273 boosters for "task" — open source, verified from GitHub, ready to install
A skill that generates detailed, bite-sized implementation plans for multi-step tasks before coding begins, designed for engineers unfamiliar with the codebase. Useful for teams wanting structured planning and onboarding guidance.
Enables concurrent investigation of multiple independent tasks by dispatching separate agents to each problem domain, saving time on parallel debugging and testing workflows.
This booster dispatches a code-reviewer subagent to catch issues before merging, promoting early and frequent code review practices. It benefits developers using claude_code who want to maintain code quality throughout their workflow.
A skill booster that structures implementation execution by dispatching independent subagents for each task with two-stage review (spec compliance, then code quality), designed for developers managing multi-task implementation plans in a single session.
The xlsx skill enables Claude to work with spreadsheet files—opening, editing, creating, cleaning, and converting .xlsx, .xlsm, .csv, and .tsv files. It's essential for users who need programmatic spreadsheet manipulation without leaving their AI assistant.
The docx skill enables AI assistants to create, read, edit, and manipulate Word documents with professional formatting, tables of contents, images, and tracked changes. It's useful for developers and users who need to programmatically generate or process .docx files as part of their workflows.
doc-coauthoring guides users through a structured three-stage workflow (context gathering, refinement, and reader testing) for collaboratively creating technical documentation, proposals, and specs. It benefits technical writers, engineers, and product managers who need to efficiently co-author structured content.
Official GitHub toolkit for Spec-Driven Development — bootstraps projects with AI-ready templates and native support for 25+ AI agents (Claude, Cursor, Windsurf, Copilot, Gemini). The Specify CLI sets up PRD/spec workflows and generates per-agent command directories.
AGENTS.md Version 2 enables AI agents to autonomously interact with websites using browser automation, allowing developers to automate complex web tasks programmatically. It's ideal for developers building AI-powered automation tools and agents that need reliable web interaction capabilities.
A system prompt that enables AI agents to automate browser tasks, navigate websites, and extract information by operating in an iterative loop. Developers and AI automation engineers use this to enhance AI capabilities for web automation across multiple platforms.
Get Shit Done (GSD) is a meta-prompting and context engineering system that helps developers coordinate AI-assisted workflows across multiple platforms while preventing quality degradation from context window bloat. Developers building with Claude, OpenCode, Gemini, and Codex benefit from its structured Plan→Execute→Verify→Complete pipeline.
Converts project specifications into structured, realistic task lists while learning from previous projects to avoid scope creep. Ideal for product managers, tech leads, and development teams who need disciplined project planning.
Heuristic scoring (no AI key configured).
Upstash QStash expert booster enables developers to build serverless message queues, scheduled jobs, and reliable HTTP-based task delivery without infrastructure management. Ideal for AI coding assistants helping teams implement async processing, cron jobs, and webhook systems.
<a href="https://github.com/VoltAgent/voltagent"> <img width="1500" height="500" alt="Group 32" src="https://github.com/user-attachments/assets/55b97c47-8506-4be0-b18f-f5384d063cbb" /> <div align="center">
This booster integrates Figma's MCP server into Claude Code to automatically fetch design context, screenshots, and variables, then translate Figma designs into production code. Developers working on design-to-code workflows benefit significantly from automated design asset retrieval and code generation.
Converts Notion product specs and PRDs into structured implementation plans, tasks, and progress tracking within Notion. Ideal for product managers and engineers who need to translate specifications into actionable work items.
Use this skill when the quality of the work depends on art direction, hierarchy, restraint, imagery, and motion rather than component count. Goal: ship interfaces that feel deliberate, premium, and current. Default toward award-level composition: one big idea, strong imagery, sparse copy, rigorous s
Automates real browser interactions from the terminal using Playwright CLI for tasks like navigation, form filling, and data extraction. Useful for developers and AI assistants building UI automation workflows without writing test frameworks.
Provides language-specific security best-practice reviews and improvement suggestions for Python, JavaScript/TypeScript, and Go code. Developers building secure applications benefit from automated security guidance tailored to their framework and language.
This skill enables users to generate and edit images directly within Claude Code using the OpenAI Image API, supporting use cases from product mockups to concept art. Developers and designers benefit by automating image creation workflows without leaving their coding environment.
This booster equips AI coding assistants with specialized guidance for reading, creating, and editing Word documents programmatically while maintaining formatting and layout fidelity. Developers working with `.docx` files—especially those requiring professional formatting, tables, or visual validation—will find this booster invaluable.
A PDF skill that guides AI assistants in reading, creating, and validating PDF files using Python tools like reportlab, pdfplumber, and Poppler rendering. Developers working with PDF generation, extraction, and layout validation will find this particularly useful.
Use this skill to create or update full-page screens in Figma by reusing the published design system — components, variables, and styles — rather than drawing primitives with hardcoded values. The key insight: the Figma file likely has a published design system with components, color/spacing variabl
