Doctor

doctor

Read-only audit. Never mutates the filesystem. Wraps bin/doctor.sh, which internally runs bin/retrofit.sh --report-only.

1. Resolve the profile

doctor.sh requires --profile <name>. The skill's job is to pick the right one without pestering the user:

1. Look for a .nyann/profile or equivalent profile hint in the repo.
2. If the repo's CLAUDE.md declares an active profile, use that.
3. If neither exists, ask the user which profile to audit against (default, nextjs-prototype, python-cli, or any user/team profile they've installed). Don't silently pick default — the audit is only meaningful against an intended baseline.

2. Invoke

bin/doctor.sh --target <cwd> --profile <name> [--json] [--scope <csv>]

--profile takes a bare profile name (e.g. python-cli, nextjs-prototype), not a filesystem path. The script resolves the name to the profile JSON internally.

Pass --json when the user says "machine-readable", "as JSON", "pipe this", or similar — otherwise emit the human-readable report.

Pass --scope <csv> when the user wants to inspect only a subset of the audit — e.g. "just check my docs", "are my hooks healthy". Accepts any of docs, hooks, branching, gitignore, editorconfig, github, history, all, comma-separated. When narrower than all, the rendered output gains a Scope: <csv> line and --persist is auto-disabled (a partial-scope health score would corrupt the trend series in memory/health.json).

3. Interpret the exit code

4. Sections in the report

The output has several blocks. When the user asks "what does each section mean?", explain in terms of the repo, not nyann internals:

• MISSING: files the profile expects but the repo lacks (e.g. no .husky/pre-commit when the profile declares husky hooks).
• MISCONFIGURED: files present but content doesn't match (e.g. a .husky/pre-commit exists but doesn't actually run the expected linter).
• NON-COMPLIANT HISTORY: last N commit subjects that don't match Conventional Commits. Informational — nyann never rewrites history.
• DOCUMENTATION: CLAUDE.md size vs budget, internal link resolution, MCP link reachability (when MCP connectors are available), orphan files under docs/ / memory/, and misplaced docs (files at non-canonical paths that could be reorganized via retrofit).
• GITHUB PROTECTION: branch protection per strategy, tag-protection rulesets (when .github.tag_protection_pattern is declared in the profile), CODEOWNERS-required gate (when a CODEOWNERS file exists or .github.require_code_owner_reviews=true), and repo-security settings (Dependabot, secret scanning, push protection, code scanning). Soft-skips when gh is missing or unauthenticated. Driven by bin/gh-integration.sh --check under the hood. Critical drift here bumps the exit code to 5; warn drift bumps it to 4.
• DOC STALENESS: doc files under docs/ whose correlated source paths have changed substantially since the doc itself was last touched. Heuristic-based (bin/docs-staleness.sh); thresholds configurable via the profile (documentation.staleness_threshold_*). Informational — never affects exit code.
• PUBLIC-DOC DRIFT: README/CONTRIBUTING/SECURITY/docs/*.md scanned for version-ref drift (semver older than latest tag), broken markdown link targets, missing npm run / make script references, and count-claim drift (opt-in per profile). Driven by bin/docs-drift-scan.sh. Critical/high findings escalate the exit code (mirrors GitHub protection); medium/low are advisory.
• IAC DRIFT: IaC source (*.tf, Chart.yaml, Pulumi*.yaml, *.tfvars, Ansible vars) scanned for committed secrets (critical), unpinned module refs / providers / deps (high), missing lockfiles and Helm appVersion lag (medium). Filesystem + git only — no terraform plan, no cloud calls. Driven by bin/iac-drift-scan.sh, gated per profile via iac.drift_check.{enabled, unpinned_refs, missing_lockfile, secrets_in_vars, version_lag}. Critical/high findings escalate the exit code (mirrors public-doc drift); medium/low are advisory. Silent on non-infra repos. Like public-doc drift, this is score-isolated — it shapes the exit code but not the numeric health score.

The protection block respects nyann's gh-best-effort invariant — it never prompts for credentials and never blocks the audit. When gh isn't reachable, the section reports skipped and contributes no drift to the exit code.

5. Surface health trend (when available)

After showing the audit report, check whether memory/health.json exists in the target repo. If it does:

1. Run bin/health-trend.sh --target <cwd> --last 10.
2. Show the sparkline and summary: "Health trend: ▃▄▅▆▇ — 72→85 over last 10 checks (↑ improving)."
3. If any category_deltas show worsening (delta < 0 in the breakdown), call them out: "⚠ missing got worse (−3 over the window)."
4. If the trend direction is down, suggest: "Score is declining — run /nyann:retrofit to address the drift."

If memory/health.json doesn't exist, skip silently — don't suggest creating it. The persist step happens automatically via doctor.sh.

6. What to do after

• User asks to fix drift → hand off to retrofit ("fix this repo's drift"). Do not attempt to fix anything from inside the doctor skill.
• User asks "why is this missing?" → read back the profile's expectation for that item; don't guess.
• User says "ignore warnings, they're false positives" → there's no silencing mechanism inside doctor itself. If it's a recurring false positive, the profile or the repo's .nyann-ignore-equivalent is the right lever (future work, not today).

When to hand off

• "Fix it" / "remediate" / "bring into compliance" → retrofit.
• "Why is this profile the active one?" → inspect-profile (if available) or read the profile JSON directly.
• "I want a different profile applied" → retrofit with the new profile name.