session-flow

Capture a new task into the project's task sequence (backlog) with a detailed breakdown. Use when something surfaces that should be done later — a bug, an optimization, a follow-up — and you want it recorded in SEQUENCE.md with a bite-sized, ready-to-execute breakdown. Produces a one-line sequence entry linked to a per-task breakdown file (or a session-task-planning phase file for multi-task work). Triggers on "/session-add-task" or when user says "add a task", "capture this for later", "put this on the backlog", or "remember to do X".

Triage incoming work (GitHub issues, feature requests, surfaced ideas) and route it — trivial aligned fixes go into the task sequence, while significant or direction-divergent items are escalated to a cowork research-design session. Grounds every decision in the app's architecture and product direction (PRD.md). Use as the front-of-chain intake funnel. Triggers on "/session-gatekeeper" or when user says "triage these issues", "process the backlog of issues", "should we do this issue", or "is this worth a research-design session".

Groom the task sequence (backlog) by researching un-broken-down entries and attaching ready-to-execute breakdowns. Use to keep SEQUENCE.md healthy — every entry researched, verified, and linked to a breakdown — especially for items added as raw one-liners. Safe to run periodically via /loop. Triggers on "/session-groom" or when user says "groom the backlog", "prepare the sequence", "fill in the task breakdowns", or "tidy up SEQUENCE.md".

Bootstrap the project documentation structure for session-flow skills. Creates research/, plans/, todo/, testing/, and architecture/ directories. Run once when adopting session-flow in a new project. Triggers on "/session-init" or when user says "initialize project", "setup docs structure", or "bootstrap project".

Implement the next task from the project's task sequence (backlog). Reads SEQUENCE.md, picks the next open entry that has a linked breakdown, executes it, and marks it done. Use when the user wants to make progress on the backlog without naming a specific task. Triggers on "/session-next" or when user says "implement the next task", "do the next task", "what's next — just do it", or "work the backlog".

Orchestrate agent execution from a session task plan. Parses dependency tags to dispatch sequential and parallel agents via the Task tool. Use after /session-task-planning produces a todo file. Triggers on "/session-delegation" or when user says "execute the tasks", "run the plan", or "dispatch the agents".

Create Claude Code-scoped tasks with parallelization analysis. Use when breaking down a multi-step implementation into discrete tasks that can each be completed in one Claude Code session. Produces task files with dependency tags ([seq], [parallel-after:X]) and session-fit validation. Triggers on "/session-task-planning" or when user says "break this into tasks", "plan the tasks", or "create a task list".

Surgical updates and current-state initialization for session-flow architecture documentation in _devdocs/architecture. Ensures token-efficient edits, current data-flow and system-structure notes, architecture index hygiene, and doc splitting checks. Called by session-post-implementation step 7. Triggers on "/update-architecture" or when user says "update arch docs", "sync architecture", "map current architecture", "initialize architecture docs", or "docs are out of date".

Deep research and design workflow for complex features. Use before /session-task-planning when a feature requires exploring implementation approaches, analyzing existing code, and designing an architecture before breaking into tasks. Produces a research report and an implementation plan that feeds into session-task-planning. Triggers on "/session-research-design" or when user says "research this", "explore approaches for", or "design this feature".

Post-implementation refinement workflow. Use after completing a major feature or plan implementation to simplify, review, sanitize, and document the code. Triggers on "/session-post-implementation" or when user says "run the iteration workflow" or "polish this implementation".

End-to-end release workflow that bumps version, packages artifacts, and verifies satellite content (docs sites, marketing sites, changelogs) is up-to-date. Combines project-specific release skills with a generic release surface scan. Triggers on "/session-release" or when user says "prepare the release", "do a release", or "release workflow".

Evidence-based verification workflow for completed features and plans. Produces a falsifiable proof artifact that implementation matches design spec, identifying defects, stubs, and spec-vs-reality gaps. Triggers on "/session-verify" or when user says "verify this feature", "prove this works", "run verification", or "confirm the implementation".

Combined technical security and legal liability audit for code changes. Covers LLM/AI security, OWASP Top 10, agentic security (Lethal Trifecta), secrets detection, desktop app security, dependency supply chain, AND legal/liability risk (GDPR, EU AI Act, ToS/EULA coverage, data protection, consumer rights, cross-border transfers). Designed for solo developers in the EU serving a worldwide userbase. Use when: completing a feature implementation, before release, after any change that touches security-sensitive areas, AI features, data handling, payment logic, or user-facing terms. Triggers on "/security-liability-audit" or as a step in session-post-implementation.