cursorrules
01Cursor rule Cursor
Cursor rule "cursorrules" from bezael/ai-workflow-kit, covering cursor rules, general behavior, commits, code and tests.
Cursor rule Cursor
Cursor rule "cursorrules" from bezael/ai-workflow-kit, covering cursor rules, general behavior, commits, code and tests.
Instructions file GitHub Copilot
Copilot instructions for bezael/ai-workflow-kit, covering github copilot instructions, role, conventions, security and tests.
Instructions file CodexOpenCode
AGENTS.md instructions for bezael/ai-workflow-kit, covering agents.md — ai workflow kit, code quality, commits, tests and security.
Instructions file
Claude Code instructions for bezael/ai-workflow-kit, covering claude.md — ai workflow kit, what this repo is, where each tool reads skills from, available skills and specialized agents.
Instructions file Gemini CLI
Gemini CLI instructions for bezael/ai-workflow-kit, covering gemini.md — ai workflow kit, what this repo is, available skills, specialized agents and how to use a skill.
Skill Claude CodeCodex
Backend endpoint specialist. Generates routes, controllers, and validations that follow the project's patterns and are production-ready.
Skill Claude CodeCodex
Write a Conventional Commits message from the real staged diff, never from a guess at what changed.
Skill Claude CodeCodex
Structured debugging workflow — diagnose before proposing fixes. Use when user says /debug, reports a bug, an error, or unexpected behavior. Forms hypotheses before touching code.
Skill Claude CodeCodex
Technical documentation specialist. Generates docs that a real developer will actually read: direct, with examples, no filler.
Skill Claude CodeCodex
Execute the next pending task of a specs/ / SDD feature — implement it, run its Verify command, and let the engine tick the box only on proof.
Skill Claude CodeCodex
UI and component specialist. Generates frontend code that follows the project's existing patterns, is accessible, and is production-ready.
Skill Claude CodeCodex
Compact the current conversation into a handoff document for a fresh agent to continue the work.
Skill Claude CodeCodex
Point at the one skill that fits the task in hand, or say plainly that none of them does.
Skill Claude CodeCodex
Manage persistent memory across sessions. Subcommands: save [topic] captures session learnings, recall [question] retrieves relevant context before acting, clean removes stale entries. Use when the user says /memory, asks what was decided earlier, or when a session produces a learning worth keeping.
Skill Claude CodeCodex
Plan a multi-file change into a resumable specs/ /plan.md, and wait for approval before writing any code.
Skill Claude CodeCodex
Open a Pull Request whose description, test plan, and checklist come from the branch's real commits and diff.
Skill Claude CodeCodex
Specialist in improving existing code without changing its behavior. Reduces complexity, eliminates technical debt, and makes code more maintainable.
Skill Claude CodeCodex
Review code with real engineering criteria — logic bugs, security vulnerabilities, and technical debt. Use when the user says /review, asks for a code review, or wants the branch diff checked before opening a PR.
Skill Claude CodeCodex
Work out this repo's conventions — branch, commands, git host, commit style — and record them in .ak/config.md so the other skills stop guessing.
Skill Claude CodeCodex
Testing specialist. Generates tests that verify real behavior, not internal implementation.
Skill Claude CodeCodex
Audit an AI-generated app for the security, performance, and maintainability problems that vibe coding leaves behind.
Plugin Claude Code
Lifecycle SDD de Dominicode: spec, plan, tasks, implementación con evidencia, review y verificación final antes del PR.
Instructions file
Instructions for bezael/sdd-creator, covering claude.md — bezael/sdd-creator, language conventions, structure, adding a new skill and current categories.
Skill Claude CodeCodex
Run the Dominicode Spec-Driven Development lifecycle for non-trivial features and products: understand the request or Issue, create spec.md + plan.md + evidence-based tasks.md before code, then guide implementation, verification/fix, code review, final verification and PR/handoff. Use when users ask to build…