Agent skill

Paper From Zero

by yunshenwuchuxun in yunshenwuchuxun/latex-paper-skills

Route a fixed research topic into a rigorous paper-generation workflow.

MITAuto-check passedResearch & Science

Install Paper From Zero

skills CLI
$ npx skills add yunshenwuchuxun/latex-paper-skills --skill paper-from-zero -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install yunshenwuchuxun/latex-paper-skills paper-from-zero --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/yunshenwuchuxun/latex-paper-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/paper-from-zero .claude/skills/paper-from-zero && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
paper-from-zero
GitHub stars
267
Token cost
~1.5k tokens
SKILL.md length
659 words
Files
12 (incl. scripts, references, assets)
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Route a fixed research topic into a rigorous paper-generation workflow.

  • Works in 8 steps: Confirm the topic, constraints, and… → Actively search literature and build a… → Produce 3-5 candidate… → …
  • Tasks that involve Literature review
  • SKILL.md covers When to Use, When NOT to Use, Outputs and Workflow, plus 6 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Paper From Zero is an agent skill from yunshenwuchuxun/latex-paper-skills. Route a fixed research topic into a rigorous paper-generation workflow. Handles active literature search, innovation framing, contribution/evidence planning, and routes to either the review writer or empirical writer skill.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including scripts, reference files and assets (for example `assets/contribution-map-template.yaml`, `assets/outline-contract-template.md` and `assets/router-decision-template.md`).

It sits in Research & Science, covering Literature review and Performance reviews. The repository describes itself as: A modular skill-based framework for writing, revising, and managing LaTeX academic papers with AI assistance. The licence is MIT.

When your agent uses it

  • Tasks that involve Literature review
  • Tasks that involve Performance reviews

Example prompts

  • “/paper-from-zero”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Confirm the topic, constraints, and whether the user already has a preferred innovation.
  2. Actively search literature and build a compact literature map.
  3. Produce 3-5 candidate innovation/contribution framings unless the user already supplied one.
  4. Kill weak framings early: reject ideas that lack a clear gap, evidence path, or falsifiable claim.
  5. Build a contribution map
  6. Build an evidence matrix for every claim
  7. Produce an outline contract with section goals, citation quotas, and figure quotas.
  8. Route

What it can do on your machine

Read from SKILL.md and the folder at commit d0f1061. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Paper From Zero loads about 1.5k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 659 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from yunshenwuchuxun/latex-paper-skills at commit d0f1061, republished under its MIT licence (© yunshenwuchuxun). 659 words, ~1,513 tokens.

Download SKILL.mdSave it as .claude/skills/paper-from-zero/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
paper-from-zero
description
Route a fixed research topic into a rigorous paper-generation workflow. Handles active literature search, innovation framing, contribution/evidence planning, and routes to either the review writer or empirical writer skill.
metadata.short-description
Research-to-paper router for review and empirical papers

Paper-From-Zero

Use this skill when the user already has a topic/domain and wants a structured path from topic -> innovation framing -> evidence plan -> draft-ready paper workflow.

This skill is the front door of the paper stack:

  • It decides whether the work is best treated as a review or empirical paper.
  • It actively searches literature and frames the contribution.
  • It produces the handoff contract used by the downstream writer skill.

When to Use

  • The topic is known, but the paper structure and contribution are not yet pinned down.
  • The user wants the model to search for candidate innovation angles.
  • The user wants a rigorous pre-writing stage before draft generation.

When NOT to Use

  • The user already has a finished review outline and only wants review execution.
  • The user already has an experimental paper contract and only wants draft execution.
  • The task is non-academic or does not need citation-grounded writing.

Outputs

  • brief/topic-brief.md
  • brief/contribution-map.yaml
  • brief/evidence-matrix.csv
  • notes/innovation/ (innovation candidates + evidence links; recommended)
  • plan/outline-contract.md
  • plan/router-decision.md
  • A routing decision to one downstream writer:
    • ../arxiv-paper-writer/SKILL.md for review papers
    • ../empirical-paper-writer/SKILL.md for experimental papers

Workflow

  1. Confirm the topic, constraints, and whether the user already has a preferred innovation.
  2. Actively search literature and build a compact literature map.
  3. Produce 3-5 candidate innovation/contribution framings unless the user already supplied one.
  4. Kill weak framings early: reject ideas that lack a clear gap, evidence path, or falsifiable claim.
  5. Build a contribution map:
    • primary claim
    • secondary claims
    • non-goals / out-of-scope claims
    • risk factors / likely reviewer objections
  6. Build an evidence matrix for every claim:
    • required citations
    • required visuals/tables
    • required experiments (if any)
    • what may remain placeholder vs what must be verified before finalization
  7. Produce an outline contract with section goals, citation quotas, and figure quotas.
  8. Route:
    • review -> use ../arxiv-paper-writer/SKILL.md
    • empirical -> use ../empirical-paper-writer/SKILL.md

The following hooks integrate the breadth (Gemini) and depth (Claude) co-pilots at fixed points in the workflow. Hooks are optional but strongly recommended for research rigor.

#TriggerCallInputOutput consumed by
1After step 2 (literature initial screening)Gemini literature-maptopic + Key Terms from topic-briefCandidate papers and keyword clusters feed back into literature search; not written directly into artifacts.
2After step 5 (contribution-map initial draft)Claude claim-stress-testcontribution-map.yaml full textrisks and reviewer_objections feed back into contribution-map revision.
3After step 6 (evidence-matrix initial draft)Gemini evidence-matrix-gap-check OR Claude evidence-sufficiency-auditevidence-matrix.csv + claims listGap list or sufficiency assessment feeds back into evidence-matrix revision.
4Before step 8 (routing decision)Claude route-review-vs-empiricalcontribution-map + evidence-matrix summaryRouting recommendation + adversarial challenge written into router-decision.md.
Show full SKILL.md (239 more words)Show less

Hooks are non-blocking. If the target model is unavailable, the orchestrator decides the fallback. Candidates-Only constraint applies regardless of executor.

Hook 3 selection rule: If the average evidence rows per claim < 3, call Gemini evidence-matrix-gap-check first (breadth). If coverage appears sufficient, call Claude evidence-sufficiency-audit (depth). Both may be called sequentially.

Constraint: Collaboration outputs are inputs to artifact revision, not direct writes. All candidate entries must pass the Candidates-Only constraint defined in the co-pilot skills. validate_handoff.py does not check capsule state — it only validates final artifact completeness.

Routing Rules

  • Route to review when the deliverable is a survey, synthesis, taxonomy, benchmark-style review, or evidence-first overview.
  • Route to empirical when the deliverable makes a novel method/setting/evaluation claim that needs experimental validation.
  • If the topic contains both, prefer the paper’s primary contribution type.

Handoff Contract

Before routing, create the following artifacts in the target project folder:

  • brief/topic-brief.md: topic, scope, audience, constraints, venue/page targets
  • brief/contribution-map.yaml: claims, non-claims, novelty framing, risks
  • brief/evidence-matrix.csv: claim-to-evidence mapping
  • plan/outline-contract.md: section tree + section intent + citation/figure quotas
  • plan/router-decision.md: chosen mode and why

The downstream writer must consume these artifacts rather than re-guessing user intent.

Before routing, validate the handoff artifacts:

bash
python3 .codex/skills/paper-from-zero/validate_handoff.py --project-dir <paper_dir>

Strictness Rules

  • Do not invent novelty. Frame novelty as a hypothesis until grounded by evidence.
  • Do not skip literature search for “obvious” topics.
  • Do not allow claim language stronger than available evidence.
  • For empirical work, explicitly separate planned, placeholder, and verified results.

References to Read

  • references/architecture.md
  • references/innovation-framing.md
  • references/routing-policy.md

© yunshenwuchuxun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (scripts, references, assets) in .codex/skills/paper-from-zero of yunshenwuchuxun/latex-paper-skills.

  • SKILL.md
  • assets/contribution-map-template.yaml
  • assets/evidence-matrix-template.csv
  • assets/outline-contract-template.md
  • assets/router-decision-template.md
  • assets/topic-brief-template.md
  • references/architecture.md
  • references/handoff-contract.md
  • references/innovation-framing.md
  • references/routing-policy.md
  • scripts/route_and_invoke.py
  • validate_handoff.py

Open the folder on GitHubat commit d0f1061

Compare with similar skills

Paper From Zero next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Paper From Zero compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Paper From Zero this skillyunshenwuchuxun/latex-paper-skills267—~1.5kAutomated safety check: PassMIT
WorkworkLeoYeAI/openclaw-master-skills2.2k—~4kAutomated safety check: PassMIT
Academic Paperbrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~7.3kAutomated safety check: PassCustom licence
Academic Paper Writing PipelineImbad0202/academic-research-skills51k—~16kAutomated safety check: PassCustom licence
Econ Writehanlulong/econ-writing-skill6512 repos~14kAutomated safety check: PassMIT
Literature PDF OCR Library BuilderLigphiDonk/Oh-my--paper739—~1.1kAutomated safety check: PassMIT

Similar skills

  • Workwork

    LeoYeAI/openclaw-master-skills

    Academic review writer and formatting assistant for Chinese academic papers.

    2.2k GitHub stars~4k tokensUpdated 2 mo ago
    Research & ScienceAuto-check passed
  • Academic Paper

    brycewang-stanford/Auto-Empirical-Research-Skills

    Academic paper writing skill with 12-agent pipeline. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

    4.6k GitHub stars~7.3k tokensUpdated 5 days ago
    Documents & OfficeAuto-check passed
  • Academic Paper Writing Pipeline

    Imbad0202/academic-research-skills

    Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.

    51k GitHub stars~16k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Econ Write

    hanlulong/econ-writing-skill

    Expert economics paper writing assistant synthesizing advice from 50+ top guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Glaeser, Kremer, and other leading economists.

    651 GitHub starsUsed in 2 repos~14k tokens
    Research & ScienceAuto-check passed
  • Literature PDF OCR Library Builder

    LigphiDonk/Oh-my--paper

    Searches and downloads legally accessible academic PDFs, OCRs them to Markdown, and organizes the results into a traceable, AI-readable literature library.

    739 GitHub stars~1.1k tokensUpdated 5 mo ago
    Research & ScienceAuto-check passed
  • Academic Integrity Rewrite

    lin1111-1/academic-integrity-rewrite

    Revise Chinese or English academic writing for lower unnecessary textual overlap while preserving meaning, evidence, numbers, equations, terminology, and citations.

    102 GitHub stars~1.1k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

More from yunshenwuchuxun/latex-paper-skills

All 8 skills in this repo
  • Arxiv Paper Writer

    yunshenwuchuxun/latex-paper-skills

    Writes ML/AI review and survey papers for arXiv using the IEEEtran LaTeX template with verified BibTeX citations.

    267 GitHub stars~3.2k tokensUpdated 6 mo ago
    Auto-check passed
  • Collaborating With Claude

    yunshenwuchuxun/latex-paper-skills

    Use the Claude Code CLI as a depth-analysis co-pilot for paper-from-zero.

    267 GitHub stars~1.2k tokensUpdated 6 mo ago
    Auto-check passed
  • Collaborating With Gemini

    yunshenwuchuxun/latex-paper-skills

    Use the Gemini CLI as a breadth-exploration co-pilot for paper-from-zero.

    267 GitHub stars~1.1k tokensUpdated 6 mo ago
    Auto-check passed
  • Results Backfill

    yunshenwuchuxun/latex-paper-skills

    Back-fill verified experiment results into an existing empirical paper draft.

    267 GitHub stars~1.7k tokensUpdated 6 mo ago
    Auto-check passed
  • Empirical Paper Writer

    yunshenwuchuxun/latex-paper-skills

    Draft IEEE-style empirical ML/AI papers from a structured research contract.

    267 GitHub stars~5.3k tokensUpdated 6 mo ago
    Auto-check passed
  • Check Collaborators

    yunshenwuchuxun/latex-paper-skills

    Verify that Gemini CLI and Claude Code CLI are installed, authenticated, and API-reachable before starting collaboration workflows.

    267 GitHub stars~1.4k tokensUpdated 6 mo ago
    Auto-check passed

Questions about Paper From Zero

What does Paper From Zero do?

Route a fixed research topic into a rigorous paper-generation workflow. Paper From Zero is an agent skill from yunshenwuchuxun/latex-paper-skills. Route a fixed research topic into a rigorous paper-generation workflow.

When should I use Paper From Zero?

Paper From Zero fits situations like: tasks that involve Literature review; tasks that involve Performance reviews.

How do I install Paper From Zero in Claude Code?

Run `npx skills add yunshenwuchuxun/latex-paper-skills --skill paper-from-zero -a claude-code`. Or copy the skill folder (.codex/skills/paper-from-zero in yunshenwuchuxun/latex-paper-skills) into .claude/skills/paper-from-zero in your project. Claude Code loads it when a task matches its description.

How do I install Paper From Zero in Codex?

Run `npx skills add yunshenwuchuxun/latex-paper-skills --skill paper-from-zero -a codex`. Or copy the skill folder (.codex/skills/paper-from-zero in yunshenwuchuxun/latex-paper-skills) into .agents/skills/paper-from-zero in your project. Codex loads it when a task matches its description.

Can I use Paper From Zero in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yunshenwuchuxun/latex-paper-skills --skill paper-from-zero -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/paper-from-zero, .gemini/skills/paper-from-zero, .github/skills/paper-from-zero and .opencode/skills/paper-from-zero in your project.

What does Paper From Zero need to run?

Going by SKILL.md and its folder, Paper From Zero needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Paper From Zero access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Paper From Zero safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Paper From Zero use?

Paper From Zero is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Paper From Zero use?

About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Paper From Zero?

Skills that share tags, products or a category with Paper From Zero: Workwork (LeoYeAI/openclaw-master-skills, 2.2k stars), Academic Paper (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars), Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars) and Econ Write (hanlulong/econ-writing-skill, 651 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Paper From Zero?

yunshenwuchuxun (a GitHub user) maintains it in yunshenwuchuxun/latex-paper-skills, which has 267 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on March 25, 2026.

Source: yunshenwuchuxun/latex-paper-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.