← ClaudeAtlas

spec-drift-auditlisted

Audits every spec under spec/<topic>/<slug>/ against the repository implementation (source code, config, workflows, docs) and produces a traceable audit artifact per spec/project/spec-drift-audit/. Invoke when the user asks to "run the quarterly spec-drift audit", "check spec versus implementation", "spec drift reconciliation", "audit all specs against the repo", "find spec vs code drift", "open the next quarterly audit", or when a spec changes and requires a matching partial audit. Also handles equivalent German-language requests. Do NOT use for continuous CI health checks (use workflow-health-triage), single-spec readiness review (use spec-readiness-reviewer agent), or feature-level code drift on new features (use feature-consistency-reviewer agent within feature-decompose scope). Supports resume on re-invocation per `spec/claude/resumable-work/`.
nolte/claude-shared · ★ 0 · AI & Automation · score 76
Install: claude install-skill nolte/claude-shared
# Spec Drift Audit Operationalises `spec/project/spec-drift-audit/<canonical_language>.md` — reconciles every in-scope spec's Requirements and Acceptance Criteria against the actual repository state, persists the result as a dated artifact, and drives findings to a documented decision. The audit artifact is the deliverable; this skill is the procedure that creates, updates, and closes it. ## Why this is a skill, not an agent - **Mid-flow interactivity** — the user decides per finding: adjust the implementation, adjust the spec, or flag as an Open Question. An agent's fire-and-forget contract loses that deliberation loop. - **Persistent on-disk output** — the audit artifact under `.audits/spec-drift/YYYY-Q<n>.md` (or a GitHub issue) must survive past the current turn and be worked off incrementally; skills own persistent artifacts, agents return ephemeral reports. - **Orchestration role** — the audit dispatches `project-structure-apply` and `vocab-drift-audit` as partial auditors in the same session; the skill-orchestrates-agent-executes pattern defaults the orchestrator to skill form. - Counter-dimension considered: *context-window load* from reading all specs plus their implementation surfaces could bias toward an agent, but the audit is inherently interactive and scoped per cycle — the user controls which specs are in scope and confirms each finding disposition. Inline execution in the skill form wins. ## German trigger phrases This skill also triggers on equivalent Ge