npx claudepluginhub codyswanngt/lisa --plugin lisa-nestjsComprehensive guide for NestJS GraphQL development using Apollo and code-first approach. This skill should be used when writing GraphQL resolvers, mutations, queries, types, subscriptions, or implementing advanced features like field middleware, complexity limits, and custom scalars. Also covers project-specific patterns including zero-trust auth decorators and DataLoader integration.
Procedural rules and patterns for NestJS backend development. This skill should be used when creating new NestJS modules, services, resolvers, or controllers. It covers component generation with NestJS CLI, TDD patterns, module structure conventions, Lambda handler patterns, and configuration standards. Use this skill alongside nestjs-graphql for GraphQL-specific patterns.
Enforces TypeORM implementation patterns for this NestJS backend project. This skill should be used when creating or modifying TypeORM entities, repositories, database configuration, migrations, or any database-related code. It covers configuration patterns (TypeOrmModule.forRootAsync, replication, naming strategy), entity patterns (base entity, comments, indexes), and observability (X-Ray logging).
Lisa is a governance layer for AI-assisted software development. It ensures that AI agents — whether running on a developer's machine or in CI/CD — follow the same standards, workflows, and quality gates.
When a request comes in (from a human, a JIRA ticket, or a scheduled job), Lisa classifies it and routes it to the appropriate flow. Flows are ordered sequences of specialized agents, each with a defined role.
A request to fix a bug routes to a different flow than a request to build a feature or reduce code complexity. The routing is automatic based on context, but can be overridden explicitly via slash commands.
A flow is a pipeline. Each step in the pipeline is an agent — a scoped AI with specific tools and skills. One agent investigates git history, another reproduces bugs, another writes code, another verifies the result.
Agents delegate domain-specific work to skills — reusable instruction sets that can be invoked by agents, by slash commands, or by CI workflows. The same skill that triages a JIRA ticket interactively is the same skill invoked by the nightly triage workflow.
Flows can nest. A build flow includes a verification sub-flow, which includes a ship sub-flow. This composition keeps each flow focused while enabling complex end-to-end workflows.
Lisa enforces quality through layered gates:
The same rules, skills, and quality gates apply everywhere:
The analytical logic lives in skills. The enforcement lives in hooks and rules. The orchestration adapts to context — using MCP integrations locally and REST APIs in CI — but the standards don't change.
Lisa distributes its standards to downstream projects as templates. When a project installs Lisa, it receives:
Templates follow governance rules: some files are overwritten on every update (enforced standards), some are created once and left alone (project customization), and some are merged (shared defaults with project additions).
curl -fsSL https://claude.ai/install.sh | bash
Ask Claude: "I just cloned this repo. Walk me through setup."
Ask Claude: "I have JIRA ticket [TICKET-ID]. Research, plan, and implement it."
Or use slash commands directly:
/fix — route through the bug fix flow/build — route through the feature build flow/improve — route through the improvement flow/investigate — route through the investigation flow/jira:triage <TICKET-ID> — analytical triage gate: detect ambiguities, edge cases, and verification methodology/plan:improve-tests <target> — improve test quality by analyzing and strengthening weak or brittle testsAsk Claude: "What commands are available?"
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.