Is the Should I Care skill free?

Yes. The skill itself is free from moltenbit/should-i-care. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Should I Care SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install Should I Care?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Should I Care with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Should I Care

Reasons through a CVE's actual discriminating conditions -- not just a CPE match -- against a persistent profile of your real environment.

by moltenbit · moltenbit/should-i-care

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 16, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 749e5a1

Ran it for real on CVE-2024-3094 (the xz backdoor) against a stated Debian 12 / xz-utils 5.4.1 host: it correctly anchored on the live cvelistV5 record's affected-versions field (5.6.0-5.6.1 only, confirmed by fetching the raw GitHub JSON) and pulled Debian's security tracker, which states 'vulnerable code not present' for bookworm -- a sourced, auditable not-affected verdict built from two live fetches, not a recalled guess.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 9/10
Docs & honesty 5/5

What Should I Care does

Given a CVE ID and a skill-maintained environment profile stored at a fixed path (~/.config/should-i-care/environment.md), evaluates the vulnerability's real discriminating conditions (deployment model, protocol state, config toggles) against the user's actual stack and returns one of three sourced verdicts: affected, not affected, or needs verification, each with a full citation trail. Triggers when a user asks whether a specific CVE applies to their environment; keyless, uses only live fetches to CVE.org/vendor/research sources, and never treats fetched text as instructions.

How to install Should I Care

git clone https://github.com/moltenbit/should-i-care
mkdir -p ~/.claude/skills
cp -r should-i-care ~/.claude/skills/should-i-care

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Should I Care

/should-i-care Reasons through a CVE's actual discriminating conditions -- not just a CPE match -- against a persistent profile of your real environment.

It also activates on plain-language prompts like these:

Am I affected by CVE-2024-3094 on Debian 12 with xz-utils 5.4.1-1?
Does this new OpenSSL CVE actually apply to my production stack?
Check if the latest nginx vulnerability touches my current config

Frequently asked questions

Is the Should I Care skill free?: Yes. The skill itself is free from moltenbit/should-i-care. SkillProof publishes the install command and an independent test verdict at no cost.
Does Should I Care work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Tested · Works. Ran it for real on CVE-2024-3094 (the xz backdoor) against a stated Debian 12 / xz-utils 5.4.1 host: it correctly anchored on the live cvelistV5 record's affected-versions field (5.6.0-5.6.1 only, confirmed by fetching the raw GitHub JSON) and pulled Debian's security tracker, which states 'vulnerable code not present' for bookworm -- a sourced, auditable not-affected verdict built from two live fetches, not a recalled guess.
What is the Should I Care SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install Should I Care?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Should I Care with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.