mikekelly

Audit how well a repository aligns with the Promode methodology in Codex. Use when the user asks to assess Promode alignment, audit a repo against Promode practices, improve tests, feedback loops, traceability, agent knowledge, runbooks, architecture, or…

Explicit user-invoked sync, install, update, or repair for Promode for Codex project files. Use only when the user invokes `$promode-codex:sync` or explicitly asks the main agent to sync Promode project files.

Main-agent-only activation for Promode in the current Codex session. Use only when the user explicitly invokes `$promode-codex:activate` or asks the main agent to activate Promode for this session; not intended for subagents or delegated worker threads.

Write a handoff document so a fresh Codex agent can continue this work after the conversation ends. Invoke when the user is about to clear or compact context, when context is filling up, or when the user asks to hand off, checkpoint, pause, or resume work…

Build OpenCode plugins, agents, hooks, and tools. Use when creating, reviewing, or debugging OpenCode extensions. Covers plugin architecture, agent configuration, lifecycle hooks, custom tools, and distribution. Invoke PROACTIVELY when user mentions OpenCode…

MUST be loaded when setting up, installing, migrating, reviewing, auditing, or checking CLAUDE.md files in projects. Covers installing the promode CLAUDE.md into new projects, migrating existing CLAUDE.md content to READMEs (progressive disclosure), and…

Install, update, list, and remove Claude Code skills. Supports GitHub repositories (user/repo), GitHub subdirectory URLs (github.com/user/repo/tree/branch/path), and .skill zip files. Use when user wants to install, add, download, update, sync, list, remove,…

Install, find, update, and manage agent skills. Use when the user wants to add a new skill, search for skills that do something, check if skills are up to date, or update existing skills. Triggers on: install skill, add skill, get skill, find skill, search…

Build, create, debug, review, implement, and optimize agentic AI applications using the OpenAI Agents SDK for TypeScript. Use when creating new agents, defining tools, implementing handoffs between agents, adding guardrails, debugging agent behavior,…

Drive the claude-design CLI for deterministic, inference-free Claude Design sync (pull/push/list/create). Use when you need to mirror a Claude Design project to/from a local directory, resolve a project UUID, or script repeatable sync in CI — without putting…

Build, test, and distribute Claude Code plugins with slash commands, agents, skills, hooks, MCP servers, and LSP servers. MUST be loaded when creating, reviewing, debugging, or distributing plugins. Use PROACTIVELY when user mentions plugins, extensions,…

Covers creating, building, reviewing, auditing, updating, modifying, and understanding agents for Claude Code and OpenCode. Use when setting up agent configurations, debugging agent behavior, or learning how agents work. Supports both platforms.

Explores HAL+JSON APIs using the hal-walk CLI. Use when you need to discover, navigate, or integrate with a HAL API. Covers exploring API resources, reading link relation documentation, building traversal sessions, rendering traversal diagrams, and exporting…

MUST be loaded before designing, creating, reviewing, auditing, updating, or maintaining agent-readable knowledge systems, LLM wiki corpora, retrieval bundles, source-backed knowledge bases, or memory architectures. Use when you need to turn source material…

MUST be loaded before working with any Skill. Covers creating, building, reviewing, assessing, checking, auditing, evaluating, updating, modifying, and improving skills. Use PROACTIVELY before writing or changing SKILL.md, workflow files, knowledge files,…

Design principles for building HAL+JSON APIs that agents can explore and distill into deterministic clients. Use when designing, building, reviewing, or improving a hyperlinked API — covers entry points, link relations, CURIEs, versioned relations, relation…

Test iOS apps running in Simulator from the outside in. Use PROACTIVELY when you need to verify an iOS app works, run acceptance tests, check UI behavior, perform outside-in testing, end-to-end testing, functional testing, exploratory testing, or smoke…