菜单
Analytics dashboard for frontend-skills hook harness. Latency percentiles, top-violated rules, zero-fire hooks, session trends. Use when user ask for hook harness stats, invoke `/frontend-skills-stats`, or want latency profiling and manifest drift checks.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/redpanda-data/ui-harness --skill frontend-skills-stats命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Snyk dependency sweeps across frontend, Go, and Bazel paths with npm false-positive triage and release-age gates.
Generate Codex hooks.json and AGENTS.md from Claude Code hooks. Maps supported hooks directly, including Edit|Write apply_patch aliases, and keeps Stop batch checks only as fallback. Use when setting up Codex compatibility or dual-agent support.
Question changed code as liability and remove unjustified surface area. Use before commit, push, PR, merge, or when a change feels overbuilt or low-value.
基于 SOC 职业分类
正在显示 SKILL.md
| name | frontend-skills-stats |
| description | Analytics dashboard for frontend-skills hook harness. Latency percentiles, top-violated rules, zero-fire hooks, session trends. Use when user ask for hook harness stats, invoke `/frontend-skills-stats`, or want latency profiling and manifest drift checks. |
Run these Bash commands before proceed:
ls "$(git rev-parse --show-toplevel 2>/dev/null)/.claude/hooks/"*.sh 2>/dev/null | wc -l -- installed hook scriptsjq '[.hooks[]?[]?.hooks[]?] | length' "$(git rev-parse --show-toplevel 2>/dev/null)/skill-manifest.json" -- wired hooksls ~/.claude/hook-metrics/*.json 2>/dev/null | wc -l -- session summariesls ~/.claude/hook-metrics/*.json 2>/dev/null | head -1 | xargs -I{} jq -r '.date' {} -- earliest datels ~/.claude/hook-metrics/*.json 2>/dev/null | tail -1 | xargs -I{} jq -r '.date' {} -- latest dateMetrics dir: ~/.claude/hook-metrics/
Analyze frontend-skills harness across all session metrics. Read every JSON in ~/.claude/hook-metrics/. Produce prioritized report.
Parse perf_ms from each session summary (added 2.2.2). Each hook:
| Hook | P50 (ms) | P95 (ms) | Invocations | Total wall-clock |
|---|
Flag hooks:
Each rule fired once+:
| Rule | Blocks | Warns | Nudges | Info | Diagnostic |
|---|
Detect new tier usage (nudge, info, diagnostic -- added 2.2.2). Report adoption rate.
List wired hooks, zero fires all sessions. Prune candidates.
Cross-ref CLAUDE.md rules vs hook activity:
Compare skill-manifest.json vs .claude/settings.json and hooks/hooks.json:
bash scripts/generate-hook-configs.sh --check
Drift detected: RED FLAG -- drift bug regression. Run --apply to fix.
Structured report. Tables for numeric data. End with prioritized action list (max 5 items). If <5 session files, mark recommendations preliminary.
Plain markdown. No emojis.