
Golden path /see — refresh stale score snapshots and identify canvases needing MER capture.
Cognition orchestrator — analyze canvases, distill fears via /distill subagent, run gap analysis, optional cross-user synthesis.
Batch scan canvases for GAP sections, deduplicate, route to correct repos, draft issue bodies, and file confirmed issues.
Validate gap hypotheses by manually simulating features for individual users and measuring commitment, not satisfaction.
Analyze a user canvas and distill structured fears, steering targets, and synthesis features into a cognition sidecar file.
Create GitHub/Linear issues from gap analysis reports with proper taxonomy labels. Use when you need to file a gap as a trackable issue.
RLM-isolated follow-up generation: orchestrator + per-user subagent architecture where cross-user contamination is architecturally impossible.
Golden path /grow — confirm proposed matches, classify evidence, update confidence, run decay, surface growth changes. Full L4 backpropagation orchestrator.
Bulk convert legacy user research profiles to UTC (User Truth Canvas) format. Use when migrating existing research from grimoires/pub/research/users/ to laboratory.
Capture user feedback as hypothesis-first research using Level 3 diagnostic. Forms theories (not conclusions) from quotes.
Re-validate an artifact and update its confidence inputs. Routes to appropriate re-validation skill based on artifact type.
# /snapshot — MiDi Experience Record (MER) Capture Capture a point-in-time MER for a wallet. Produces a 4-layer snapshot: data state, visual screenshot, user perception, and decision context. ## Usage ``` /snapshot <wallet-or-alias> /snapshot xabbu --trigger feedback /snapshot xabbu --data-only /snapshot --cohort /snapshot --cohort --diff MER-2026-001 ``` ## Arguments | Argument | Description | Required | |----------|-------------|----------| | `wallet-or-alias` | Wallet address or alias fr
Compare user expectations (UTCs) with code reality to identify gaps. Use when you need to understand discrepancies between what users expect and what code actually does.
Parallel multi-user processing using Claude Code native teams. Leader spawns workers per user, each runs /ingest-dm, leader aggregates for cross-canvas patterns.
Automated end-to-end feedback pipeline that pulls new Supabase entries, enriches, classifies, routes to canvases, and generates a synthesis report.
Show what changed since last validation for a specific artifact. Computes confidence without writing to frontmatter.
Scan all artifacts for confidence metadata and report staleness using pure derived scoring.
Read agent interaction logs across packs and detect operational patterns. Emits state-transition FeedbackEvents for degradation/recovery.
Single-user conversation import that creates an enriched canvas scaffold from a DM export.
Diagnostic-first user research for support conversations and feedback analysis. Reaches Level 3 (user goal) before investigating or fixing. Applies The Mom Test methodology to extract product insights from bug reports and feature requests.
List user canvases and shape common patterns into journey definitions. Use when consolidating user research into testable user flows.
Golden path /speak — generate RLM-isolated follow-ups with chronicle temporal context injection.
Golden path /listen — ingest all new signals: chronicle releases, Supabase feedback, DM exports, growth matches.
Golden path /shape — consolidate journey patterns across canvases and file gap issues.