caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Agent workflow skills — /work, /handoff, /splitoff, /audit, /issue, /day-audit, /recall, /showme, /push, /report, /elevator, /tag, /pict, /print, /install-rules — four of them (/tag, /pict, /print, /splitoff) answered in a UserPromptSubmit hook without a model turn, plus the timeline, inbox, rule-injection and scheduler they run on.
Plugin jstack from marketplace jStack in jenyalebid/jStack. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
auditUse when the user asks to audit, double-check, or get a second opinion on this session's work.
day-auditUse when the user asks for a day audit — "audit yesterday", "did anything we shipped break".
elevatorUse when the user asks for the short version of a result — "/elevator", "give me the pitch", "short version", "where are we".
handoffUse when the user asks to hand this session off to a fresh terminal or to another agent.
install-rulesUse when the user asks to install or refresh the jStack rules and bare slash commands in ~/.claude/.
issueUse when working a GitHub issue end to end, or when an issue is assigned to the agent account.
pictUse only when the user asks what a session opens with and the jStack hook did not answer it.
post-session-reviewUse when reviewing a session that has ended — spawned by the session-review engine, or invoked with a session id.
printUse only when the user asks for this session's transcript path and the jStack hook did not answer it.
pushUse when the user says push, commit, ship it, or land this.
recallUse when the user asks what happened on a day or period — "/recall yesterday", "what did we do Monday?". Not for keyword lookups.
reportUse at the end of any task that produced work.
showmeUse when the user asks to see, show, preview, open, or look at what you've been working on.
splitoffUse only when the user asks to fork or copy this session into a new terminal and the jStack hook did not answer it.
tagUse when filing this session under a timeline subject, or when asked what it is filed under.
takeoverUse only when the user asks to hand this session to a fresh one that reads it from source, and the jStack hook did not answer it.
taskUse when handing a unit of work to an agent — files a GitHub task issue, spawns the executor on it, and keeps the conversation in this CLI.
workUse when the user says "let's work on X", or otherwise wants you prepared on an area before the work starts.
${CLAUDE_PLUGIN_ROOT}/hooks/inject-path-rules.py
${CLAUDE_PLUGIN_ROOT}/hooks/memory-ceiling.sh
${CLAUDE_PLUGIN_ROOT}/hooks/pretooluse-read-transcript.py
${CLAUDE_PLUGIN_ROOT}/hooks/attention.py set
${CLAUDE_PLUGIN_ROOT}/hooks/context-ceiling.py
${CLAUDE_PLUGIN_ROOT}/hooks/turn-budget.py
${CLAUDE_PLUGIN_ROOT}/hooks/env-announce.py
${CLAUDE_PLUGIN_ROOT}/hooks/plan-exit.py
${CLAUDE_PLUGIN_ROOT}/hooks/session-start-pad.py
${CLAUDE_PLUGIN_ROOT}/hooks/session-start-environment.py
${CLAUDE_PLUGIN_ROOT}/hooks/session-start-inject.py
${CLAUDE_PLUGIN_ROOT}/hooks/codex-carry.py
${CLAUDE_PLUGIN_ROOT}/hooks/env-entry.py
${CLAUDE_PLUGIN_ROOT}/hooks/attention.py clear
${CLAUDE_PLUGIN_ROOT}/hooks/tag-command.py
${CLAUDE_PLUGIN_ROOT}/hooks/pict-command.py
${CLAUDE_PLUGIN_ROOT}/hooks/print-command.py
${CLAUDE_PLUGIN_ROOT}/hooks/splitoff-command.py
${CLAUDE_PLUGIN_ROOT}/hooks/takeover-command.py
${CLAUDE_PLUGIN_ROOT}/hooks/env-delta.py
${CLAUDE_PLUGIN_ROOT}/hooks/plan-mode-watch.py
${CLAUDE_PLUGIN_ROOT}/hooks/attention.py clear
${CLAUDE_PLUGIN_ROOT}/hooks/stop-inbox-guard.py
${CLAUDE_PLUGIN_ROOT}/hooks/stop-timeline-remind.py
${CLAUDE_PLUGIN_ROOT}/hooks/stop-compact-delivery.sh
${CLAUDE_PLUGIN_ROOT}/hooks/env-announce.py
${CLAUDE_PLUGIN_ROOT}/hooks/plan-mode-watch.py
${CLAUDE_PLUGIN_ROOT}/hooks/attention.py clear
${CLAUDE_PLUGIN_ROOT}/hooks/session-end-review.sh
${CLAUDE_PLUGIN_ROOT}/hooks/record-session-files.py
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.