subagent-driven-development
Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
446 skills found
Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.
Token-efficient codebase analysis skill for call graphs, semantic search, impact analysis, and data flow. Saves ~95% tokens vs. raw reads.
Scaffold custom React Flow node components with TypeScript, Zustand integration, and standard handles for visual workflow editors.
Maintain test suite health by automatically detecting orphaned tests, missing coverage, and implementation-coupled anti-patterns.
A comprehensive configuration toolkit for Claude Code featuring battle-tested agents, skills, hooks, and automation workflows for software development.
PostgreSQL schema and migration expert for Diddit. Manages idempotent SQL files, tables, indexes, and constraints following strict camelCase conventions and transactional safety.
Create well-structured user stories with clear acceptance criteria using the standard As a/I want/So that framework for agile team alignment.
Structured task planning framework for AI agents to break down complex features, refactors, and bugs into actionable, verifiable steps.
Fixes CJS/ESM module compatibility issues in Nango integrations after zero-yaml migration, including path adjustments, ESM wrappers, and restoring original implementations.
Meta-skill for structured, multi-depth codebase exploration including architectural analysis, fast structural overviews, and deep-dive documentation workflows.
Reference for all MCP tools exposed by the CCOS server, enabling capability discovery, session management, and governed RTFS execution for autonomous agent workflows.
Orchestrate an automated PR review-fix loop. Dispatches subagents to analyze code, CI status, and comments, then applies iterative fixes until the PR reaches a passing state.