Gap Analysis

Multi-document engagement scoping against a platform codebase. Turns a folder of client materials (transcripts, spec docs, requirement dumps) into an evidence-backed Epic/Story tree where every story carries a grounded verdict and an atomic-commit effort, then derives a client-facing summary + prioritized backlog. The engine's trust model is structural, not prose: subagents investigate, but every verdict is re-run by a deterministic gate against a validated, just-freshened local checkout of the platform — a subagent's claim is never written to the tree unverified.

Arguments

• {input} (required) — a directory of client docs (Phase 1), or the path to an existing gap-analysis MD (Phases 2/3 and resumed runs).
• --phase <1|2|3> (optional) — force a phase; otherwise inferred from the MD's phase: frontmatter.
• --project <slug> (optional) — kebab-case project slug driving output filenames; asked for when unclear.

Step 0 — Load config and context

Load .ai/agentic.config.json using the standard config-loading snippet from the om-setup-agent-pipeline skill. If the config or the tracker descriptor is missing, do not stop — run the om-setup-agent-pipeline skill now to create them (interactively when a user is present, with --defaults when running unattended), then reload the config and continue. The snippet resolves TRACKER and TRACKER_FILE=".ai/trackers/${TRACKER}.md". On top of it, this skill reads its own platform section (all keys via jq -r '.platform.<key> // <default>'):