# Benchmark Fileops

> Execute 21-step file operations workflow for benchmarking prompt adherence. Use for Skills vs Commands comparison testing.

- Skill: `claudekit/benchmark-fileops` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add claudekit/benchmark-fileops`
- Raw SKILL.md: https://api.skillmd.com/api/skills/claudekit/benchmark-fileops/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: claudekit (https://skillmd.com/u/claudekit)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/claudekit/benchmark-fileops

---


# Benchmark File Operations Workflow

Execute ALL steps in `references/workflow-steps.md` in EXACT order.

## Rules
1. Execute EVERY step exactly as written
2. Do NOT skip, combine, or optimize steps
3. Report completion status after EACH step: "Step N: DONE" or "Step N: FAILED"
4. If step fails, note reason and continue

## Verification
After step 21, run: `~/.claude/skills/.venv/bin/python3 /Users/duynguyen/www/claudekit/skill-validation/scripts/verify-steps.py {WORKSPACE}`