Design and improve revenue operations, lead lifecycle rules, scoring, routing, handoffs, and CRM process automation. Use when marketing, sales, and customer success workflows need clearer operational structure.

Build end-to-end type-safe APIs with tRPC — routers, procedures, middleware, subscriptions, and Next.js/React integration patterns.

Forensic root cause analyzer for Antigravity sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.

Diagnose and optimize Agent Skills (SKILL.md) with real session data and research-backed static analysis. Works with Claude Code, Codex, and any Agent Skills-compatible agent.

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.

Economic analysis of government intervention -- taxation (incidence, efficiency, optimal design), regulation (cost-benefit, market failure correction), externalities (Pigouvian taxation, cap-and-trade, Coasian bargaining), and public goods provision (non-rivalry, non-excludability, free-rider problem). Covers welfare analysis of policy interventions, government failure, and the institutional context of policy-making. Use when evaluating policy proposals, analyzing tax effects, assessing regulatory design, or reasoning about the appropriate scope of government action.

Study of human activities, spatial patterns, and social processes on Earth's surface. Covers population and migration, cultural diffusion and landscapes, urbanization and city systems, economic geography and development, political geography and borders, and social/identity geographies. Use when reasoning about why people live where they do, how cultures spread, how cities grow, how economies are spatially organized, or how power operates through space.

Cascade the same edit pattern across N files safely. Use when applying the same refactor to multiple files (e.g. swap import paths across 11 scripts, rename a symbol, migrate a call signature). Detects the common-shape-across-files situation and turns an N-file cascade into a planned audit → apply → verify workflow instead of N sequential manual edits.

Bridges the gap between existing projects and GSD adoption by inferring GSD artifacts from current project state, preserving git history and existing work.

Provides release management strategies including deployment patterns, version control, and rollback procedures. Use when planning releases, managing deployments, or when user mentions 'release', 'canary', 'blue-green', 'rollback', 'feature flag', 'release train', 'semantic versioning', 'changelog', 'migration'.

Provides SQL best practices for query optimization, schema design, migrations, transactions, and indexing. Use when writing database queries, designing schemas, creating migrations, or when user mentions 'SQL', 'database', 'query', 'schema', 'migration', 'index', 'transaction'.

Classical root cause analysis techniques for quality improvement and incident investigation. Covers 5 Whys (with Card's 2017 critique and boundary conditions), Ishikawa/fishbone diagrams, Fault Tree Analysis (FTA), Failure Modes and Effects Analysis (FMEA), Cause Mapping, and Doggett's method-selection framework. Use when investigating a failure, running a post-incident analysis, building a fishbone, calculating fault tree cut sets, running an FMEA pass, or deciding which classical technique fits the problem. Not suitable alone for complex socio-technical failures — escalate to rca-systems-theoretic or rca-causal-inference when the incident has multiple interacting causal chains.

Token budget tracking and enforcement for Gastown convoy-level execution. Hard limits with pre-execution checking, per-convoy and per-agent tracking, structured stop reasons.

OpenStack Cinder block storage service. Provides persistent volume management for cloud instances including volume creation, snapshots, backups, LVM/iSCSI backend, volume types with QoS, encryption (LUKS), volume migration, and multi-backend support. Use for deploying, configuring, operating, and troubleshooting OpenStack block storage.

Plan and build MCP servers with agent-friendly tools, schemas, error handling, and evaluation. Use when creating or refactoring MCP integrations.

Create or update agent skills with concise SKILL.md instructions, bundled resources, agent metadata, validation, and packaging. Use when building or refactoring skills.

Data persistence patterns in Go covering raw SQL with sqlx/pgx, ORMs like Ent and GORM, connection pooling, migrations with golang-migrate, and transaction management. Use when implementing database access, designing repositories, or managing schema migrations.

Provides the complete Swift Concurrency Migration Guide. Use when migrating to Swift 6, resolving data-race safety errors, understanding Sendable and actor isolation, or incrementally adopting async/await.

Safe refactoring workflow using trace-mcp — assess risk, find candidates, check impact, and rename symbols across all files without missing import sites or cross-file references.

Use when formulating the best technical approach for a task — before writing implementation plans or code. Triggers on architecture decisions, complex features, refactors, or when the user asks how to approach something. Investigates current codebase, questions existing patterns, researches alternatives, and presents approaches with trade-offs.

Coach PMs: evidence-based assessment, growth bets, development plan, coaching cadence.

**Objective:** Redesign and relaunch the user onboarding experience to improve activation rates, reduce time-to-value, and decrease early churn.

**Skill used:** `delegating-work`

- **Task:** Improve onboarding activation rates for our product

- **Company**: B2B analytics SaaS

Produce a Tech Debt Management Pack (debt register, scoring, refactor vs rewrite memo, paydown plan).

Diagnose and improve marketplace liquidity: metric tree, fragmentation map, bottleneck diagnosis.

This plan targets improving the booking fill rate from 55% to 75% for SF evening slots (5-9 PM) within 6 weeks. The core problem is a supply-demand imbalance during peak evening hours, resulting in an

**Company:** B2B Analytics SaaS (Series B, 50 engineers)

Multiple feature teams are independently rebuilding export functionality, filtering logic, and permission checks. This results in:

- **Product**: B2B SaaS platform for data teams

Improve retention and engagement: diagnosis, aha moment, lever hypotheses, experiment backlog. See also: user-onboarding (first-time UX).

**Product:** Meditation & Mindfulness App (B2C Subscription)

| Parameter | Value |

Turn engineering strategy into a Technical Roadmap Pack (diagnosis, roadmap table, initiative briefs).

Create or improve a skill by using the system skill when available and the legacy local bundle as fallback

Fetch Huawei HarmonyOS developer document正文 by calling documentPortal getDocumentById API with slug objectId, convert HTML content to Markdown, and maintain local-first migration references. Use when scraping Huawei HarmonyOS docs that are SPA-rendered and not directly readable by generic web fetchers.

>

Maintain a development log (DEVLOG.md) at the project root. Use at the START and END of every coding session, after implementing features, fixing bugs, refactoring code, or making any meaningful code changes. Automatically triggered for all development tasks.

`cm-<name>` — what it does in one sentence.

Code hygiene gate — detect and eliminate dead code, duplicates, naming mess, and code smells. TRIZ-powered. Run after features, before PRs, during debt sprints.

One-off full repository audit for documentation health (docstrings, README, architecture, scripts conventions). Use explicitly when requested.

Scientific, customer-centric approach to conversion rate optimization based on the CRE Methodology(TM). Extraordinary improvements come from understanding WHY visitors don't convert, not from copying

Searches and rewrites code using AST patterns. Use when finding code patterns, refactoring at scale, or detecting anti-patterns across a codebase.

Refactors TypeScript codebases with AST-aware rename, extract, and reference finding. Use for moving functions between files, renaming across codebase, or finding all usages of a symbol.

Audits and optimizes websites for search engine visibility (SEO) and AI search citation (GEO), covering technical health, E-E-A-T content scoring, domain authority, structured data, rich results, and entity signals. Use when running SEO audits, diagnosing traffic drops or ranking losses, generating Schema.org JSON-LD, checking Core Web Vitals, crawlability, robots.txt, sitemaps, hreflang, backlinks, planning content strategy or site migrations, fixing indexing issues, or optimizing for AI Overviews, ChatGPT, and Perplexity. NOT for paid ads (PPC/SEM), social media strategy, email marketing, or general web development unrelated to search.

Start/stop Kokoro TTS HTTP server. TRIGGERS - start tts server, kokoro server, tts http, stop tts server.

Guide for building, configuring, and deploying microfrontends on Vercel. Use this skill when the user mentions microfrontends, multi-zones, splitting an app across teams, independent deployments, cross-app routing, incremental migration, composing multiple frontends under one domain, microfrontends.json, @vercel/microfrontends, the microfrontends local proxy, or path-based routing between Vercel projects. Also use when the user asks about shared layouts across projects, navigation between microfrontends, fallback environments, asset prefixes, or feature flag controlled routing.

Use when creating, reorganizing, or maintaining the skills/ directory. Covers the shared skill layout conventions, directory structure, SKILL.md format, symlink architecture, and how to add or restructure skills so both Claude Code and Gemini CLI discover them.

Migrate code from quorum-desktop to quorum-shared. Activates when moving utils, hooks, or components to the shared package. Guides the full workflow: analysis, copy, refactor imports, update barrel, delete local source, verify builds on web and mobile.