codeaholicguy/ai-devkit

Agent Communication lets an AI agent discover active AI coding agents, read their recent context, and send them messages or request information using the ai-devkit CLI. Use it when one agent needs to coordinate with another or hand off work.

Agent Management uses ai-devkit agent commands to list, start, inspect, assign work to, and stop AI agents. Use it when an agent needs to identify itself, manage other agents, or delegate tasks.

Agent Orchestration coordinates dependencies between multiple AI agents, polls their progress, unblocks waiting agents, relays outputs, resolves conflicts, and verifies completion. Use it for ongoing multi-agent supervision rather than one-off agent actions.

Brainstorm runs a compact diverge-to-converge loop that helps users generate, challenge, compare, and narrow ideas. Use it for ideation, evaluating options, naming, technical approaches, content angles, or strategic decisions.

Changelog updates the Unreleased section of CHANGELOG.md from commits after the latest release. Use it when asked to update changelog or release notes from recent git commits.

Dev Commit stages and commits only the files that belong to a requested change, avoiding unrelated user edits and generated artifacts. Use it when an agent needs to make an intentional, verified conventional commit or prepare a PR-ready checkpoint.

Dev Design runs the design review phase for configured AI docs features. Use it to validate architecture, review design docs, resolve trade-offs, or run dev-lifecycle phase 3.

Dev Implementation provides implementation-phase guidance for executing feature plans and checking implementation against design. Use it when implementing planned tasks, updating implementation docs, verifying code matches design, or running dev-lifecycle phases 5 and 7.

Dev Lifecycle coordinates phase-specific AI DevKit skills across requirements, design, planning, implementation, testing, and review. Use it to run the full software development lifecycle or choose the next phase during structured feature work.

Dev Lifecycle gives coding agents a repeatable engineering workflow that moves from requirements and design through planning, implementation, testing, and review. Use it to make Claude Code or Codex work like a senior engineer instead of jumping straight into code.

Dev PR publishes a ready feature branch for code review on GitHub, GitLab, or another Git host. Use it after the commit workflow to sync, push, and open or update a review request.

Dev Planning creates and reconciles feature task plans by converting requirements, design, and testing docs into ordered implementation tasks. Use it after requirements and design exist to update planning docs, mark task progress, and capture blockers or new tasks.

Dev Requirements guides the capture and review of requirements for AI-assisted development, including clarifying scope, initializing feature docs, and validating requirements before design. Use it when starting a new feature or reviewing existing requirements in the dev-lifecycle phases 1-2.

Dev Review runs final pre-push code review for AI-assisted development. Use it when you need holistic code review, design alignment checks, integration risk review, or dev-lifecycle phase 9 verification.

Dev Testing guides adding and validating feature test coverage for AI docs features, including unit and integration tests, running coverage, and closing gaps. Use it when the user wants to write tests, update testing docs, run coverage, or run dev-lifecycle phase 8.

Dev Worktree sets up or resumes isolated git worktrees for feature branches so an agent can work in a clean, repo-local workspace. Use it before starting, resuming, switching, or verifying feature work to keep branch state and dependencies consistent.

Document Code builds structured documentation for code entry points by analyzing dependencies and saving knowledge docs. Use it when asked to document, understand, or map a module, file, folder, function, or API.

Memory CLI stores verified, reusable project knowledge for AI coding agents and searches it before non-trivial work. Use it to persist conventions, fixes, and decisions while avoiding secrets and task progress.

Security Review finds vulnerabilities in code, skills, and prompts — including OWASP Top 10, prompt injection, business logic flaws, and insecure defaults — before they ship. Use it when reviewing PRs, auditing modules, reviewing AI skills/prompts, or preparing for release.

Simplify Implementation analyzes existing code to reduce complexity, improve maintainability, and enhance scalability. Use it when asked to simplify code, refactor for readability, clean up implementations, reduce technical debt, or make code easier to understand.

Structured Debugging guides evidence-first debugging before code changes by clarifying expected behavior, reproducing issues, identifying likely root causes, and agreeing on a fix plan with validation steps. Use when debugging bugs, regressions, incidents, failing tests, or running root cause analysis.

TDD enforces a red-green-refactor cycle: write a failing test before any production code. Use it when implementing new functionality, adding behavior, or fixing bugs.

Task Progress Tracking records development progress on a durable task: phase, progress, next step, blockers, and validation evidence. Use it to track dev-lifecycle and structured-debug progress with the ai-devkit task CLI.

Technical Writer reviews documentation as a novice would experience it, rating clarity, completeness, actionability, and structure, then suggests concrete fixes. Use it when asked to review docs, improve READMEs, audit API docs, or evaluate guides.

Verify enforces evidence-based completion claims by requiring fresh terminal output before an agent reports success. Use it when completing any task, fixing a bug, finishing a phase, or running tests, builds, or deployments.