agentic-engineering-framework
Structured workflows for requirements, design, coding, testing, and review
All Skills in This Repository (15)
Pure Emerald Level Indicatorsbp-component-design
Define component design principles for classes, interfaces, data models, concurrency, and error handling.
std-cpp
Standardize C++ coding practices for .cc, .cpp, and .h files.
std-go
Enforce Google Go style guidelines for formatting, imports, and error handling.
bp-skill-authoring
Guide authors in creating and refining Agent Skill SKILL.md metadata and structure.
self-refinement
Identify recurring error patterns from user corrections and consolidate them into persistent Rules and Skills.
troubleshooting
Diagnose root causes from logs and code context in pipelines and deployments.
bp-performance-optimization
Apply structured optimization rules to improve software performance across CPU, memory, I/O, and concurrency.
workflow-system-design
Guide step-by-step system design discussions and update spec.md after confirmations.
workflow-code-review
Automate multi-agent code review coordination and triage into a structured assessment.
workflow-code-generation
Generate and execute code change tasks with spec verification.
workflow-requirements-clarification
Extract codebase context and user needs into a structured requirements spec.
bp-distributed-systems
Apply distributed-systems best practices and SDLC checklists to guide robust design.
Frequently Asked Questions
FAQPage SchemaHow to install agentic-engineering-framework?▼
Run `npx skills add davidYichengWei/agentic-engineering-framework --all -g -y` in your terminal to install all skills globally.
What problem does this framework solve?▼
It stops coding agents from skipping requirement clarification, forgetting coding standards mid-session, and producing inconsistent output across conversations by enforcing structured workflows.
Which coding agents does it support?▼
It works with Claude Code, Codex CLI, CodeBuddy, Cursor, Windsurf, and any agent that supports the standard skill and command structure.
How does the self-refinement feature work?▼
When you correct the agent's mistake, it suggests saving that lesson as a persistent skill or rule, so the same error never repeats in future sessions.
Do I need to follow the full workflow every time?▼
No. Small bug fixes can go straight to code generation, and incidents can jump directly to troubleshooting. Process rigor scales with task risk.
Related Repositories in Software Engineering
View All in Software Engineering→openclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core