Agent skill · Design & Presentation

meta-paper-write

Use this meta-skill instead of answering directly when the current user asks to draft, repair, compile, or produce an academic/research paper or LaTeX manuscript. It uses multi-skill orchestration for manuscript workflows that need source search, citation planning, experiment or figure/table placeholders, drafting, length checks, citation integrity, and LaTeX/PDF compilation. Ordinary paper requests use a compact draft path; explicit full/PDF/long-form requests use the full manuscript path. Do not use it for web research reports, slide decks, document decisions, or generic plotting.

opensquilla6,385★ · +160/wk · 1 repos on radarProfile →
claude-codeApache-2.0
Install
npx skills add opensquilla/opensquilla --skill meta-paper-write --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 94 KB
Bundled scripts: none
Path: src/opensquilla/skills/bundled/meta-paper-write/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 6,515 · +130 this week
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 4, 2026

What it does

Orchestrates multiple sub-skills to manage academic manuscript workflows. It handles intake of paper requirements, mode selection (compact draft or full manuscript), potential clarification, and builds a final contract describing topic, mode, language, target pages, and audience. It expands requirements into a planning contract and then proceeds through translation of search queries, paper search, reference generation, and source packaging as part of producing a manuscript artifact. The meta-skill delegates to a pipeline that includes drafting, citations, and compilation checks as requested by the user.

How it works

  • Paper intake: extracts a structured brief from the user request, marking NEEDS_CLARIFICATION if fields are missing. Defaults: COMPACT_SKELETON for ordinary requests; FULL_MANUSCRIPT only if explicitly requested. Clarification policy defines required fields and default targets.
  • Paper clarification: if needed, prompts user to fill topic, mode, language, target length, and audience, offering defaults and language-specific prompts.
  • Paper contract: merges extracted requirements with clarification answers to produce a final contract containing TOPIC, PAPER_MODE, LANGUAGE, TARGET_PAGES, AUDIENCE, CITATION_TARGET, PDF_REQUIRED, and ASSUMPTIONS.
  • Paper preferences: expands the contract into a detailed planning contract, preserving explicit confirmed facts.
  • search_query_translation: if not compiling only, translates the confirmed topic into a concise English search query for scholarly sources.
  • search_papers: uses the translated query to search multiple scholarly engines, capped at 20 results.
  • refbib: generates references based on search results.
  • source_pack: compiles the source package and prepares artifacts for manuscript assembly.

When to use it

Use when the user asks to draft, repair, compile, or produce an academic/research paper or LaTeX manuscript. Ordinary requests follow a compact draft path; explicit full/PDF/long-form requests use the full manuscript path. Do not use for web research reports, slide decks, document decisions, or generic plotting.

What it can touch

  • Music of tools and artifacts is described in the workflow: includes llm_chat steps, skill_exec steps, and a multi-search engine. Declared tools: claude-code. File and process interactions occur through the described steps (e.g., paper_collect, paper_clarify, paper_contract, paper_preferences, search_query_translation, search_papers, refbib, source_pack).

Caveats

  • Declared risk: high. License: Apache-2.0. Requires specific tooling (xeLatex, bibtex) for platform opensquilla. Do not fabricate citations or results per policy tags (no-fabricated-citations, no-fabricated-results).
From the SKILL.md

# meta-paper-write (Meta-Skill) Draft a long LaTeX manuscript by orchestrating paper-specific skills and bounded LLM synthesis. The pipeline now leads with explicit experiment design + placeholder figures/tables + citation provenance audit so the deliverable can be reviewed for academic rigor, not just length. DAG (in order): 1. **`paper_collect`** — extracts topic, mode, language, target length, audience, and reference count from the same turn without pausing for a form. Missing facts are marked as assumptions so first-pass paper requests complete inline. 2. **`paper_preferences`** — expand the collected facts into a planning contract. 3. **`search_papers`** — `multi-search-engine` query biased toward arXiv / ACL Anthology / ACM DL / OpenReview / IEEE / Nature / Science so the returned URLs translate into real bibliographic identifiers. 4. **`refbib`** — `paper-refbib-stub` now extracts ``eprint``/``doi`` from arXiv/DOI URLs and tags each entry with ``note = {source: <domain>}`` so downstream gates can classify provenance without re-fetching. 5. **`source_pack`** — curate references and enforce ≥20-source coverage. 6. **`experiment_design`** — **decides** how many figures and tabl

More from opensquilla
All skills →
About this skill
What does the meta-paper-write skill do?

Use this meta-skill instead of answering directly when the current user asks to draft, repair, compile, or produce an academic/research paper or LaTeX manuscript. It uses multi-skill orchestration for manuscript workflows that need source search, citation planning, experiment or figure/table placeholders, drafting, length checks, citation integrity, and LaTeX/PDF compilation. Ordinary paper requests use a compact draft path; explicit full/PDF/long-form requests use the full manuscript path. Do not use it for web research reports, slide decks, document decisions, or generic plotting.

How do I install it?

Run `npx skills add opensquilla/opensquilla --skill meta-paper-write --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 opensquilla/opensquilla, a repository with 6,515 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.

Keep going