(forwward) Runs lint, typecheck, build, and test in a self-healing loop that reads errors, fixes them, and retries up to 4 times. Triggers on verify, check, make sure it works, pre-commit validation, pre-deploy checks, or any quality gate.
(forwward) Ships code — owns the pipeline from verified branch to deployed and healthy. Stack-aware shipping engineer and on-call SRE: detects Node/Go/Python/Ruby/Rust/Java/Terraform/Pulumi/Lambda/CDK and runs the right gate, build, test, deploy. Three modes — PR, release (version bump, changelog, tag, health check), hotfix. Confirms before every irreversible step. Use for "ship this", "open a PR", "release", "deploy", "cut a release", "hotfix".
(forwward) Orchestrates multi-agent engineering and business teams by analyzing tasks, selecting team shapes, assigning specialist roles, and coordinating parallel agent work with skill dispatch. Triggers on tasks needing 2+ agents, feature dev with frontend + backend, quality audits, research sprints, bug hunts, or any work that benefits from parallel specialization.
(forwward) Consolidates recent team work — commits, PRs, decisions, fixes, learnings — into a shared `team-memory/MEMORY.md`. Like REM sleep for the team. Use after a PR merges, after a release, at sprint-end, or when the user says "team memory", "what did we ship this week". Reads git log, PRs, CHANGELOG, ADRs, and the conversation; appends Shipped, Decisions (with WHY), Fixes (root cause), Learnings, Open Threads. Not for one-off summaries or PII.
(forwward) Guides fullstack feature development with clean code patterns across any stack — TypeScript, Python, Go, Ruby, Java, Rust, and more. Detects the project's stack before advising. Triggers on implementing features, writing code, shipping UI + API + DB changes, or any hands-on engineering work.
(forwward) Onboards founders to forwward-teams by learning what they build, initializing the environment, and recommending which skills to use first. Triggers on first install, new project setup, getting started, or when a user asks what forwward-teams can do.
(forwward) Aggressively audits and cleans a codebase — removes slop, dead code, and AI-generated noise; fixes DRY/SOLID violations; restructures toward the simplest correct implementation. One commit, no behavior changes. Use when the user says "audit the code", "clean up tech debt", "remove dead code", "deslop", "this codebase is a mess", or asks for a code-quality pass. Detects stack and applies idiomatic patterns. Works on full codebase or specific paths.
(forwward) Structures slide content for pitches, QBRs, board updates, investor updates, strategy decks, and all-hands. Produces slide-by-slide outlines with titles, talking points, and key data per slide — content, not visual design. Use when the user says "help me build a deck", "pitch deck", "QBR", "board update", "what slides do I need", or is preparing a high-stakes presentation without structure yet.