nauro-adoptlisted

Seeds Nauro's project store from an existing repo. Use after `nauro adopt` has run locally. On filesystem-capable surfaces, reads docs (README, manifests, ADRs, Memory-Bank) for rationale and inspects code, config, tests, lockfiles, and recent git history for evidence, then surfaces targeted probes that turn evidence into rationale. On chat surfaces, operates on pasted content against an already-adopted project.
Nauro-AI/nauro · ★ 6 · AI & Automation · score 76

Install: claude install-skill Nauro-AI/nauro

# Nauro adopt skill The agent helps the user seed Nauro with context from the current repo. Before this skill runs, the user has run `nauro adopt` from the repo root, which created the project, wired MCP across surfaces, and installed this skill into the agent's surface directory. The agent's job here is to seed the Nauro store via MCP write tools: docs supply the rationale for documented decisions, code and config and tests and manifests and recent git history supply evidence, and the user supplies the "why" via targeted probes when only evidence is present. Do not invent rationale. Record only what was actually decided, with the reasoning that supports it. ## Surface modes The agent's behaviour depends on whether the surface can read the repo directly. - **Filesystem-capable surfaces** (Claude Code, Cursor, Codex CLI). The agent runs Step 0 and Steps 1–11 in full. Step 0 is an optional rapid first pass that files only the decisions carrying two verifiable citations; Docs are read for rationale in Step 3; code, config, tests, manifests, and recent git history are inspected for evidence in Step 4; targeted probes in Step 6b turn evidence into rationale by asking the user. - **Chat surfaces** (Claude.ai, Perplexity). The agent has no shell. It operates only on content the user pastes into the chat (Step 3b), and only against an already-adopted project (verified in Step 3b). Step 0 is filesystem-only and is skipped on chat surfaces, exactly as Steps 1, 2, and 4 are; the Ste