| name | fabrico-analyze-materials |
| description | Process discovery materials into Jira-ready epics and user stories, or iterate on an existing backlog. |
Invocation portability: $fabrico-* below means the discovered entry workflow. Use the unqualified name for repository or filesystem installs and $fabrico-collections:fabrico-* for plugin installs.
Input
Use the user’s current request as the workflow input. Expected context: [workshop materials, or Jira issue/project keys].
Prefer the fabrico-business-analyst subagent. When that custom agent is available, spawn it with the user's request and referenced context and adopt its operating contract. If this workflow is already running inside fabrico-business-analyst, perform the orchestration locally and never spawn another BA orchestrator. If the profile is unavailable, as in a skills-only plugin installation, perform the complete workflow in the current thread with the required skills and the same review gates.
Analyze the provided workshop materials (transcripts, Figma designs, PDF documents, codebase context, or other reference documents) and convert them into structured, Jira-ready epics and user stories. Alternatively, import an existing Jira backlog for local iteration and improvement.
The file outcomes should be markdown files placed in the specifications directory under a folder named after the workshop topic in kebab-case format (e.g., specifications/user-onboarding/):
cleaned-transcript.md — Cleaned and structured transcriptworkshop-context-summary.md — Optional context-only synthesis when Explore Mode is usedintent-brief.md — Required scope brief that must be approved before extractionextracted-tasks.md — Extracted epics and stories (updated after quality review)quality-review.md — Quality review report with all suggestions and decisionsjira-tasks.md — Final Jira-ready tasksspecifications/projects/<project-name>/task-baseline.md — Optional project-level continuity baseline that may be maintained for future workshops
Required Skills
Before starting, load and follow these skills in order:
fabrico-task-analysing - for business/context exploration, ambiguity resolution, and continuity baseline reviewfabrico-transcript-processing - for cleaning and structuring raw transcriptsfabrico-task-extracting - for identifying epics and user stories from all materialsfabrico-task-quality-reviewing - for analyzing extracted tasks for gaps, edge cases, and improvementsfabrico-jira-task-formatting - for formatting tasks per the benchmark template and managing Jira pushfabrico-codebase-analysing - for understanding the existing codebase when relevant
Workflow
Determine the entry point based on what the user provides:
If the user provides existing Jira issue keys or a project key instead of workshop materials, skip transcript processing and task extraction. Use the fabrico-jira-task-formatting Import Mode to fetch and convert existing tasks into jira-tasks.md. Then proceed to quality review (Step 5) and formatting.
Explore Mode branch: If the user explicitly wants exploration first, or the available materials are ambiguous enough that backlog extraction would be premature, create workshop-context-summary.md first. This mode is business/context discovery only; it does not create epics or stories for Jira unless the user explicitly asks to continue.
Standard workflow (workshop materials provided):
- Process transcript: If a raw transcript is provided, clean it using the
fabrico-transcript-processing skill. Remove small talk, structure by topics, extract decisions and action items. Save as cleaned-transcript.md.
- Analyze additional materials and baseline: Review Figma designs using the figma MCP server, read PDF documents using the pdf-reader MCP server, analyze the existing codebase using the
fabrico-codebase-analysing skill, review any other reference documents provided, and load the project baseline if specifications/projects/<project-name>/task-baseline.md already exists.
- Draft intent brief: Using the
fabrico-task-extracting skill, synthesize an intent-brief.md that captures goal, scope, exclusions, stakeholders, likely epics, baseline overlap, and open questions.
- Review Gate 0: Present the intent brief to the user for validation. Confirm scope, intent, and candidate epics before extraction. Iterate until the user approves.
- Extract tasks: Using the
fabrico-task-extracting skill, identify epics and user stories from all processed materials and the approved intent brief. Save as extracted-tasks.md.
- Review Gate 1: Present the extracted task list to the user for validation. Ask if any tasks were missed, should be split, merged, or removed. Iterate until the user approves.
- Quality review: Using the
fabrico-task-quality-reviewing skill, run Lite or Full analysis passes against the approved task list. Build the domain model, identify gaps, and produce structured suggestions. This step runs automatically after Gate 1 approval — do not ask the user whether to run it.
- Review Gate 1.5: Present all quality review suggestions to the user, grouped by epic and ordered by confidence. The user accepts or rejects each suggestion individually. Apply accepted suggestions to
extracted-tasks.md and save the quality review report as quality-review.md.
- Confirm updated tasks: After applying accepted suggestions, briefly summarize the changes made to
extracted-tasks.md (new stories added, criteria added, stories modified). If the user wants to review the full updated task list, present it. Proceed when the user confirms.
- Format for Jira: Using the
fabrico-jira-task-formatting skill, apply the benchmark template to format all tasks for Jira while preserving source traceability. Save as .
Important
- Output must be business-oriented — no technical implementation details beyond what was explicitly discussed in the workshop.
- Ask the user directly proactively whenever confidence is low about scope, priority, or intent.
- Both review gates are mandatory — no data is pushed to Jira without explicit user approval.
- Gate 0 is mandatory whenever an intent brief is created. The brief must be approved before extraction begins.
- The quality review step (Gate 1.5) runs automatically after Gate 1 approval. The user reviews and accepts/rejects individual suggestions, but does not need to opt-in to the review itself.
- The BA orchestrator may route transcript cleanup, analysis, extraction, quality review, and formatting to internal model-specialized BA workers, but all user-facing approval gates and final Jira actions still run through the
fabrico-business-analyst subagent.
- When working with imported Jira tasks, the quality review step still applies — it can identify gaps in existing backlogs just as with newly extracted tasks.
- After import or initial creation, individual task changes trigger a "Push to Jira now?" prompt. Batch pushes follow the standard Gate 2 approval.
- If exploration is requested, keep the output focused on business context and readiness for extraction rather than creating backlog items prematurely.
- If no transcript is provided (e.g., user provides structured notes or direct requirements), skip the transcript processing step and proceed directly to task extraction.
Follow the template structures and naming conventions from each skill strictly to ensure clarity and consistency.
