caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
init / run / triage / weekly — a driver runs the loop in code, repo-agnostic; each repo binds it with .claude/ouro.toml.
Plugin ouro from marketplace ouro in iteramen/ouro. Commands read from the repo's manifest — 5 days 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.
initOnboards a repo to ouro: asks the owner what the plugin's installer needs, runs it from the repo root, reports each file it wrote, skipped or refused, then reads the repository's Issues and merged-branch settings and offers to turn either on. Invoked by the owner as `/ouro:init`, for a first run and
runTake one agent-ready issue to a landed change with the ouro driver. Invoked as `/ouro:run <N> [--part <k>] [--dry-run] [--validate] [--override-claim] [--pr <M>]`. Use when the user says "run issue N", "execute and land N", "take N end to end", or hands over an agent-ready issue number. The driver b
triageGrade one GitHub issue against the ouro contract with the ouro driver: it posts the `**Triage**` verdict comment, writes the Size, Flow and Doc impact lines and sets the labels. Invoked as `/ouro:triage <N> [--dry-run]`. Use when the user asks to triage an issue, promote it to agent-ready, grade its
weeklyPrint the ouro loop's weekly outcome table, or the queue's next wave, with the ouro driver. Invoked as `/ouro:weekly [--post]` for the table and `/ouro:weekly compile` for the wave. Use when the user asks how the loop did this week, for the outcome or quality table, or for what can run next. `--post
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/guard-delete.py"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/guard-stash-kill.py"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/guard-discard.py"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/guard-commit.py"
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/session-sync.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.