swamp-software-factory

Drive @adam/software-factory runs: a fully generic, model-driven state machine for software development lifecycles with adversarial review gates, verified testing, and human approvals. Use when the user wants to start factory work on a work item, check factory status, drive a run forward, author a new factory definition, report on how a work item was implemented, or pull specific fields out of recorded run data (plans, review findings, evidence, the journal). Triggers on "software factory", "factory run", "start work on", "factory status", "advance the factory", "author a factory", "what happened with <work item>", "work item history/report/summary", and any question about artifacts or findings a factory recorded. Consult this skill the moment a message mentions a factory, factory run, or work item — before answering or running any command.

Interactive getting-started walkthrough for new swamp users. Guides through understanding the user's goals, creating and running a first model, inspecting output, and choosing next steps. Uses a state-machine checklist with verification at each step. Triggers on "getting started", "get started", "new to swamp", "first time", "tutorial", "walkthrough", "onboarding", "how do I start", "what do I do first", "quickstart", "quick start", "hello world", "first model", "just installed swamp", "show me how swamp works", "intro to swamp", "new user", "set up swamp", "learn swamp".

Swamp CLI — create and run models, build and validate workflows, query and manage data, store and retrieve vault secrets, develop and publish extensions, initialize repos, run reports, file issues, and troubleshoot errors. Triggers on swamp commands (swamp model, swamp workflow, swamp vault, swamp data), extension development, repo setup, or diagnostic questions. Do NOT use for getting started / onboarding (use swamp-getting-started), pull requests, git operations, worktree management, cron/agent scheduling, or general coding tasks unrelated to swamp.