blindspotlisted

Shklovsky-inspired peripheral-vision audit of a SINGLE figure or table in a quantitative-marketing paper. Forces a four-quadrant grid — Unexplained Feature, Convenient Absence, Unasked Question, Unexploited Strength — to surface what the author has stopped seeing in a coefficient plot, DiD event-study, conjoint utility plot, predicted-engagement curve, GAN attribute-axis image grid, SAE feature heatmap, or livestream time-series. Use when the user says "/blindspot", "audit this figure", "blindspot check on Figure 3", "what am I missing in this plot", "what's a hostile referee going to ask about this figure", "peripheral vision on Table 4", or "make the stone stony again". Operates at the figure / table level only — manuscript-level adversarial review is `/seven-pass-review`; numeric-claim verification is `/audit-reproducibility`; correctness of the code that built the figure is `/review-paper-code`. They compose — run `/blindspot` early on a fresh figure, then `/seven-pass-review` once the surrounding draft i
ericluo04/claude-academic-workflow · ★ 3 · AI & Automation · score 72

Install: claude install-skill ericluo04/claude-academic-workflow

# Blindspot A single-figure peripheral-vision audit. After weeks on a paper, the main finding collapses attention onto one feature of a plot and everything else — the spike at t=1, the missing subgroup, the heterogeneity richer than the average, the identification strength the paper undersells — goes invisible. This skill forces you to see them again. > Shklovsky's frame: art exists to restore perception, to make the stone stony again. `/blindspot` does that for one figure or table at a time. **Position vs. neighbors.** `/blindspot` is figure-level. `/seven-pass-review` is manuscript-level (seven parallel reviewers across abstract/intro/methods/results/robustness/prose/citations). `/audit-reproducibility` cross-checks numbers against code outputs. `/review-paper-code` audits the script that built the figure. They compose; they do not substitute for each other. If the user asks for a "deep review of the paper" or "review my draft," that is `/seven-pass-review`, not this skill. ## When to use - A new figure or table has just appeared in an analysis and the prose around it is not yet written. - Before circulating a draft to coauthors — sanity-check the headline figure. - Before a seminar, when the first question will obviously be about one specific panel. - During R&R, on any figure a referee complained about, to find what the response letter has to address before drafting prose with `/draft` or `/referee-response`. ## Inputs - `$0` — path to ONE figure or table. Accepted