메뉴
Show Claude Code usage stats from cache, then optionally build the HTML dashboard (24h / 7d / 30d / all)
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Standard editorial template for any standalone HTML output (reports, RCAs, dashboards, diagrams, slides, recaps). Use EVERY time you generate an HTML file so output follows one consistent house style instead of ad-hoc theming.
Findings-first review agent for code changes. Use when the user asks to review a branch, PR, diff, commit range, or recent changes and wants prioritized, actionable issues instead of implementation work.
Scan and clean stale Claude Code sessions from the shared store at ~/.local/share/claude/projects (used by all .claude / .claude-accountN dirs via symlink). Removes session JSONLs older than N days, orphan subagent dirs, and reports reclaimable space.
Triage ShopHelp XCTest/Swift Testing failures before proposing fixes.
Manage Jira issues through jhelp shell functions (jv, jm, jd, jc, jforward, etc.). Use when the user wants to view, transition, assign, comment on, edit, search, or create Jira work items; when they provide a bare issue number, Jira issue key, or Jira URL; or when the task involves the current git branch ticket.
Create git commits. Use when user says "commit", "commit this", "commit changes", "split commit", "split commit change", "split the changes".
| name | usage-dashboard |
| description | Show Claude Code usage stats from cache, then optionally build the HTML dashboard (24h / 7d / 30d / all) |
| args | ["range"] |
Show usage stats from the rolling cache, then ask before generating HTML.
Generated files live under ~/.agent/usage-dashboard/<project>/ by default, not the repo worktree.
range — one of 24h, 7d, 30d (default), all
Set the script path:
SCRIPT=~/dotfiles/ai/commonSkills/usage-dashboard/scripts/generate.py
RANGE=${range:-30d}
Refresh the cache and print stats (no HTML yet):
python3 "$SCRIPT" --range "$RANGE" --stats-only 2>/dev/null
This prints a summary table to the terminal showing sessions, output tokens, cache read, and cache written for all four windows (24h / 7d / 30d / all). The requested range is marked with ◀.
Ask the user: "Build HTML dashboard? (y/n)"
n or anything other than y / yes → stop here.If confirmed, generate all 4 HTML variants and open the target range:
OUT=$(python3 "$SCRIPT" --range "$RANGE" 2>/dev/null)
open "$OUT"
~/.agent/usage-dashboard/<project>/usage-cache.json/usage-dashboard → 30d view (default)
/usage-dashboard 24h → last 24 hours
/usage-dashboard 7d → last 7 days
/usage-dashboard all → all cached data