OneResearchClaw: Skill for Cursor

.cursor/skills/report-export/SKILL.md

report-export is a skill for Cursor from gaotiexinqu/OneResearchClaw. It costs 29 tokens per session (2,307 once invoked), scanned B, original, MIT.

A report-formatting tool that turns a final reviewed research report into files such as Markdown, Word, PDF, PowerPoint, or audio. It is the last step after research, summarising, and review are complete.

In plain words
What is it for?
Use it to read a reviewed report, identify its project folder, and save the requested output formats in a dedicated final-output folder.
Why use it?
It removes the need to reformat the same approved report by hand for different audiences or delivery formats. It does not conduct research or change the report’s conclusions.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is gaotiexinqu/OneResearchClaw's own configuration. It tells Cursor how to work on OneResearchClaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything OneResearchClaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gaotiexinqu/OneResearchClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/gaotiexinqu/OneResearchClaw/main/.cursor/skills/report-export/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/gaotiexinqu/OneResearchClaw

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for report-export

README.md
[![agentmods](https://agentmods.dev/badge/skills/gaotiexinqu/oneresearchclaw/report-export/github.svg)](https://agentmods.dev/skills/gaotiexinqu/oneresearchclaw/report-export)
Your own site
<a href="https://agentmods.dev/skills/gaotiexinqu/oneresearchclaw/report-export"><img src="https://agentmods.dev/badge/skills/gaotiexinqu/oneresearchclaw/report-export/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for report-export

Your own site · 80×15
<a href="https://agentmods.dev/skills/gaotiexinqu/oneresearchclaw/report-export"><img src="https://agentmods.dev/badge/skills/gaotiexinqu/oneresearchclaw/report-export.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,307 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.02307
Opus 5 $0.00015 $0.01154
Sonnet 5 $0.00006 $0.00461
Haiku 4.5 $0.00003 $0.00231

Measured 10d ago against content hash 06e782855770, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

report-export scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/export_audio.py, scripts/export_docx.py, scripts/export_md.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo apt-get update && sudo apt-get install -y fonts-noto-cjk fonts-wqy-zenhei
.cursor/skills/report-export/SKILL.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Report Export

This skill is the unified output-layer export skill.

It reads a final reviewed research report and renders it into one or more requested output formats.

This skill is the output-layer renderer for the pipeline:

grounding -> grounded-research-lit -> grounded-summary -> grounded-review -> report-export


Purpose

Use this skill to export a final reviewed report from:

  • data/reports/<ground_id>/research_report.md

into one or more requested formats, currently:

  • md
  • docx
  • pdf
  • pptx
  • audio

The output should be written under:

  • data/final_outputs/<ground_id>/...

What this skill does

This skill:

  1. reads the final reviewed report
  2. infers <ground_id> from the input path
  3. exports the report into the requested format(s)
  4. writes outputs into a dedicated <ground_id> output folder

What this skill does not do

This skill must not:

  • run new research
  • revise the research conclusions
  • add new evidence
  • rewrite the report as a different argument
  • act as a substitute for grounded-review

It may perform only the minimum transformation needed for the requested output format, such as:

  • markdown normalization
  • document formatting
  • PDF rendering via the DOCX export path
  • light speech-oriented normalization for audio rendering

Inputs

How to get ground_id

Infer ground_id from the parent directory of the input report:

data/reports/<ground_id>/research_report.md

The <ground_id> is embedded in the input path — no need to read ground_id.txt.

The main input is:

  • data/reports/<ground_id>/research_report.md

The skill assumes this file is already the final reviewed report.

Do not go back to:

  • grounded.md
  • lit.md
  • summary.md

unless the user explicitly asks for a re-review or re-synthesis task.

output_lang

The language for the exported report. Controls the language of all output format files (DOCX, PDF, PPTX, etc.).

Expected values:

  • en — English (default)
  • zh — Chinese (Simplified)

Read the full file on GitHub · 346 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 346 lines · 29 tokens per session scan B 06e782855770

Subscribe to this mod's changes

report-export is a skill published in the GitHub repository gaotiexinqu/OneResearchClaw (446 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 2,307 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

literature-survey

Use when the user wants a comprehensive literature survey on a specific research topic. Outputs a complete PDF survey (6–20 pages, 60+ real citations, 100+ recommended) with LaTeX source, topic-specific publication figures, and a classified literature table. Single-stage, no Python runtime.

ai4s-research/ai4s-skills · 66 tokens

figure-duplicate-audit

A review of scientific figure images for duplicated, reused, altered, or uninformative panels. Scientific figures are the charts, photographs, and image panels included in research papers.

xuzhougeng/wisp-science · 115 tokens

pdf-explore

Use this skill when the user has attached a PDF, paper, report, or other document and the answer needs its content: summarize a section, compare sections, read specific pages, check the table of contents, or read a value off a figure. The read tool cannot parse PDF binary — python is the extraction path. Provides…

xuzhougeng/wisp-science · 137 tokens

rocrate-metadata-bundle-starter

Use this skill to package a small local data file into an RO-Crate directory with basic provenance-rich metadata and a compact summary of the generated graph.

ma-compbio-lab/SkillFoundry · 0 tokens

pdf

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

DANG-ai/SKILLER · 50 tokens

paper-poster

A workflow for turning a completed research paper into a large conference poster, with PDF, editable PowerPoint, and SVG exports. An SVG is an image format that stays editable when resized.

AI4Scientist/nano-scientist · 76 tokens