musicofhel

Capture mirror bundles from OpenObserve — health, schemas, alerts, functions, traces, supplementary data, config chains, screenshots, and DOM.

Full end-to-end pipeline — collect all mirror data (8 steps), run all analysis agents, produce grounding documents.

Run multi-agent analysis pipeline on collected mirror data — baseline, 3 per-dashboard analysts (structure, data, UX), and synthesizer.

Capture mirror bundles from OpenObserve dashboards — screenshots, DOM text, API responses, config chains, layout metrics, alerts, traces, functions, health.

Full end-to-end pipeline — collect mirror data, run all analysis agents, produce grounding documents.

Run a software quality audit — six signals (reliability, speed, clarity, efficacy, efficiency, beauty), seven adversarial execution passes, measurable thresholds, code-level smell greps, and a papercut checklist. Use for quality audits, polish passes, papercut hunts, UX reviews, pre-launch checks, or when asked to make software feel higher quality.

Build an "Intent Layer" for a codebase — walk the repo, chunk at semantic boundaries, and produce hierarchical, token-efficient context bundles ("Intent Nodes") written into CLAUDE.md / AGENTS.md files so any AI agent gets deep codebase understanding without parsing raw source. Use on large/multi-service codebases (>~1M tokens / 50k–100k LOC) or when agents keep re-reading the same files to rebuild context. Reimplements the method behind Intent Systems' Intent Layer (intent-systems.com/intent-layer) — it is not the commercial product.