integrity-auditor
Use when the user wants a paper audited for integrity issues — image misuse, numerical anomalies, logical gaps — and needs a reviewable evidence report. Works on external papers (PDF / DOI / arXiv) and on outputs from a local paper-writer run. Single-stage skill.
Profile →npx skills add ai4s-research/ai4s-skills --skill integrity-auditor --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Integrity Auditor ## Overview Paper-integrity audit package. **Single stage, full quality from the start.** The agent reads each reference, then carries out three evidence tracks (image / numerical / logical) and produces a structured `audit_report.md` with Level 1–4 graded findings. This skill ships no LLM SDK — it is the skill instructions, references, templates, and single-purpose `forensics_tools/` only. The substantive work is decomposed into reference playbooks under `references/`: | Reference | Topic | |---|---| | `references/00-incremental-execution.md` | how to do this without losing work: batches, persistence, resume — **read first** | | `references/01-image-evidence.md` | image evidence: panel split, dup detection, rotate/flip alignment, Western-blot continuity | | `references/02-numerical-evidence.md` | numerical evidence: n-consistency, mean/SD/SEM recompute, P-value sanity, decimal trail, Benford with caveats, deterministic-column-pair and last-digit chi-square sweepers, variance-reporting consistency | | `references/02a-supplement-acquisition.md` | publisher CDN routes: how to get hi-res figures and source-data XLSXs even when the article PDF is paywalled | | `refe
- Overview
- When to Use
- When NOT to Use
- Workflow
- Step 1 — Identify the input and set up the run
- Step 2 — Gather materials into the run
- Step 3 — Run the three audit tracks (REQUIRED — this is the whole job)
- Step 4 — Deliver
- Cross-skill data flow (path convention)
- Important rules
For local-slug mode, set SLUG to the existing paper-writer slug directly. mkdir -p "$RUN/findings/image" "$RUN/findings/numerical" "$RUN/findings/logical" ln -sfn "$TS" "output/integrity-auditor/$SLUG/latest" Text (every numeric claim, caption, figure reference will be greppable later) pdftotext -layout "$PDF" "$RUN/paper.txt" Panels (one .png / .ppm per embedded raster image) mkdir -p "$RUN/panels" pdfimages -all "$PDF" "$RUN/panels/page" Fallback for vector-figure papers (e.g., paper-writer outputs): pdfimages only extracts embedded raster images; a paper built from matplotlib
What does the integrity-auditor skill do?
Use when the user wants a paper audited for integrity issues — image misuse, numerical anomalies, logical gaps — and needs a reviewable evidence report. Works on external papers (PDF / DOI / arXiv) and on outputs from a local paper-writer run. Single-stage skill.
How do I install it?
Run `npx skills add ai4s-research/ai4s-skills --skill integrity-auditor --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From ai4s-research/ai4s-skills, a repository with 163 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.