figure-text-alignment

A text-only review that compares figure captions with the sentences in a manuscript that refer to those figures. It checks whether the written descriptions match, without looking at the actual images.

In plain words
What is it for?
Use it to review figure-to-text references in research papers and report aligned, partly aligned, mismatched, or undeterminable caption and body-text pairs.
Why use it?
It can reveal references that do not match captions, missing or extra figures, panel mix-ups, and unclear axis or unit references. It does not edit the manuscript or judge what an image actually shows.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/seandavi/scriptorium/figure-text-alignment
Any agent
npx skills add seandavi/scriptorium --skill figure-text-alignment
Clone the repo
git clone --depth 1 https://github.com/seandavi/scriptorium

Made for: Claude Code, Codex.

Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,933 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00111 $0.03933
Opus 5 $0.00056 $0.01966
Sonnet 5 $0.00022 $0.00787
Haiku 4.5 $0.00011 $0.00393

Measured 2d ago against content hash ebb0335a9654, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

figure-text-alignment scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/figure-text-alignment/SKILL.md · 358 lines

How it starts

The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Figure-text alignment (text-only)

You are running scriptorium's figure-text-alignment skill — the text-only subset. Your job is to assess whether each figure's caption and the body-text sentences that reference that figure are talking about the same thing. You are a critique skill, not a generation skill, and you are explicitly not reading figure images. The multimodal counterpart (sub-skill B) is deferred — see What this skill did NOT check below and the project roadmap.

Critical constraints — read before doing anything else

  1. Do not read or interpret figure images. This skill operates on manuscript prose only: the figure caption text and the body-text sentences referencing each figure. Any claim that requires looking at axes, error bars, panel content, or rendered data points belongs to sub-skill B (multimodal) and is out of scope. If asked to "check whether the figure actually shows X", refuse cleanly and name the text-only scope.
  2. Never modify the manuscript. This skill emits a markdown report. Edits to captions or body-text references are the author's job based on the report.
  3. Never invent figure content. If a caption is too sparse to compare against a body-text reference, the alignment is cannot determine, not a guess about what the figure probably shows. Inventing a description of figure content the caption did not state is the figure-side analogue of citation hallucination ([[hallucination-in-llm-citations]] reasoning generalises here).
  4. Output is gradient, not binary. Use aligned / partially aligned / misaligned / cannot determine — the same gradient discipline citation-audit uses. Forcing yes/no answers loses load-bearing nuance, especially for the "the caption and the body text overlap but disagree on one panel" cases which are the most common real-world finding.
  5. Pattern flags are facts, not verdicts. An orphan figure or a phantom figure reference is a structural fact about the manuscript. Report the fact; do not infer authorial intent (was a figure removed mid-revision? did a reference get edited away?). The author knows; the skill does not.

Read the full file on GitHub · 358 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 358 lines · 111 tokens per session scan A ebb0335a9654

Subscribe to this mod's changes

figure-text-alignment is a skill published in the GitHub repository seandavi/scriptorium (3 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 3,933 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

academic-paper-review

Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation.…

bytedance/deer-flow · 95 tokens

agent-matrix-optimizer

Agent skill for matrix-optimizer - invoke with $agent-matrix-optimizer.

ruvnet/ruflo · 21 tokens

weather-fetcher

Instructions for fetching current weather temperature data for Dubai, UAE from Open-Meteo API.

shanraisshan/claude-code-best-practice · 21 tokens

scienceworld-ambiguous-action-resolution

Use when the ScienceWorld environment returns an "Ambiguous request" prompt with a numbered list of identical action options. This skill resolves the disambiguation by selecting the lowest available number (typically 0) to proceed, ensuring task progression when multiple identical object instances exist and the system…

zjunlp/SkillNet · 73 tokens

scienceworld-animal-identifier

Use when the agent needs to locate, identify, and focus on a specific animal or biological entity in the ScienceWorld environment. This skill handles tasks involving animal comparison, examination, or interaction (such as determining lifespan extremes) by navigating to the correct location with "teleport to"…

zjunlp/SkillNet · 83 tokens

skillpack-creator

Create a reusable SkillPack from a successful completed task. Use when the user wants to convert a one-off research, coding, analysis, or content workflow into a distributable local SkillPack with skillpack.json, local skills under skills/, starter prompts, start scripts, and an optional zip package.

CreminiAI/skillpack · 67 tokens