Skip to content
TrustedSkillsbeta
Back to all skills

Topic Reviewer

Checked
zephyrwang6·vlatest·other

This tool analyzes text to identify key topics discussed and their prominence, streamlining review processes and summarizing content effectively.

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 spacezephyr/myskill --skill topic-reviewer -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

zephyrwang6

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 zephyrwang6/myskill at fa7105abba.

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

Commit
fa7105abba
Manifest
topic-reviewer/SKILL.md
Scanned
1 file, 94 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 Topic Reviewer skill analyzes proposed topics (either generated by another AI or provided directly) to determine their suitability for content creation. It assesses topics based on a predefined checklist, assigning scores and ultimately concluding whether a topic should be approved ("✅ 通过") or rejected ("❌ 不通过"). The review considers factors like popularity, relevance, timeliness, and potential user value.

When to use it

This skill is useful in the following scenarios:

  • Evaluating topics generated by AI content creation tools.
  • Filtering user-submitted topic suggestions for quality and feasibility.
  • Streamlining the initial stages of content planning and idea validation.
  • Ensuring that selected topics align with editorial guidelines and audience interests.
  • Quickly assessing whether a topic is worth pursuing based on rapid evaluation questions.

Key capabilities

  • Topic Scoring: Assigns scores across several dimensions (Unique Angle, User Value, Domestic Relevance, Title Appeal, Writing Difficulty).
  • Automated Rejection Criteria: Automatically flags topics that fail mandatory checks (e.g., low discussion volume, outdated news).
  • Detailed Feedback: Provides specific reasons for approval or rejection, including strengths and areas for improvement.
  • Weighted Scoring System: Uses a weighted scoring system to prioritize different aspects of topic quality (Unique Angle - 30%, User Value - 25%, etc.).
  • Rapid Assessment Questions: Includes a set of quick questions to help determine if a topic is worth pursuing immediately.

Example prompts

  • "Review this topic: 'The Future of Quantum Computing in Healthcare'"
  • "Assess the potential of this title for an article: '5 Ways to Improve Your Python Coding Skills'"
  • "Can you evaluate whether this topic aligns with our editorial focus on AI and productivity?"

Tips & gotchas

  • Mandatory Checks: Topics failing "must-pass" criteria (e.g., low discussion volume) will automatically be rejected.
  • Domestic Relevance: The skill prioritizes topics relevant to a domestic (presumably Chinese) audience.
  • Writing Difficulty: Topics requiring significant research or technical expertise may receive lower scores if they are deemed too challenging to produce quickly and effectively.