Skip to content
TrustedSkillsbeta
Back to all skills

Nsfc Reviewers

Checked
huangwb8·vlatest·writing·MIT

This skill simulates NSFC reviewer feedback on research proposals, offering valuable insights for improvement and increasing chances of success.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add huangwb8/chineseresearchlatex --skill nsfc-reviewers -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

huangwb8

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned huangwb8/chineseresearchlatex at f1c7206faa.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
f1c7206faa
Manifest
skills/nsfc-reviewers/SKILL.md
Scanned
18 files, 2,555 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Nsfc Reviewers skill simulates feedback from expert reviewers for National Natural Science Foundation of China (NSFC) research proposals. It analyzes proposal documents to identify potential weaknesses and areas for improvement, providing insights into risks and suggesting a prioritized sequence of modifications to increase the likelihood of success. The skill operates in either a parallel review mode (multiple independent reviews) or a single-group mode if parallel processing isn't available. Critically, it only reads, analyzes, and summarizes content; it does not modify source files or perform LaTeX compilation.

When to use it

  • Before submitting an NSFC proposal for review.
  • To identify potential weaknesses in a research proposal early on.
  • To understand the risks associated with a current version of a proposal if submitted today.
  • To prioritize areas for modification and improvement based on expert feedback simulation.
  • When seeking insights into whether a proposal would pass initial (函评) or panel (会评) review stages.

Key capabilities

  • Simulates NSFC reviewer feedback.
  • Analyzes proposals to identify risks and weaknesses.
  • Provides prioritized modification sequences.
  • Offers stage assessment (函评 / 会评).
  • Supports parallel review mode for multiple independent assessments.
  • Identifies consensus points and individual viewpoints across simulated reviewers.
  • Distinguishes between design flaws and compromises due to funding limitations.

Example prompts

  • "Review this proposal: [path/to/proposal.tex]"
  • "Simulate NSFC reviewer feedback on my research proposal, focusing on the innovation aspects."
  • "Analyze this proposal for potential risks if submitted today: [path/to/proposal.zip]"

Tips & gotchas

  • The skill requires at least one of proposal_path, proposal_file, or proposal_zip as input.
  • The skill prioritizes reading and analysis; it will not compile LaTeX documents or correct grammatical errors.
  • Proposal content is treated as sensitive information, and the skill avoids sending large portions of text externally unless explicitly requested by the user.