Benchmark Fileops
Execute 21-step file operations workflow for benchmarking prompt adherence. Use for Skills vs Commands comparison testing.
Install
npx skills add claudekit/skillmark --skill benchmark-fileopsgit clone --depth 1 https://github.com/claudekit/skillmark.git /tmp/skillmark
mkdir -p ~/.claude/skills
cp -r /tmp/skillmark/demo/.claude/skills/benchmark-fileops ~/.claude/skills/benchmark-fileopsPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# 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}`Details
- Skill name
benchmark-fileops- Repository
- claudekit/skillmark
- Path
demo/.claude/skills/benchmark-fileops/SKILL.md- Repo updated
- 23 September 2026
FAQ
What does the Benchmark Fileops skill do?
Execute 21-step file operations workflow for benchmarking prompt adherence. Use for Skills vs Commands comparison testing.
How do I install the Benchmark Fileops skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add claudekit/skillmark --skill benchmark-fileops. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Benchmark Fileops popular?
It lives in claudekit/skillmark, which has 9 GitHub stars and 4 forks.
Related skills
Brainstorm
9claudekit/skillmark
Brainstorm solutions with trade-off analysis and brutal honesty. Use for ideation, architecture decisions, technical debates, feature exploration, feasibility assessment, design discussions.
Code Review
9claudekit/skillmark
Review code quality, receive feedback with technical rigor, verify completion claims. Use before PRs, after implementing features, when claiming task completion, for subagent reviews.
Context Engineering
9claudekit/skillmark
Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking about context percentage, rate limits, usage warnings, context optimization, agent architectures, memory systems.
Improve Queue
9duvoai/skills
Run the guided, end-to-end loop that makes one Duvo Queue — and the producer→consumer workflow around it — better. Use when the user wants to "improve this Queue", "this Queue keeps backing up, fix it", or take a Queue to a concrete, applied improvement — not just a read-only audit. You drive the conversation: pin the Queue, survey its whole shape (producers and consumers, backlog and case state, both Agents' AOPs at the seam, triggers and concurrency, the Runs flowing through), agree what to base the improvement on (the user's feedback or the evidence in the Runs/backlog), propose a Run/case
Swap Simulate
8KyberNetwork/kyberswap-skills
This skill should be used when the user asks to "simulate swap", "dry run swap", "test swap transaction", "check if swap would succeed", "simulate before executing", "dry run the trade", "preview swap on-chain", or wants to verify a previously built swap transaction would succeed without actually sending it. Uses Foundry's `cast call` to run an eth_call simulation. Requires swap calldata from swap-build skill output.
Orby
9prismatic-io/agent-skills
Explore, operate, and troubleshoot Prismatic environments. Use when a user asks about their Prismatic organization, customers, integrations, instances, executions, logs, deployment, configuration, documentation, GraphQL API, or an end-to-end outcome involving the Prismatic platform.
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.