terrylica
terrylica/cc-skills
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 diagnose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。
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
正在显示 SKILL.md
| name | diagnose |
| description | Diagnose Kokoro TTS issues. TRIGGERS - kokoro not working, tts diagnose, kokoro error, tts troubleshoot. |
| allowed-tools | Read, Bash, Glob, Grep, AskUserQuestion |
Troubleshoot Kokoro TTS engine issues through systematic diagnostics.
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.
| Issue | Likely Cause | Diagnostic | Fix |
|---|---|---|---|
| Import error | Venv corrupted | python -c "from mlx_audio.tts.utils import load_model" | kokoro-install.sh --uninstall && --install |
| Model not found | Download incomplete | ls ~/.cache/huggingface/hub/models--mlx-community--Kokoro-82M-bf16/ | kokoro-install.sh --install to re-download |
| Slow synthesis | First-run warmup | Time a test synthesis | Normal — subsequent runs use cached model |
| Not Apple Silicon | Intel/Linux system | uname -m != arm64 | MLX-Audio requires Apple Silicon (M1+) |
| Wrong Python | Not 3.14 | ~/.local/share/kokoro/.venv/bin/python --version | Rebuild venv with --uninstall && --install |
| Server won't start | Port in use | lsof -i :8779 | Kill existing process or change port |
| No audio from CLI | Empty text | Check --text argument | Provide non-empty text |
Use AskUserQuestion:
# Platform check
echo "Arch: $(uname -m)"
echo "macOS: $(sw_vers -productVersion)"
# Venv check
[[ -d ~/.local/share/kokoro/.venv ]] && echo "Venv: OK" || echo "Venv: MISSING"
# Python version
~/.local/share/kokoro/.venv/bin/python --version 2>/dev/null || echo "Python: NOT FOUND"
# MLX-Audio import
~/.local/share/kokoro/.venv/bin/python -c "from mlx_audio.tts.utils import load_model; print('MLX-Audio: OK')" 2>&1 || echo "MLX-Audio: FAIL"
# Scripts present
for f in kokoro_common.py tts_generate.py tts_server.py; do
[[ -f ~/.local/share/kokoro/$f ]] && echo "$f: OK" || echo "$f: MISSING"
done
# Version info
cat ~/.local/share/kokoro/version.json 2>/dev/null || echo "version.json: MISSING"
Use the Known Issues table above to identify the root cause and apply the targeted fix.
# Quick synthesis test
~/.local/share/kokoro/.venv/bin/python ~/.local/share/kokoro/tts_generate.py \
--text "Diagnostic test" --voice af_heart --lang en-us --speed 1.0 \
--output /tmp/kokoro-diag-test.wav && echo "Synthesis: OK"
After this skill completes, reflect before closing the task:
Do NOT defer. The next invocation inherits whatever you leave behind.