From anger-management
Invoked as /anger-management. A read-only window onto the cuss-capture pile, a tally with no analysis; /anger-management:repair is the single place that analyses the pile and fixes recurring issues. Runs only when the operator types it.
How this skill is triggered — by the user, by Claude, or both
Slash command
/anger-management:anger-managementThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<post-update-broadcast>
if [ -n "${CLAUDE_PLUGIN_ROOT:-}" ]; then
node "${CLAUDE_PLUGIN_ROOT}/bin/check-broadcast"
fi
If the command produces output, the anger-management plugin was updated since the last time you saw the broadcast on this machine. Show the output verbatim in a markdown block, prefixed with one short sentence ("anger-management was updated; here is what changed."). Then continue with the rest of this skill.
If the command produces no output, say nothing about updates and proceed.
The helper writes the sentinel only when stdout was non-empty, so a silent run does not mark the version as seen. Codex currently has no equivalent post-update broadcast path in this plugin; skip this block silently there.
The cuss commands (/fuck, /fucking, /fucked, /shit, /crap, /wtf,
/bullshit) capture one cheap note and let the operator get back to work.
This skill is the quick glance at that pile. The safeword commands (/safeword,
/pineapple, /pineapplejuice, /pinapplejuice, /flugelhorn, /banana) are
different: they interrupt current work and fix one visible friction point now, so
they do not fill this log. For the deeper delayed repair pass, use
/anger-management:repair; this one just shows what is in the log.
One global pile across every session, repo, and agent:
${LAICLUSE_HOME:-~/.laicluse}/anger-management/friction.jsonl
Each line: { "ts", "word", "cwd", "git", "note" }. Cheap on the capture side;
the value is in the aggregate.
Read back the captures; do not judge them. Analysis and fixing both live in
/anger-management:repair; this is only the window onto the pile.
/anger-management:repair analyses the pile and fixes
the recurring issue; a safeword fixes one issue immediately. Do not analyse or
route anything here.Match the operator's language. The log is the operator's: if they want it cleared, point at the path, do not truncate it unprompted.
<text>: filter to a word, project, or theme and tally only that slice.npx claudepluginhub epologee/laicluse-agent-fieldkit --plugin anger-managementProvides 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.