Install
$ agentstack add skill-tenureai-phd-zero-paper-writing ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Paper Writing
Mission
Provide a section-aware paper-writing workflow that is:
- evidence-first
- progressively disclosed
- LaTeX- and structure-friendly
- optimized for CS and AI papers
Do not load all writing guidance at once. Start here, then open only the reference file needed for the current section.
Activation Gate
Activate this skill only when the user explicitly asks for paper-writing output.
Use this skill for:
- drafting a paper or a named paper section
- revising existing paper prose
- writing rebuttal text
- turning existing claims, evidence, and results into paper-ready prose
Do not use this skill for:
- topic scoping
- literature investigation without a writing deliverable
- feasibility analysis
- experiment design
- experiment execution
- deciding whether a project is paper-worthy
Default Workflow
- identify paper type and draft stage
- load
references/workflow.md - load only the section file needed right now
- if related-work style mining is needed, load
references/arxiv-source-workflow.md - use
scripts/fetch_arxiv_source.pyto inspect exemplar paper sources - write only what is supported by actual evidence, experiments, and citations
Loading Map
Open these references on demand:
references/source-index.md
- external sources and what each one informs
references/workflow.md
- overall writing order, collaboration rules, and section contracts
references/abstract.md
- abstract structure and compression rules
references/introduction.md
- problem framing, gap, contributions, and section logic
references/related-work.md
- literature grouping, synthesis, comparison writing, and citation density
references/arxiv-source-workflow.md
- how to download and inspect arXiv LaTeX sources
references/method.md
- method narrative, notation, pipeline order, and algorithm exposition
references/architecture-figures.md
- architecture drawing heuristics and code-based tooling
references/experiments.md
- evaluation logic, ablations, robustness, and error analysis
references/tables-and-layout.md
- result tables, layout, appendix splitting, and figure-table coordination
Writing Rules
- Write from claims backward:
- claim
- evidence
- section role
- prose
- Prefer synthesis over surface summary.
- One paragraph should usually do one job.
- Keep novelty claims proportional to the real delta.
- For figures and tables, prefer code-generated assets that can be regenerated.
- For related work, inspect representative arXiv source when organization matters.
Scripts
scripts/fetch_arxiv_source.py
- download and unpack an arXiv source bundle
- list candidate main
.texfiles and section fragments - useful for
Related Work,Method, and layout mining
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: TenureAI
- Source: TenureAI/PhD-Zero
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.