Download

Skill UI

Browse and discover 19804+ curated skills

All Development Artificial Intelligence Design & Creative Product & Business Data Science Marketing Soft Skills Productivity Engineering Languages

Search Sub-agent , found 68 results

Default Newest Most Downloaded

Codebase Automation Recommendation Engine

claude-automation-recommender

anthropics/claude-plugins-official

This advanced skill analyzes an existing codebase to identify architectural patterns, dependencies, and technical stacks. It recommends tailored Claude Code automations—including Hooks, Subagents, Skills, Plugins, and MCP Servers—to optimize development workflows, improve code consistency, and enhance overall project scalability. Use this when setting up a new project or looking to refine existing Claude Code configurations.

Cursor Subagent Creator

cursor-subagent-creator

tech-leads-club/agent-skills

Guides creation of Cursor-specific subagents with isolated contexts, structured prompts, and frontmatter so multi-step workflows, verifiers, or specialists follow Cursor’s directories and delegation rules.

Daily Tech News Report

daily-news-report

sickn33/antigravity-awesome-skills

Daily News Report orchestrates agents to scrape a curated URL list, filter high-quality technical findings, and compile them into daily Markdown summaries while monitoring batch progress and leveraging smart caching for reliability.

Workflow Skill Design

designing-workflow-skills

trailofbits/skills

Guides Claude Code skill authors through designing and structuring workflow-based skills with numbered phases, decision routing, subagent delegation, and progressive disclosure so multi-step automations remain predictable and auditable.

Iterative Retrieval Pattern

iterative-retrieval

affaan-m/everything-claude-code

Guides multi-agent workflows through an iterative context retrieval loop—dispatching broad queries, evaluating relevance, refining criteria, and looping up to three times so sub-agents gather exactly the files they need without overwhelming limits.

Nx Ci Monitor

tech-leads-club/agent-skills

Monitors Nx Cloud CI pipelines by running the ci-watcher subagent, polling execution status, and applying self-healing fixes or rerun requests while honoring user overrides and Nx Cloud connection requirements.

Agent Task Conductor

numman-ali/n-skills

Orchestrates multiple agents for complex workflows, decomposing feature, review, refactor, test, or documentation requests into parallel subtasks tracked via cc-mirror and TodoWrite for live visibility.

Parallel Subagent Execution

parallel-execution

CloudAI-X/claude-workflow-v2

Guides orchestrating multiple Task tool subagents with run_in_background for concurrent work, covering when to trigger parallelism, how to craft prompts, launch in one message, synchronize results, and integrate TodoWrite status updates.

Code Review Workflow Guide

requesting-code-review

sickn33/antigravity-awesome-skills

This workflow guides developers through the systematic process of requesting and acting upon code reviews. It emphasizes the core principle of reviewing early and often, providing structured inputs (commits, requirements, implemented features) via a subagent to catch technical issues, ensure compliance with requirements, and maintain high code quality before merging.

Semgrep Security Scan

trailofbits/skills

Runs Semgrep static analysis with auto language detection, parallel Task subagents, Semgrep Pro checks, and configurable “run all” or “important only” modes to audit codebases for vulnerabilities and bug patterns.

Subagent Driven Development

subagent-driven-development

sickn33/antigravity-awesome-skills

A workflow for executing implementation plans by spinning up a fresh subagent for each task and enforcing consecutive spec compliance and code quality reviews so the session stays focused and high-quality without manual context switches.

Requesting Code Review

requesting-code-review

obra/superpowers

Explains when to call the code-reviewer subagent, how to collect SHAs, fill the template, and act on its feedback so every task, feature, or merge meets quality expectations.

12 3 4 5 6 Next

Language