examples/f-to-a-improvement/after/SKILL.md
Organizes files in a directory by sorting them into subdirectories based on file extension. Supports dry-run preview, custom rules via config file, and undo via move log. Use when the user asks to organize, sort, or clean up files in a directory. NOT for: renaming files, deduplication, or managing cloud storage.
npx skillsauth add aws-samples/sample-agent-skill-eval file-organizerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Sorts files into subdirectories by extension. Supports dry-run mode, custom rules, and undo.
# Preview what would happen
python scripts/organize.py ~/Downloads --dry-run
# Organize files
python scripts/organize.py ~/Downloads
# Undo last organization
python scripts/organize.py ~/Downloads --undo
This skill needs access to the target directory only:
Read(<target_dir>/*) — List files in the directoryWrite(<target_dir>/*) — Move files into subdirectoriesBash(python scripts/organize.py <target_dir> *) — Run the organizertools
Evaluate AI Agent Skills across safety, quality, reliability, and cost efficiency. Audit for security issues (secrets, injection, unsafe installs), test functional correctness with-skill vs without-skill, measure trigger precision, classify cost-efficiency tradeoffs, track version lifecycle, and generate unified grades. Use when evaluating a skill before installing, auditing marketplace skills, proving your skill works with automated tests, setting up CI/CD quality gates, or comparing two skill versions. NOT for: evaluating full agent systems, testing non-skill plugins, runtime performance benchmarking, or monitoring production agent behavior.
testing
Test fixture for scoped vs full scanning
testing
No frontmatter here, just plain text. This is not a valid SKILL.md file.
tools
A skill that references external MCP servers for testing SEC-009 detection.