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/terrylica/cc-skills --skill daemon-logs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。
正在显示 SKILL.md
| name | daemon-logs |
| description | View asciinema chunker daemon logs. TRIGGERS - daemon logs, chunker logs, backup logs. |
| allowed-tools | Bash |
| argument-hint | [-n lines] [--follow] [--errors] |
| model | haiku |
View logs from the asciinema chunker daemon.
Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.
| Argument | Description |
|---|---|
-n N | Show last N lines (default: 50) |
--follow | Follow log output (like tail -f) |
--errors | Show only ERROR lines |
/usr/bin/env bash << 'LOGS_EOF'
LOG_FILE="$HOME/.asciinema/logs/chunker.log"
LAUNCHD_STDOUT="$HOME/.asciinema/logs/launchd-stdout.log"
LAUNCHD_STDERR="$HOME/.asciinema/logs/launchd-stderr.log"
if [[ ! -f "$LOG_FILE" ]]; then
echo "No daemon logs found."
echo ""
echo "Log locations:"
echo " Daemon log: $LOG_FILE"
echo " launchd stdout: $LAUNCHD_STDOUT"
echo " launchd stderr: $LAUNCHD_STDERR"
exit 0
fi
echo "=== Daemon Log (last 50 lines) ==="
echo "File: $LOG_FILE"
echo ""
tail -50 "$LOG_FILE"
LOGS_EOF
/usr/bin/env bash << 'FOLLOW_EOF'
LOG_FILE="$HOME/.asciinema/logs/chunker.log"
if [[ ! -f "$LOG_FILE" ]]; then
echo "No daemon logs found. Start the daemon first."
exit 1
fi
echo "=== Following Daemon Log (Ctrl+C to stop) ==="
echo "File: $LOG_FILE"
echo ""
tail -f "$LOG_FILE"
FOLLOW_EOF
/usr/bin/env bash << 'ERRORS_EOF'
LOG_FILE="$HOME/.asciinema/logs/chunker.log"
if [[ ! -f "$LOG_FILE" ]]; then
echo "No daemon logs found."
exit 0
fi
echo "=== Error Log Entries ==="
echo ""
grep -E "ERROR|WARN|FAIL" "$LOG_FILE" | tail -30 || echo "(no errors found)"
ERRORS_EOF
[2025-12-26 15:30:00] === Daemon started (PID: 12345) ===
[2025-12-26 15:30:00] Config: idle=30s, zstd=3, active_dir=/Users/user/.asciinema/active
[2025-12-26 15:30:00] Credentials loaded (Pushover: enabled)
[2025-12-26 15:30:00] SSH caches cleared
[2025-12-26 15:30:02] Idle detected (35s) for workspace_2025-12-26.cast, creating chunk...
[2025-12-26 15:30:03] Pushed: chunk_20251226_153002.cast.zst to https://github.com/...
| File | Content |
|---|---|
~/.asciinema/logs/chunker.log | Main daemon log |
~/.asciinema/logs/launchd-stdout.log | launchd stdout |
~/.asciinema/logs/launchd-stderr.log | launchd stderr |
# View recent logs
/asciinema-tools:daemon-logs
# Follow logs in real-time
/asciinema-tools:daemon-logs --follow
# Show only errors
/asciinema-tools:daemon-logs --errors
| Issue | Cause | Solution |
|---|---|---|
| No logs found | Daemon never started | Run /asciinema-tools:daemon-start |
| Empty log file | Daemon just started | Wait a few seconds, check again |
| Logs not updating | Daemon crashed | Check /daemon-status, restart |
| Permission denied | Wrong file owner | Check ls -la ~/.asciinema/logs/ |
After this skill completes, check before closing:
Only update if the issue is real and reproducible — not speculative.
user wants to create a macOS Calendar event with sound alarms and paired Reminders, schedule a meeting, RSVP to an invitation, or set reminders.
Park a draft message/text in macOS Notes for the operator to review and edit, then read it back before acting (e.g. before sending to a real person). Notes is the source of truth (AppleScript CRUD, iCloud-synced, provenance-stamped with the Claude Code session UUID); Stickies is a best-effort view-only desktop mirror. Use whenever you draft something a human should confirm/edit before it is sent or committed — messages, replies, announcements, anything outbound. TRIGGERS - park this draft, park the message, hold this draft, let me edit first, draft for my approval, save to notes for review, read back the draft.
Programmatic Firecrawl usage via the public API, academic paper routing, recursive deep research, and raw corpus persistence.
基于 SOC 职业分类