AI Agent Workflow Collection

Systematic debugging — evidence before hypotheses, hypotheses before fixes, root cause before patches, and the diagnosis saved to the vault. Use for any real bug, test failure, regression, crash, or unexplained behavior — before proposing any fix.

System design phase — architecture, tech-stack options, module boundaries, data model, and ADRs from a validated SRS. Use after requirements are validated, when choosing a tech stack, designing system structure/APIs/data models, or recording an architecture decision.

The developer-driven design lane — the user commits to each approach before anything is written, then the design goes to pseudocode, algorithms, invariants, sequence diagrams and test vectors in their chosen design language. Use when the user wants to own the system rather than receive it: "developer mode", deep/detailed design, designing algorithms or data structures, writing pseudocode or sequence diagrams during design, or human-driven planning after the SRS.

UI/UX design phase — propose an intentional design system (pattern, brand, color, typography, spacing, atomic components) with the user, offering distinct directions and per-page layout options, for any interface type: Web, Mobile, Desktop, TUI, or CLI. Use when the SRS declares a user interface, when defining a design system or visual identity, choosing layouts, or reviewing UI work against UX laws.

Disconnect a project from SwarmVault and choose what happens to its knowledge — keep it, export it into the repo, or delete it. Use when the user wants to stop using SwarmVault here, remove the vault wiring, uninstall the framework from a project, offboard or archive a project, or delete a project's vault data.

The SDLC router — figures out where a project stands and runs the right phase. Use at the START of any work in a SwarmVault project: continuing/resuming a project, starting a new one, "what's next", or before writing any feature code, spec, design, or ticket. Also use when unsure which phase (requirements, design, implementation, review) comes next. Resume-from-anywhere on any platform.

Implementation phase — turn a validated design into dependency-ordered tickets, then work them as one of N parallel agents with atomic claims, model tiering, and tests-in-ticket definition of done. Use to plan tickets from a design, pick up/continue implementation work, coordinate parallel agents, or check what to build next.

Optional autonomy control plane — set up (which platforms you have + a pace: budget/balanced/fast), launch, monitor, recover, or stop local CLI-agent workers (Claude Code and Codex verified; Gemini, OpenCode, Droid, Cursor, Copilot best-effort; any other agent via a launch-command template) through SwarmVault's durable supervisor, with budget- and model-fit-aware task assignment, a cross-platform observability board (usage/limits, tokens, per-agent progress), safe-state context compaction, and usage-limit continuation so long projects survive quota resets. Use when the user asks to orchestrate agents, enable/disable a supervisor, dispatch work across platforms, assign work by usage limits or model strength, view or monitor a live board of all agents, add a launch adapter, compact/continue past a usage limit, or recover idle work.

Author new high-quality skills that trigger reliably and stay lean. Use when creating or editing a skill, packaging a workflow as a skill, or deciding whether something should be a skill at all.

Requirements phase — a clarifying, options-first stakeholder interview that removes confusion and assumptions (not a relentless grilling) and produces a validated SRS + per-feature specs with EARS acceptance criteria and ISO 25010 NFRs. Use to start a new project's requirements, gather/analyze/specify/validate requirements, stress-test a plan, or mine requirements from an existing codebase (brownfield). Also handles requirement changes after validation.

The vault contract — how any agent reads, writes, and queries the SwarmVault. Use at the start of work in any vault-connected project, before exploring the repo, when deciding where to record memory/plans/decisions/sessions, when handing off between sessions or agents, or whenever unsure how the vault works.

Writing for humans — any end-user-facing text, in any language. READMEs, landing pages, blog posts, social posts, marketing copy, release notes, docs, and UI microcopy (tooltips, buttons, empty states, error messages). Use when asked to write, rewrite, polish, or humanize copy, when text sounds robotic or AI-generated, when defining a voice or tone, and — unprompted — whenever you are about to produce any string a real user will read.