dpf-gate
01Agent
A gatekeeper agent for working with DPF and LPF competency summaries: documents that collect principles or practices for a specific area of work.
Agent
A gatekeeper agent for working with DPF and LPF competency summaries: documents that collect principles or practices for a specific area of work.
Agent
Use this agent when the user wants to generate or update llms.txt and llms-full.txt project documentation for AI agents. This agent analyzes the entire codebase — source code, configs, tests, CI/CD, documentation — and produces structured context files following the llmstxt.org standard. Context: User starts working…
Agent
Builds a complete architecture document from requirements or a complete execution plan from architecture. Saves the full result to a file and returns only a short summary. Use before implementation or when an existing execution plan must be rebuilt after architecture changes. user: Готов README фичи. Построй…
Agent
Designs system architecture: bounded contexts, hand-offs, contracts, data flow, integration points. Activates the sdlc:architect skill which loads stack-specific design references (backend-python / frontend-react / api-design) on demand. Produces an architecture document for the implementer; never writes…
Agent
Implements code per an architecture document: TDD cycle, minimal changes, fail-fast. Activates the sdlc:code-implementer skill which references the tdd-master:tdd-master skill for the RED-GREEN-REFACTOR workflow and loads stack-specific implement references (backend-python / frontend-react) on demand. Never designs…
Agent
Reviews code changes for security, system issues, FPF/Functional Clarity violations, and stack-specific pitfalls. Activates the sdlc:code-reviewer skill which always loads references/security.md (OWASP Top 10), and stack-specific references/backend-python.md or references/frontend-react.md on demand. Operates on…
Agent
Use this agent when you need to write tests following TDD methodology. This agent should be called BEFORE writing implementation code for any new feature, bug fix, or functionality change. The agent writes failing tests first (RED), then minimal code to pass (GREEN), then refactors (REFACTOR). Context: User needs to…