From 3a3fb6cbe2035d74e01f2166d30864367e1e2a0f Mon Sep 17 00:00:00 2001 From: Suhaib Janjua Date: Tue, 17 Mar 2026 16:19:08 +0500 Subject: [PATCH] docs: align FAQ risk labels with frontmatter values and add skill-review guidance (#330) --- docs/users/faq.md | 22 ++++++++++++++++++---- docs/users/getting-started.md | 2 +- 2 files changed, 19 insertions(+), 5 deletions(-) diff --git a/docs/users/faq.md b/docs/users/faq.md index a8b2d101..96c5071a 100644 --- a/docs/users/faq.md +++ b/docs/users/faq.md @@ -71,11 +71,13 @@ The skill files themselves are stored locally on your computer, but your AI assi ### What do the Risk Labels mean? -We classify skills so you know what you're running: +We classify skills so you know what you're running. These values map directly to the `risk:` field in every `SKILL.md` frontmatter: -- ⚪ **Safe (White/Blue)**: Read-only, planning, or benign skills. -- 🔴 **Risk (Red)**: Skills that modify files (delete), use network scanners, or perform destructive actions. **Use with caution.** -- 🟣 **Official (Purple)**: Maintained by trusted vendors (Anthropic, DeepMind, etc.). +- 🔵 **`none`**: Pure reference or planning content — no shell commands, no mutations, no network access. +- ⚪ **`safe`**: Community skills that are non-destructive (read-only, planning, code review, analysis). +- 🔴 **`critical`**: Skills that modify files, drop data, use network scanners, or perform destructive actions. **Use with caution.** +- 🟣 **`offensive`**: Security-focused offensive techniques (pentesting, exploitation). **Authorized use only** — always confirm the target is in scope. +- ⬜ **`unknown`**: Legacy or unclassified content. Review the skill manually before use. ### Can these skills hack my computer? @@ -237,6 +239,18 @@ Common fixes: ``` +### My PR triggered the `skill-review` automated check. What is it? + +Since v8.0.0, GitHub automatically runs a `skill-review` workflow on any PR that adds or modifies a `SKILL.md` file. It reviews your skill against the quality bar and flags common issues — missing sections, weak triggers, or risky command patterns. + +**If it reports findings:** + +1. Open the **Checks** tab on your PR and read the `skill-review` job output. +2. Address any **actionable** findings (missing "When to Use", unclear triggers, blocked security patterns). +3. Push a new commit to the same branch — the check reruns automatically. + +You do not need to close and reopen the PR. Informational or style-only findings do not block merging. + ### Can I update an "Official" skill? **No.** Official skills (in `skills/official/`) are mirrored from vendors. Open an issue instead. diff --git a/docs/users/getting-started.md b/docs/users/getting-started.md index 7920aaf2..1e964d31 100644 --- a/docs/users/getting-started.md +++ b/docs/users/getting-started.md @@ -1,4 +1,4 @@ -# Getting Started with Antigravity Awesome Skills (V7.9.1) +# Getting Started with Antigravity Awesome Skills (V8.0.0) **New here? This guide will help you supercharge your AI Agent in 5 minutes.**