菜单
Execute 21-step file operations workflow for benchmarking prompt adherence. Use for Skills vs Commands comparison testing.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create or update Claude skills optimized for Skillmark benchmarks. Use for new skills, skill scripts, references, benchmark optimization, extending Claude's capabilities.
Brainstorm solutions with trade-off analysis and brutal honesty. Use for ideation, architecture decisions, technical debates, feature exploration, feasibility assessment, design discussions.
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.
Review code quality, receive feedback with technical rigor, verify completion claims. Use before PRs, after implementing features, when claiming task completion, for subagent reviews.
ALWAYS activate this skill before implementing EVERY feature, plan, or fix.
Plan implementations, design architectures, create technical roadmaps with detailed phases. Use for feature planning, system design, solution architecture, implementation strategy, phase documentation.
| name | benchmark-fileops |
| description | Execute 21-step file operations workflow for benchmarking prompt adherence. Use for Skills vs Commands comparison testing. |
| version | 1.0.0 |
| allowed-tools | ["Bash","Write","Edit","Read","Glob"] |
Execute ALL steps in references/workflow-steps.md in EXACT order.
After step 21, run: ~/.claude/skills/.venv/bin/python3 /Users/duynguyen/www/claudekit/skill-validation/scripts/verify-steps.py {WORKSPACE}
