Narrative Quality Auditor

Narrative Quality Auditor

Audit narrative truth, message-system coherence, or measured effectiveness as separate TALE profiles. There is no v18 overall composite: truth cannot be averaged away by coherence, and coherence cannot stand in for effectiveness evidence.

When This Must Trigger

• The user asks whether positioning/differentiation is defensible.
• A flagship surface needs a pre-publish canon/message-match gate.
• A message experiment or resonance claim needs evidence-integrity review.
• A full narrative review is requested; run linked profiles rather than one blended score.

Quick Start

Run TALE truth on canon v7 against named alternatives and approved claims.
Run TALE system on homepage/pricing/deck against canon v7 before release.
Run a full review as three linked profile results; do not compute an overall score.

Skill Contract

Reads: one canon/surface set or message experiment plus current narrative/claims truth. Writes: only permissioned v3 artifacts. Done when: each requested profile is independently complete or its Unknowns are explicit, with no canon, claims, or surface mutation.

narrative-registry owns canon/version state and offer-claims-registry owns claims. This skill judges; authoring/fixing belongs to Trace/Architect/Land skills.

Data Sources

Instructions

Runtime Reads

• ../../../references/auditor-runbook.md
• ../../../references/scoring-semantics.md
• ../../../references/tale-benchmark.md
• ../../../references/runtime-invocation.md
• references/auditor-runtime.md

Runtime and Setup

Read ../../../references/auditor-runbook.md, scoring-semantics.md, tale-benchmark.md, and the TALE catalog entry. Standalone installs use bundled immutable references/auditor-runtime.md; never fetch mutable main. Before deterministic calls, follow runtime-invocation.md, resolve AARON_SKILLS_ROOT="${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}", and require the scorer, validator, and typed catalogs. If unavailable, still collect the selected profile's typed observations and Unknowns, but return score_state: NOT_SCORED / score_confidence: not_scored with no gate verdict or persistent artifact; runtime absence blocks deterministic scoring, not the observation pass.

Declare target, profile/mode, brand scope, market, audience, canon version, observation date, and evidence window.

Profile Procedure

• truth: score T1–T10 for material differentiation and factual grounding.
• system: score A1–A10 and L1–L10 for canon coherence and landing consistency.
• effectiveness: score E1–E10 for one experiment/locked panel/date.
• full: run the three profiles independently and keep three artifacts/results. Aggregate release language conservatively: any BLOCK → block; otherwise any UNDECIDED → undecided; otherwise any FIX → fix; all SHIP → ship. Never average scores.

For a flagship pre-publish gate, always execute the system profile procedure and require a compatible current truth result. If no compatible truth result exists, run truth separately when its evidence is available; otherwise record the truth prerequisite as Unknown while still rendering the requested system-profile result. A missing scorer/runtime changes that result to NOT_SCORED/UNDECIDED; it does not justify skipping the profile. Run effectiveness separately only when the user requests it or the surface makes an effectiveness claim.

Every observed state needs source/date/type/confidence. A missing canon is Unknown, not N/A. A2/A4/A8 are conditional: three pillars, a change arc, and fixed boilerplate lengths are patterns only when deliberately chosen. Run the typed scorer per profile.

Verify profile-relevant vetoes: TALE-T1 false/contradictory/unsubstantiated material differentiation, TALE-A1 demonstrated canon contradiction, TALE-L1 material flagship/canon contradiction, and TALE-E1 unsupported effectiveness claim or proxy-as-measured.