/help-flow

name: help-flow
description: "Help about Rosetta: explains capabilities and usage."
tags: ["workflow"]
baseSchema: docs/schemas/workflow.md

<self_help_flow>

<description_and_purpose>

Audience: developers and orchestrators exploring Rosetta-powered workspaces. Use when: "what can you do", "how do I use X", "how to develop with Rosetta", "what workflows are available", or any capability discovery question. Provides: guides user on how to use Rosetta and its capabilities; live overview of available skills, workflows, and agents; detailed guidance on matched capabilities; seamless handoff to any discovered workflow within the same session; Consider user sees this first time, you must explain, be clear, specific, non-ambiguous, user should just be able to follow it.

</description_and_purpose>

<invocation_guidance>

When presenting capabilities to users, always show concrete slash command examples following this pattern: `/[command-name] [request in natural language]`

QUICKSTART REFERENCE PATTERN — use this exact style for all examples shown to users:

/coding-flow Implement side bar on the home page, ...
/coding-flow Identify and implement fix, ...
/coding-flow Improve unit tests coverage to 85% for ...
/requirements-authoring-flow Extract detailed business and technical requirements from ... using subagents.
/modernization-flow Perform modernization phase 1 to reuse library refsrc/... using subagents.
/research-flow Investigate OAuth 2.0 implementation options for our stack
/ui-aqa-flow Create UI test automation for the checkout flow
/api-aqa-flow Automate backend API tests for TC-1234 with Swagger: https://api.example.com/swagger.json

HOW WORKFLOWS EXECUTE: Workflows are multi-phase pipelines. The AI guides the user through each phase automatically — HITL gates pause for user review and approval at critical decisions. Users invoke the workflow once with a slash command and follow AI guidance; they do not manage phases manually.

DIRECT SKILL INVOCATION (also supported): Skills can be invoked directly. Slash command = folder name of the skill. Naming rule: `skills/[folder-name]/SKILL.md` → `/[folder-name] [request]`

WHAT MAKES A VALID DIRECT SKILL EXAMPLE — a valid request must have all three: 1. Specific artifact or target (not "this error" or "the tests" — name the file, log, or exact thing) 2. Explicit method or action (not "investigate" alone — state what to produce and how) 3. Explicit scope constraint (state what NOT to do, or what the boundary is)

WORKFLOWS ARE SELF-CONTAINED — they invoke skills internally: `coding-flow` handles all coding tasks and invokes debugging, testing, and other skills itself as needed. Similarly, every other workflow invokes its own skills internally. Users should never manually invoke `/debugging`, `/testing`, `/coding`, or similar skills for work that belongs inside a workflow — the workflow handles that automatically.

BAD examples (do NOT show these — they are wrong):

• `/coding Debug this error in auth.py` — `/coding` is an IMPLEMENTATION skill invoked internally by `coding-flow`, not a standalone tool; and `coding-flow` invokes `/debugging` itself when needed
• `/debugging Investigate why payment tests fail` — too vague: no specific artifact, no expected output, no constraint; and if a fix is needed afterward, this belongs in `coding-flow` entirely
• `/research Compare event sourcing vs CRUD for our order service` — this IS what `/research-flow` is for; using the skill directly bypasses the structured research workflow; PRIORITY RULE applies

GOOD examples:

• `/natural-writing Rewrite the executive summary in docs/CONTEXT.md — remove AI clichés, max 4 sentences, audience is a new engineer joining the project`
• `/debugging Read the stack trace in agents/TEMP/error.log — identify root cause only, do NOT propose fixes, report findings`

DIRECT SUBAGENT INVOCATION (also supported): Subagents can be invoked directly. Slash command = file name without `.md`. Naming rule: `agents/[name].md` → `/[name] [request]`

Same rule applies — each example must specify the artifact, method, and constraints. Vague requests like "Design the auth module" or "Implement the payment service" require a full workflow, not direct subagent invocation.

GOOD examples:

• `/architect Question me and initialize as a loop a project-brief.md as concise dense document for business context, technical context, architecture, tech stack, etc. No coding.`
• `/reviewer Check current git changes, understand what was changed and why, validate against AC, find gaps or possible issues according to DoD`
• `/reviewer Validate implemented changes by actually running the code and using manual QA by AI`

PRIORITY RULE — WORKFLOWS ARE PREFERRED: When a workflow and a skill or subagent share a similar name or purpose, always recommend the WORKFLOW. Reason: workflows provide the full structured process — discovery, specs, plan, review, HITL gates, subagent delegation, and validation — that open-ended or multi-step requests require. Direct skill and subagent invocation is ONLY appropriate for targeted, self-contained, one-pass tasks where the user already knows exactly what they want done and it does not require phases, plan approval, or review by a separate agent.

</invocation_guidance>

<workflow_phases>

<prerequisites phase="0", applies="ALL">

1. All Rosetta prep steps MUST be FULLY completed, SKILL `load-project-context` loaded and fully executed. 2. MUST use todo tasks for reliability 3. Phases are sequential. Orchestrator coordinates; trust skills and subagents to execute. 4. Scale: conversational — output is a message, no files, no state tracking.

<prerequisites phase="0", applies="ALL">

<list_capabilities phase="1" subagent="discoverer" role="KB catalog lister">

1. List capabilities from KB with XML format:

• `LIST workflows`
• `LIST skills`, then `LIST skills/<name>` for each.
• `LIST agents`

2. Build `Capability Catalog`: name, type (workflow/skill/agent),