Risco Project Harness

A workspace orchestrator that audits a project root, proposes a concrete migration plan, and — only with explicit user consent — scaffolds two canonical layers:

• 01-TOOLS/<PROVIDER>/ — operational tooling, one folder per external provider, co-locating credentials (.env) with the scripts that consume them. Each tool ships a working probar_conexion against the real API.
• 02-DOCS/ — LLM wiki (raw/ + wiki/ + wiki/index.md + wiki/log.md + wiki/gaps.md + wiki/scores.json) following the Karpathy pattern, fully embedded in this skill. The protocol lives at references/wiki-protocol.md with templates at references/wiki-*.md. The wiki self-improves continuously: every Ingest and Query triggers a Maintenance Pass (deterministic lint, score recomputation, gap detection, See Also sweep), and every N interactions a Micro-Improve runs (rewrite 1 low-scoring article, fill 1 gap, preserving old versions in _archive/). Deep Improve runs on explicit request or via scheduled cron. No external skill needed.

Also generates root CLAUDE.md and AGENTS.md, and migrates legacy XX-* numbered folders into the canonical layout.

Core principle

Detection with interactive confirmation. Never speculative tools. Never destructive without explicit consent.

The skill proposes, the user confirms, the skill executes. Every destructive operation (deleting a legacy folder, merging into an existing CLAUDE.md) requires explicit consent quoted back from the user, not inferred.

When to use