Individual skill
skill-curator
Safely vet and import third-party agent skills: read-only shallow clone, validate frontmatter, safety-scan every file, adapt tool-specific-isms, never execute repo code or installers, dedupe by content not just name. Use when adding skills from GitHub repos or community sources to a skills library.
skills/skill-curator/SKILL.md
Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 8, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 53
- Repository last updated
- Oct 10, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai-agents Repository topic
- ai-agents-automation Repository topic
- ai-skills Repository topic
- awesome Repository topic
- awesome-list Repository topic
- chatgpt Repository topic
- claude-skills Repository topic
- meta-ai Repository topic
- muse-ai Repository topic
- writing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Read excerpt
# Skill Curator
A safety-first pipeline for importing third-party agent skills (SKILL.md-format) from GitHub or other sources into your own library. Skills are executable-adjacent: a malicious or sloppy skill can exfiltrate data, harvest credentials, or inject prompts. Curate like a package maintainer, not a downloader.
## The Pipeline
### 1. Read-only acquisition
- `git clone --depth 1` into a temp directory. Shallow and read-only.
- **Never** run installers, setup scripts, `curl | sh`, `npx` bootstrappers, or any executable from the repo. Read files; don't run them.
### 2. Validate structure
- Every skill must have a `SKILL.md` with YAML frontmatter containing `name:` and `description:`.
- `name` must be lowercase-hyphens and match its directory name.
- `description` must say what the skill does *and when to trigger it* — it's the routing mechanism.