Check my vibe
全球最大的 Claude Code 技能聚合库 · 收录 3900+ 来自 12+ 来源的技能，提供在线搜索与趋势分析看板 / The world's largest Claude Code skill aggregation hub — 3900+ skills from 12+ sources with online search and trend dashboard
npx -y skills add bg-szy/TOP-SKILLS --skill check-my-vibeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when a user wants to review the public security posture of an AI-generated, vibe-coded, or deployed website through an authorized passive scan, especially for security headers, exposed secrets, source maps, public files, and deployment mistakes.
SKILL.md
2.5 KB, 479 tokens by cl100k_base, as published. Nobody here has run it
Check My Vibe
Overview
Use Check My Vibe for an authorized, passive review of one public website. Run the real scan at https://checkmyvibeapp.com/; never invent results or replace it with an unprotected API call.
Workflow
- Get the target URL.
- Confirm authorization: the user must own the target or have the owner's permission. Stop if authorization is absent.
- Open
https://checkmyvibeapp.com/in the available browser. - Enter the target URL. The user must complete Turnstile; never bypass or solve it for them.
- Start the scan and wait for a completed or failed result.
- Read the score, coverage, limited or partial state, findings, evidence, remediation, limits, and errors.
- Report only findings supported by the scan evidence.
If no browser is available, give the user the Check My Vibe URL and ask them to paste the resulting report. Do not simulate the scan or call the protected endpoint directly.
Response Format
- Summary: Target, score, coverage, and whether the scan was partial or limited.
- Fix now: Critical and high findings, ordered by risk and dependencies.
- Fix next: Medium and low findings.
- Manual review: Review, not-tested, partial, or weak-evidence items.
- Top three actions: The highest-value next steps.
- Coverage limits: What this passive public-surface scan did not verify.
Boundaries
The scan does not prove a site is secure. It does not validate authenticated areas, database authorization, private repositories, business logic, complete dependency risk, or full penetration-test coverage. It does not log in, submit target forms, exploit vulnerabilities, or recursively crawl the site.
Never request passwords, API keys, cookies, or private source code. For verification failure, rate limiting, invalid targets, or safely unreachable pages, explain the error and use the site's normal retry path without changing identity or bypassing controls.
Common Mistakes
- Treating a public URL as permission to scan it.
- Claiming that a clean report means the site is secure.
- Guessing code locations or vulnerabilities not present in the evidence.
- Bypassing Turnstile, same-origin checks, rate limits, or URL safety rules.
What ships with it: 1 file
15.3 KB alongside SKILL.md
- skill-report.json15.3 KB
Gives 0 of the 12 instructions most quality gates skills give in 479 tokens
Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-07
- Read the output and check the exit codein 54 of 1195, across 14 files
- Verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
- Identify the verification command proving the claimin 51 of 1195, across 12 files
- Run the full verification commandin 50 of 1195, across 11 files
- Verify output confirms the claimin 49 of 1195, across 12 files
- Check version control diff after agent delegationin 46 of 1195, across 6 files
- State claim with evidencein 44 of 1195, across 4 files
- Run the test suitein 33 of 1195, across 26 files
- Keep state in memory by defaultin 27 of 1195, across 6 files
- Make prototype runnable with one commandin 26 of 1195, across 5 files
- Produce a verification reportin 25 of 1195, across 14 files
- Detect the package manager from lockfilesin 24 of 1195, across 5 files
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.