de orchestkit150
Deep pull-request code review using parallel specialized agents (quality, security, tests, architecture, performance) and synthesized review reports for approve
Performs comprehensive PR reviews by launching 6–7 specialized agents in parallel (code quality, security, test generation, frontend/backend performance, architecture). It gathers PR metadata, diffs, CI status and changed files, runs domain-aware agents, and synthesizes findings into a structured review with conventional comments (praise/issue/suggestion/nitpick) and an approve/request-changes verdict.
Use this for reviewing pull requests before merge, security audits, performance-sensitive changes, or when you need an automated, multi-perspective review that produces actionable comments and a final recommendation. Also useful for engineering teams wanting consistent, auditable review reports.
references/ and rules/ for prompts, templates, and validation commands.Designed for Claude Code-style orchestration and agent toolsets (parallel agent launches, AskUserQuestion, Bash, gh CLI). Compatible with agents that support task creation, tool calls, and structured JSON outputs.
Cette compétence n'a pas encore été examinée par notre pipeline d'audit automatisé.
Cross-Project Analytics
Query local, privacy-safe cross-project analytics to report on agent, skill, hook, and team performance; replay sessions and estimate token costs.
Task Dependency Patterns
Patterns and workflows for creating, sequencing, and managing task dependencies using TaskCreate/TaskUpdate/TaskGet/TaskList tools to coordinate multi-step impl
Write PRD (Product Requirements Document)
Generate an 8-section Product Requirements Document with user stories, INVEST-formatted acceptance criteria, and go/no-go criteria to turn product vision into e
