Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/yhlai0911-to-paper
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/to-paper
What's inside
- Skill name
to-paper- Description
- Draft an academic paper from verified research artifacts.
- License
- MIT
- Instructions
- 14 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# To Paper Run `$render-research-deliverable` with: - destination: `paper blueprint` when required analyses or results are missing; - destination: `manuscript draft` only when completed results and provenance exist; - source: the current canonical Research Brief and registered result artifacts; - journal, language, format, and style from the user's request. For paper/thesis delivery, require the renderer's scholarly-delivery contract: developed academic prose and verified literature, explained numbered equations, managed APA citations, editable LaTeX, an actual LaTeX-compiled PDF, first-build evidence, visual QA and a source package. Missing compilation or evidence means partial/blocked delivery, not permission to substitute Word-to-PDF or invent sources. A blueprint remains a blueprint even when its PDF compiles. This wrapper requires a current canonical Research Brief. If the workspace or brief is missing, stop and recommend `$research-auto` or `$research-2-brief`; do not silently create the prerequisite here. Stop after readback. Never fill a results section with expected, simulated, or plausible findings unless they are explicitly labeled as such and the requested artifact permits them.
From yhlai0911/research-os, MIT.
More from yhlai0911/research-os
- 0.570score
research-finance-social-science
yhlai0911
Review an empirical finance or social-science research design using domain-specific validity checks, when the user chooses this optional profile.
SkillAFreshness: AClaude Code +9 - 0.570score
artifact-reconciliation
yhlai0911
Resolve conflicting canonical research artifacts into one verified current state without erasing either intent or provenance.
SkillAFreshness: AClaude Code +9 - 0.567score
research-auto
yhlai0911
Develop a topic, direction, problem, source, or partial idea through adaptive interviewing, evidence research, reviewer attack, and repair until it becomes a…
SkillAFreshness: AClaude Code +9 - 0.567score
research-5-run
yhlai0911
Claim and execute one eligible research workpackage with bounded authority, falsification gates, receipts, and readback.
SkillAFreshness: AClaude Code +9 - 0.565score
citation-audit
yhlai0911
Verify that citations exist, are primary where appropriate, and entail the claims they support.
SkillAFreshness: AClaude Code +9 - 0.564score
writing-research-skills
yhlai0911
Design, review, and maintain predictable Research OS skills.
SkillAFreshness: AClaude Code +9 - 0.558score
research-status
yhlai0911
Show where the project stands on the mainline, what exists so far, and what the next action is.
SkillAFreshness: AClaude Code +9 - 0.558score
research-1-grill
yhlai0911
Interrogate a research idea one decision at a time until it is researchable.
SkillAFreshness: AClaude Code +9 - 0.558score
research-3-falsify
yhlai0911
Predeclare what evidence would kill the current research design before any expensive work begins.
SkillAFreshness: AClaude Code +9 - 0.558score
research-4-tasks
yhlai0911
Split a research brief into dependency-aware tracer workpackages.
SkillAFreshness: AClaude Code +9 - 0.558score
research-save
yhlai0911
Create a verifiable handoff that preserves research continuity across sessions.
SkillAFreshness: AClaude Code +9 - 0.558score
research-6-review
yhlai0911
Attack the current research design or draft as a skeptical journal panel and record every finding.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 27, 2026 (3 months ago)
- Last release
- Oct 19, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/yhlai0911/research-os
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from yhlai0911
- 0.570score
artifact-reconciliation
yhlai0911
Resolve conflicting canonical research artifacts into one verified current state without erasing either intent or provenance.
SkillAFreshness: AClaude Code +9 - 0.570score
research-finance-social-science
yhlai0911
Review an empirical finance or social-science research design using domain-specific validity checks, when the user chooses this optional profile.
SkillAFreshness: AClaude Code +9 - 0.567score
research-5-run
yhlai0911
Claim and execute one eligible research workpackage with bounded authority, falsification gates, receipts, and readback.
SkillAFreshness: AClaude Code +9 - 0.567score
research-auto
yhlai0911
Develop a topic, direction, problem, source, or partial idea through adaptive interviewing, evidence research, reviewer attack, and repair until it becomes a…
SkillAFreshness: AClaude Code +9 - 0.565score
citation-audit
yhlai0911
Verify that citations exist, are primary where appropriate, and entail the claims they support.
SkillAFreshness: AClaude Code +9 - 0.564score
writing-research-skills
yhlai0911
Design, review, and maintain predictable Research OS skills.
SkillAFreshness: AClaude Code +9
Cite this page
to-paper skill. Agent Mart. https://agentmart.dev/skills/yhlai0911-to-paper (last updated 2026-10-24)