9 added, 6 removed. Audit A to A.
---
name: score
- description: Recompute and display the two scores (Search SEO + AI Visibility) from the most recent audit's findings, without re-crawling. Use to re-show or refresh the scores after an audit, or to score a saved findings JSON file.
- argument-hint: "[findings.json]"
+ description: Recompute and display the two scores (Search SEO + AI Visibility) from a persisted audit run, without re-crawling. Use to re-show or refresh the scores after an audit, to score a specific run directory or host, or to score a saved findings JSON file.
+ argument-hint: "[findings.json | run-dir | latest[:host]]"
allowed-tools: Read, Bash
---
# /claude-seo-ai:score
- Recompute and show the two 0–100 scores from the latest audit's findings by re-running the **seo-score** skill (which uses `scripts/score.mjs` for a reproducible number).
+ Recompute and show the two 0–100 scores by running the **seo-score** skill, which uses `scripts/score.mjs` for a reproducible number. Runs live under `${CLAUDE_PLUGIN_DATA}/runs/<host>/<run-id>/`; `latest` resolves to the most recent run. <!-- reconcile-flags-v0.2 -->
- - If a findings JSON path is given in `$ARGUMENTS`, score that file: `node scripts/score.mjs --findings <path>`.
- - Otherwise use the findings from the most recent audit this session. If no audit has run yet, tell the user to run `/claude-seo-ai:audit <url>` first.
+ - No argument (default): `node "${CLAUDE_PLUGIN_ROOT}/scripts/score.mjs" --run latest` <!-- reconcile-flags-v0.2 -->
+ - `latest:<host>` → `node "${CLAUDE_PLUGIN_ROOT}/scripts/score.mjs" --run latest:<host>` <!-- reconcile-flags-v0.2 -->
+ - A run directory → `node "${CLAUDE_PLUGIN_ROOT}/scripts/score.mjs" --run <run-dir>` <!-- reconcile-flags-v0.2 -->
+ - A findings JSON path → `node "${CLAUDE_PLUGIN_ROOT}/scripts/score.mjs" --findings <path>` (pass `--vertical a,b --multilingual` when the file has no run context). <!-- reconcile-flags-v0.2 -->
+ - If the script reports that no run exists, tell the user to run `/claude-seo-ai:audit <url>` first — never score from memory.
- Show both scores with bands, the per-category breakdown, any severity-gating cap, and the `needs_api` count. Two scores, never blended.
+ Show both scores with bands, the per-category breakdown, any severity-gating cap (`cap_reasons`), the `unscored` state when no category is active, and the `needs_api` / `manual_review` / `dropped` counts. Two scores, never blended.