AI Agent Workflow Collection

Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Use when setting up agent training, instrumenting agents with tracing, configuring LightningStore, implementing reward functions, or optimizing prompts with RL/APO algorithms.

Use when implementing Liquid Glass effects, reviewing UI for Liquid Glass adoption, debugging visual artifacts, optimizing performance, or requesting expert review of Liquid Glass implementation - provides comprehensive design principles, API patterns, and troubleshooting guidance from WWDC 2025.

Auto-generate a slim CLAUDE.local.md from brain DB. Preserves manual behavior rules. Produces ~1,200 token auto-generated context section with key people, systems, decisions, and project status.

Incremental rescan of project folder. Detects new/changed files since last scan, extracts knowledge from CLAUDE.local.md, memory files, and doc inventory, and updates the brain DB. Requires an existing projectbrain.db — run /brain-init first if none exists.

End-of-session brain flush. Scans the full conversation, extracts all new entities, decisions, tasks, events, relationships, and updates, presents a summary, and writes to projectbrain.db after confirmation. Use at end of every session or when you want to capture everything discussed.

CoCo — your AI PM brain. Unified interface wrapping skills, commands, and knowledge tools. Invoke /coco to activate.

Turn the project you just shipped into a short, polished, shareable launch video (an "ad") using HyperFrames. Use when someone says "/coco-ads", "make a launch video", "brag about this", "turn this into a promo", "make an ad for this", or wants to share what they built. Reads the project code directly — no live URL or screenshots needed. Renders locally.

Install, update, version-check, or uninstall the Coco open-source AI workflow framework via its CLI (@coco-research/coco-cli, run with npx). Use when setting up Coco on a machine, pulling the latest into an existing clone, checking the installed version, or removing it. Triggers on "install coco", "update coco", "set up coco", "coco cli", "uninstall coco".

Post-implementation verification system that catches AI-introduced bugs. Covers 7 categories — TDZ errors, import mismatches, reference integrity, dead code, React state/effects, mock isolation, and CSS integrity. Run after every code change, after writing tests, or before marking a task complete. Triggers on "verify", "check code quality", "run verification", "audit code", "quality gate", "pre-commit check".

Auto-fix issues found by code review in REVIEW.md. Spawns fixer agent, commits each fix atomically, produces REVIEW-FIX.md summary.

Multimodal memory — ingest, embed, and search media (images, video, audio, files) with Gemini Embedding 2 +…

Build ChatGPT apps with MCP servers on Cloudflare Workers. Extend ChatGPT with custom tools and interactive widgets (HTML/JS UI).

PM Studio command center. Use for a quick overview of available commands and document inventory. Use when someone says "pmstudio", "show commands", "what can I generate", or "project status". Do NOT use for detailed completeness audits — use /pmstudio-nfr instead. Shows document coverage dashboard and recommends which /pmstudio- command to run next.

Generate an Architecture Review Board (ARB) presentation in Coco Inc's standard 11-slide format. Use when someone asks to "create an ARB deck", "architecture review presentation", "prepare for architecture review board", "ARB slides", or needs to present a product/platform architecture for sign-off. Reads PRD, architecture maps, and project memory to pre-fill technical content. Produces a self-contained HTML slide deck.

Create or update a structured change log for a product or platform. Use when someone asks to "create a change log", "log this change", "what changed", "update the change log", "release notes", or "changelog". Reads project memory (CLAUDE.local.md Recent Changes) and meeting notes to build chronological change records. Supports init (backfill from memory), update (append new entries), and release (summarize for a version).

Generate a Disaster Recovery plan with RTO/RPO targets. Use when someone asks to "create a DR plan", "disaster recovery", "business continuity", or "RTO RPO". Do NOT use for step-by-step restoration runbooks — use /pmstudio-recovery instead. Designed for SaaS platform products where Coco Inc is the customer — focuses on service continuity, data recovery, and vendor dependency management rather than infrastructure rebuild.

Generate an Incident Response Plan (IRP) with severity classification, escalation procedures, and communication templates. Use when someone asks to "create an incident response plan", "IRP", "incident procedures", "escalation matrix", "incident playbook", or needs to document how to handle incidents for a product/platform. Reads PRD, stakeholder directory, and project memory to build product-specific response procedures. Complementary to DR plan (DR = restore service; IRP = manage the incident while it's happening).

Detailed completeness audit of all project documents. Use when someone asks "are we ready for production", "audit our docs", "readiness check", "nfr tracker", or "what's missing". Do NOT use for a quick command listing — use /pmstudio instead. Scans every document for section-level completeness, reports staleness, and gives prioritized gap-closure recommendations.

A skill that blends the wisdom of top industry experts, ensures token-efficient PRDs, and organizes outputs in a clear folder structure.

Use when users request new features, enhancements, bug fixes, or any work that needs planning. Creates structured task files and PRDs (Product Requirements Documents) before implementation. Activates for "I want to add X", "implement Y", "create a task for Z", "plan this feature", or any feature request.

Deep analysis with adversarial reasoning — Evidence-First + Multi-Perspective + Steel-Man + Pre-Mortem + Sensitivity. Produces a recommendation with confidence bounds.

Use at the start of any task to route between Superpowers skills and GSD commands based on project state, task scope, and context signals. Fires before other skills when both systems are installed.

Rapid codebase assessment — lightweight alternative to…