mikekelly

Audit how well a repository's codebase and practices align with the promode methodology, then produce a prioritised, actionable improvement plan. Fans out parallel assessors (one per dimension) and synthesises their findings. Use when the user wants to assess promode alignment/fit, audit a repo against the methodology, or get a plan to bring a codebase in line with promode. Also flags stale per-project install leftovers — promode ships its own SessionStart hook, so nothing should be copied into a project.

Walk the knowledge graph (rooted at CLAUDE.md) and ensure every crucial design constraint — invariants, prohibitions, required patterns, load-bearing decisions — is guaranteed-loaded into the nearest loaded CLAUDE.md orientation that governs the affected area: stated inline, or @import-transcluded when it must stay in its own file, with a link to its full rationale for expanded discovery. Use when constraints are buried in ADRs, knowledge docs, code comments, or tribal knowledge; when an agent violated a rule it had no way to know; or when asked to surface, hoist, lift, strengthen, or reinforce design constraints, or make them discoverable to agents.

Write a handoff document so a fresh agent can continue this work after the conversation ends. Invoke when the user is about to /clear or /compact, when context is filling up, or when the user asks to hand off, checkpoint, or pause work for a later session. Argument (optional): what the next session will focus on.

Persist a multi-task plan as durable per-task markdown docs (the canonical brief + state + outcome), so the plan/execution trace survives the prompt, hands off cleanly to fresh sessions, and feeds durable history. Invoke when planning multi-task work, when delegating a planned task to a subagent, or when a subagent records its outcome. The Kanban board tracks flow; these docs hold the detail.

Put the bulk of acceptance coverage below the UI through a fast, deterministic headless client driving an operator seam, and reserve a surgical UI state-graph tier for defects that only manifest through the real GUI. Use when designing test/QA or acceptance-testing strategy, automating acceptance, end-to-end (E2E), or QA testing of a running app, deciding what to cover with fast headless tests vs slow UI/E2E, building agent-driven exploration or automation of a running app, building a below-UI operator seam (interaction layer) or headless client, or crystallising agent-discovered knowledge into reusable deterministic artifacts (maps, graphs, scripts, tests). Covers the Discovery⇄Determinism flywheel, the operator-seam architecture (one seam serving both a headless test client and AI-agent tools), and layered headless-first acceptance testing with a surgical UI state-graph tier for GUI-only defects.

Establish a design source-of-truth (a DESIGN.md-style two-layer doc of tokens + rationale), build a lookbook that renders it, and wire a live-refresh preview server so visual work gets a fast edit→see feedback loop. Use when setting up or restructuring a design system / design tokens, creating a DESIGN.md or design source-of-truth, building a lookbook, or wanting live preview / live reload of design or marketing artifacts — landing pages, decks, one-pagers, marketing material previews. The visual analogue of the operator-seam test loop: it crystallises taste into determinism. Defers aesthetic taste (typography/color/motion choices) to the frontend-design skill.

Inspect a failed or stalled subagent's transcript compactly to recover. Use when a background subagent failed, stalled, or its <result> summary isn't enough to decide what to do next, and you need to look inside its run without loading the whole transcript into your context.

Install, update, audit, or repair Promode for Codex in a project. MUST be loaded when the user asks to set up promode-codex, install Promode for Codex custom agents, check the Codex Promode hook or setup, update the project-scoped Promode agents, scaffold Promode project tracking files, or verify that Promode is correctly adapted for Codex.

Audit how well a repository aligns with the Promode methodology in Codex, then produce a prioritised improvement plan. Use when the user asks to assess Promode alignment, audit a repo against Promode practices, improve tests, feedback loops, traceability, agent knowledge, runbooks, or architecture, or bring a codebase into Promode shape. Also flags stale Claude Promode install leftovers; use managing-promode-codex for Codex setup audits.

Put the bulk of acceptance coverage below the UI through a fast, deterministic headless client driving an operator seam, and reserve a surgical UI state-graph tier for defects that only manifest through the real GUI. Use when designing test/QA or acceptance-testing strategy, automating acceptance, end-to-end (E2E), or QA testing of a running app, deciding what to cover with fast headless tests vs slow UI/E2E, building agent-driven exploration or automation of a running app, building a below-UI operator seam (interaction layer) or headless client, or crystallising agent-discovered knowledge into reusable deterministic artifacts (maps, graphs, scripts, tests). Covers the Discovery⇄Determinism flywheel, the operator-seam architecture (one seam serving both a headless test client and AI-agent tools), and layered headless-first acceptance testing with a surgical UI state-graph tier for GUI-only defects.

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 later. Optional user text may specify what the next session should focus on.

Recover from failed, stalled, or unclear Codex subagent runs without over-reading unstable transcripts. Use when a Codex subagent failed, stalled, drifted, returned an insufficient result, or needs steering, closing, or a follow-up recovery prompt.

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 plugins, agents, hooks, or wants to extend OpenCode functionality.

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 auditing projects for conformance. Invoke PROACTIVELY when user mentions CLAUDE.md, project setup, agent configuration, or code meta files.

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, uninstall, or delete skills.

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 skill, update skill, check skills, list skills.

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, reviewing agent code, or orchestrating multi-agent systems with the @openai/agents package.

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, marketplaces, or wants to add custom commands/agents to Claude Code.

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, templates, or skill evals. Supports personal and standalone distributable skills.

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 documentation, deprecation, embedded resources, and progressive disclosure.

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 deterministic path specs from recorded sessions.

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 testing of iOS apps. Covers launching test flows, verifying screens, interacting with UI elements, and diagnosing failures. Triggers on: test my app, verify the app, check the UI, does this work, acceptance test, outside-in test, e2e test, functional test, smoke test, exploratory test.

MUST be used when you need to browse the web. Efficient browser automation designed for agents - enables intuitive web navigation, form filling, screenshots, and data scraping through accessibility-based workflows. Triggers on: browse website, visit URL, open webpage, fill form, click button, take screenshot, scrape data, web automation, interact with website.

Local semantic search for markdown documents using qmd. Combines BM25 full-text, vector semantic, and LLM re-ranking—all on-device. Use when searching notes, documentation, meeting transcripts, or knowledge bases. Triggers on: search markdown, find in notes, query documents, semantic search, search my docs.