Research Paper Figure Skill Factory
Spin up lawful, corpus-backed reusable skills that produce publication-quality research-paper figures with a gated multi-step image workflow.
Overview
research-paper-figure-skill-factory is an agent skill most often used in Build (also Validate prototype, Idea research) that factories reusable paper-figure skills from lawful corpus evidence with a gated candidate-board
Install
npx skills add https://github.com/c-narcissus/research-paper-figure-skill-factory --skill SKILL.mdWhat is this skill?
- Specialized-skill-first factory: build, patch, and package paper-figure skills from lawful literature or corpus evidence
- Full-feasible local PDF coverage where available, with target-paper candidate vs final image isolation
- Startup-plan-only first replies plus mandatory first-round diverse candidate board before final prompts
- P6b/P6c paper-local best-practice optimization after the candidate board
- Image-embedded visual-structure explanation and non-target concept/modeling examples for abstract layout choices
- Mandatory first-round diverse candidate board before final prompt construction
- P6b/P6c paper-local best-practice optimization step in the figure workflow
Adoption & trust: 43 GitHub stars.
What problem does it solve?
You need publication figures tied to real papers and local PDFs, but generic image skills skip corpus coverage, candidate isolation, and repeatable specialized workflows.
Who is it for?
Grad students, indie researchers, or ML engineers standardizing multi-panel paper figures as agent skills with PDF-grounded evidence and strict render gates.
Skip if: Quick social graphics, slides without citations, or teams that cannot use lawful corpora or hosted image APIs.
When should I use this skill?
The user wants a research-paper figure Skill Factory: build, patch, package, or use reusable specialized paper-figure-making skills from lawful literature/corpus evidence.
What do I get? / Deliverables
You get packaged specialized figure skills with plan-first replies, isolated candidate/final assets, and optimized final prompts ready to invoke on target papers.
- Packaged specialized paper-figure SKILL.md with gated workflow and state footers
- Candidate board outputs isolated from final figure assets
- Optimized final render prompts after P6b/P6c review
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is build/agent-tooling because the factory’s core job is authoring and packaging specialized agent skills—not one-off chat images. agent-tooling fits meta skill factories that patch, package, and wire procedural SKILL.md workflows for other agents.
Where it fits
Survey target-paper figure subtypes from a local PDF corpus before committing to a specialized skill template.
Run the mandatory diverse candidate board on one section to see if P6b/P6c rules improve readability before final assets.
Patch and package a figure skill with startup-plan-only gates and Codex imagegen-first rendering for your lab repo.
Attach image-embedded visual-structure explanations so co-authors understand panel layout without separate legend docs.
How it compares
Use this skill factory for procedural, corpus-backed figure pipelines—not a single-shot generative media prompt.
Common Questions / FAQ
Who is research-paper-figure-skill-factory for?
Solo and indie builders publishing research who want agent skills that turn literature evidence into repeatable figure workflows with audited render steps.
When should I use research-paper-figure-skill-factory?
During Idea research when scoping figure types from papers, Validate prototype when testing candidate boards on a target PDF, and Build agent-tooling when packaging or patching specialized figure skills for Claude Code, Cursor, or Codex.
Is research-paper-figure-skill-factory safe to install?
Review the Security Audits panel on this Prism page for install risk, file permissions, and network exposure before pointing it at local PDFs or image APIs.
SKILL.md
READMESKILL.md - Research Paper Figure Skill Factory
Use when the user wants a research-paper figure Skill Factory: build, patch, package, or use reusable specialized paper-figure-making skills from lawful literature/corpus evidence. Generated skills must use a specialized-skill-first workflow, full-feasible local PDF coverage where available, startup-plan-only first replies, target-paper candidate/final image isolation, mandatory image-embedded visual-structure explanation, mandatory non-target concept/modeling example display for abstract visual decisions, saved subtype/style illustration atlases, ChatGPT web Create image / ChatGPT Images 2.0 rendering, Codex $imagegen-first rendering, sample-image transfer rules, all-step/current-position state footers, and a mandatory first-round diverse candidate board followed by P6b/P6c paper-local best-practice optimization before final prompt construction. # research-paper-figure-skill-factory { "name": "research-paper-figure-skill-factory", "description": "Use when the user wants a research-paper figure Skill Factory: build, patch, package, or use reusable specialized paper-figure-making skills from lawful literature/corpus evidence. Generated skills must use a specialized-skill-first workflow, full-feasible local PDF coverage where available, startup-plan-only first replies, target-paper candidate/final image isolation, mandatory image-embedded visual-structure explanation, mandatory non-target concept/modeling example display for abstract visual decisions, saved subtype/style illustration atlases, ChatGPT web Create image / ChatGPT Images 2.0 rendering, Codex $imagegen-first rendering, sample-image transfer rules, all-step/current-position state footers, and a mandatory first-round diverse candidate board followed by P6b/P6c paper-local best-practice optimization before final prompt construction." }