deep multi-source research, technical analysis, learning new topics, current events, or comparative studies. Returns LLM-ready ranked URLs with extended excerpts (up to 30K chars). Single API call handles multiple query angles with automatic deduplication.
gh-code-search
by otrebu
Search GitHub for real-world code examples and implementation patterns. Use when user wants to find code examples on GitHub, search GitHub repositories, discover how others implement features, learn library usage patterns, or research architectural approaches. Fetches top results with smart ranking (stars, recency, language), extracts factual data (imports, syntax patterns, metrics), and returns clean markdown for analysis and pattern identification.
readwise-api
by otrebu
Fetch and analyze Readwise reading activity for any date range. Use when user asks about articles saved, highlights created, or most-highlighted content for today, yesterday, last week, last month, or custom date ranges (e.g., "show my Readwise activity from Jan 1-7"). Requires READWISE_API_TOKEN env var. Connects to Readwise Highlights API (v2) and Reader API (v3).
timestamp
by otrebu
Generate deterministic timestamps in YYYYMMDDHHMMSS format using bash. Use when you need timestamps for filenames, logging, or any situation requiring consistent timestamp formatting without LLM generation.
analyze-size
by otrebu
Analyze codebase size and language distribution using cloc. Use when user wants to understand codebase scale, primary languages, code composition, or assess project complexity. Provides total LOC, size category, language breakdown percentages, and key insights.
brainwriting
by otrebu
Facilitate structured brainstorming using parallel sub-agents to explore idea spaces. Use for IDEATION/CONCEPTUAL WORK ONLY, NOT for implementation planning or task breakdown. Use when user wants to brainstorm, explore ideas, generate concepts, develop vision, or discover creative directions. Transforms vague ideas into practical, tangible expressions through 5 rounds of parallel agent analysis and refinement.
scratchpad-fetch
by otrebu
Download and aggregate web pages/docs into timestamped scratchpad files. Use when user asks to "concatenate all these resources", "get all these links", "checkout all these resources", or wants to gather fresh context from documentation URLs. All URLs from one prompt go into single file at docs/scratchpad/<timestamp>.md.
web-to-markdown
by otrebu
Batch-process web pages via headless Playwright browser, extract HTML, convert to markdown using Turndown, and save to timestamped scratchpad file. Use when user asks to "capture these pages as markdown", "save web content", "fetch and convert webpages", or needs clean markdown from HTML. All URLs from one prompt → single file at docs/web-captures/<timestamp>.md.
dev-work-summary
by otrebu
Scan ~/dev recursively for git repos and report today's work with commits, branches, stats, and detailed change analysis. Use when user asks "what did I work on", "show my work", "daily summary", "what repos did I touch".
plugin-creator
by otrebu
Create Claude Code plugins with proper structure. Use when user requests "create a plugin" or needs to scaffold a new plugin with metadata, directories, and marketplace registration.
git-commit
by otrebu
Create conventional commits from staged/unstaged changes. Use when user asks to commit, create commits, commit changes, commit all, make commits, separate commits, commit everything, stage and commit, commit these changes, save and push, commit this work, or requests push after committing. Handles single or multiple commits, staging, message generation from diffs, and push operations.
finish-feature
by otrebu
Complete feature work and merge back to main branch. Use when user wants to finish a feature, close a feature, or merge feature branch. Switches to main, pulls latest changes, merges feature branch, and pushes to remote.
typescript-coding
by otrebu
Expert TypeScript/JavaScript development guidance. Use when planning or writing TypeScript/JavaScript code, setting up TS/JS projects, configuring build tools (pnpm, Vite, TypeScript), implementing tests (Vitest), adding logging (pino for services, chalk/console for CLIs), working with React/Tailwind/Xstate, or following FP patterns. Covers stack decisions, tooling setup, testing strategies, and logging patterns for both services and CLI tools.
prompting
by otrebu
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.
skill-creator
by otrebu
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
claude-permissions
by otrebu
Configure, manage, update and review Claude Code permissions, sandboxing, and tool access. Use when user wants to set up permissions, configure sandboxing, update allowed tools, manage settings.json permissions, or review permissions in skills or commands or agents or settings.json. When user writes a new skill, command, agent, or updates settings.json, they should use this skill to manage permissions.
start-feature
by otrebu
Create or switch to feature branches with proper naming conventions. Use when user wants to start working on a new feature, start a feature. Generates feature/branch-name patterns from descriptions, checks existence, and creates/switches accordingly.
code-review
by otrebu
Expert code review specialist. Reviews for quality and intent alignment. Use immediately after writing or modifying code, or when user requests code review. Handles both uncommitted changes and targeted file reviews.
fix-eslint
by otrebu
Automatically fix ESLint errors by modifying code to comply with linting rules. For small codebases (≤20 errors), fixes directly. For larger codebases (>20 errors), spawns parallel agents per directory for efficient processing. Never disables rules or adds ignore comments.