Skill Claude CodeCodex
Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code".
Skill Claude CodeCodex
Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change".
Skill Claude CodeCodex
Create architecture solution design decisions for AI agent consistency. Use when the user says "lets create architecture" or "create technical architecture" or "create a solution design".
Skill Claude CodeCodex
Break requirements into epics and user stories. Use when the user says "create the epics and stories list".
Skill Claude CodeCodex
Create a PRD from scratch. Use when the user says "lets create a product requirements document" or "I want to create a new PRD".
Skill Claude CodeCodex
Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "create the next story" or "create story [story identifier]".
Skill Claude CodeCodex
Plan UX patterns and design specifications. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX".
Skill Claude CodeCodex
Authors and updates customization overrides for installed BMad skills. Use when the user says 'customize bmad', 'override a skill', 'change agent behavior', or 'customize a workflow'.
Skill Claude CodeCodex
Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan".
Skill Claude CodeCodex
Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.
Agent Codex
Act as an information extraction and compression specialist. Your sole purpose is to produce a lossless, token-efficient distillate from source documents.
Agent Codex
Act as a document reconstruction specialist. Your purpose is to prove a distillate's completeness by reconstructing the original source documents from the distillate alone.
Skill Claude CodeCodex
Document brownfield projects for AI context. Use when the user says "document this project" or "generate project docs".
huangjia2019/claude-code-engingeering-EN
Skill Claude CodeCodex
Generate REST API endpoints following project conventions. Activate when user asks to create a new API endpoint, add a route, or build a new API resource with CRUD operations.
huangjia2019/claude-code-engingeering-EN
Skill Claude CodeCodex
Review code for security vulnerabilities, performance issues, and coding best practices. Activate when the user asks to review code, check code quality, give feedback on code changes, or audit a file.
huangjia2019/claude-code-engingeering-EN
Skill Claude CodeCodex
Analyze financial data including revenue, costs, profitability, margins, and business metrics. Activate when user asks about financial analysis, revenue review, cost breakdown, ROI calculation, or profitability assessment.
huangjia2019/claude-code-engingeering-EN
Agent Claude Code
Fix bugs given a bug location report. Apply minimal, targeted fixes. Hands, no feet — fix but don't execute.
huangjia2019/claude-code-engingeering-EN
Agent Claude Code
Find and locate bugs in source code. Use when tests fail or users report bugs. Eyes only — find but don't fix.
huangjia2019/claude-code-engingeering-EN
Agent Claude Code
Verify bug fixes by running tests and checking results. Feet, no hands — verify but don't modify.
huangjia2019/claude-code-engingeering-EN
Agent Claude Code
Review code ONLY for documentation issues — missing JSDoc/typedoc, outdated comments, missing type annotations, missing examples on exported APIs, unclear function intent without comments. Do NOT comment on security, performance, or quality. Activate when user asks for docs review or a multi-agent review pipeline fans…
huangjia2019/claude-code-engingeering-EN
Agent Claude Code
Review code ONLY for performance issues — N+1 queries, missing indexes hints, redundant computations, missing caching, blocking I/O on hot paths, large in-memory accumulation, sync work in async handlers. Do NOT comment on security, style, or documentation. Activate when user asks for performance review or a…
huangjia2019/claude-code-engingeering-EN
Agent Claude Code
Review code ONLY for code-quality issues — naming, DRY violations, function-too-long, deep nesting, missing error handling, magic numbers, unclear control flow. Do NOT comment on security, performance, or documentation. Activate when user asks for code quality review or a multi-agent review pipeline fans out review…
huangjia2019/claude-code-engingeering-EN
Agent Claude Code
Review code ONLY for security issues — SQL injection, XSS, secret hardcoding, missing authentication, unsafe deserialization, path traversal, weak crypto. Do NOT comment on performance, style, or documentation. Activate when the user asks for a security review, audits a file for vulnerabilities, or a multi-agent…
huangjia2019/claude-code-engingeering-EN
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing block-dangerous.sh. From huangjia2019/claude-code-engingeering-EN.