skills/watch/SKILL.md
Start Discord auto-response loop. Use when user mentions watch, discord watch, auto-response.
npx skillsauth add thkt/dotclaude watchInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Start a /loop that monitors Discord DM channels and auto-responds to new messages.
$1: interval (optional, default: 1m). Supports Ns, Nm, Nh format.$2: channel_id (optional). If omitted, read all channel IDs from ~/.claude/channels/discord/access.json allowFrom entries and check approved channels.$ARGUMENTS (default 1m).~/.claude/channels/discord/access.json and find active DM channels from ~/.claude/channels/discord/approved/ directory (file contents = chatId).1m → */1 * * * *5m → */5 * * * *Nm where N <= 59 → */N * * * *Nh → 0 */N * * *cron: the expressionprompt: the monitoring prompt (below)recurring: trueFor each channel:
Check Discord channel {channel_id} for new messages using fetch_messages. Reply to any new messages not from me. Do not re-reply to already-replied messages. If no new messages, do nothing.
If user says "stop":
documentation
Generates and updates .claude/OUTCOME.md interactively. When the file is absent or empty (no Behavior / all sections TBD), collects content via AskUserQuestion and writes the stub; when present, shows the current state and applies updates.
development
Judge a SKILL.md against craft axes (single responsibility, description distinctiveness, imperative voice, verifiable completion, calibration, progressive disclosure) and apply the fixes the audit surfaces. Do not use for format-presence-only checks (use reviewer-prompt) or reproducibility loops (use /tuning).
tools
Internal helper for /think Step 11. Renders SOW.md + Spec.md as an integrated Astro view and returns a dev server URL.
development
Extract repository spec while detecting bugs, spec gaps, and consistency drift via dual-purpose documentation. OUTCOME.md-axis question-driven exploration with ephemeral output. Do NOT use for code review (use /audit or /polish), feature implementation (use /code), planning only (use /think), or single-bug fix (use /fix).