How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-report:usageThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Post a daily token usage summary to the team Slack channel by parsing local Claude Code transcript files.
Post a daily token usage summary to the team Slack channel by parsing local Claude Code transcript files.
/usage 2026-04-13), use that date.report_usage MCP tool with the date parameter (YYYY-MM-DD format). It returns stats plus a per-project activity snippet block wrapped in <untrusted_activity>…</untrusted_activity>.post_usage_to_slack with date and summaries as { "<project path>": [bullet, ...], ... }.The scheduled daily 19:00 job (bin/daily-usage-wrapper.sh) already runs under --model sonnet, so automated posts are cheap. Interactive /usage uses whatever model is driving the session — if you want to save cost on a manual run, switch to Sonnet with /model first.
For a persistent daily 19:00 report that survives reboots, run /install-daily-report. It installs a launchd job on macOS.
The old /schedule-usage path creates a session-only CronCreate that expires after 7 days; prefer /install-daily-report for team distribution.
npx claudepluginhub knorq-ai/claude-report --plugin claude-reportProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.