Source-backed research, reproducible experiment loops, and data visualization guidance
Plugin lab from marketplace agent-toolbox in kpeez/agent-toolbox. Commands read from the repo's manifest — 3 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.
autoresearchRun a bounded autonomous experiment loop against an approved metric and evaluator, or clean up a completed run into a verified archive. Use for autoresearch, repeated optimization runs, or autoresearch cleanup; not for one-off research memos or multi-lane reviews.
deep-researchProduce repository-retained research briefs, lane evidence, and an audited Markdown report. Use for multi-lane project research requiring those artifacts; not for a single bounded question or an experiment loop.
go-deeperMake a new task deeper, not bigger, before you start: what a top expert would do, the rawest source, the real methods and tools, and a check outside you and the user. Use first on any new task, request, or proposal. Skip chat, quick facts, and fully specified mechanical edits.
making-plotsCreate or revise publication- or report-quality scientific result figures and their plotting code. Use for benchmark, training, and evaluation figures; not ordinary tabulation, general dashboard critique, or UI mockups.
researchProduce one retained, cited memo for a bounded research question or explicit source audit. Not for multi-lane programs or experiment loops.
visualizing-dataDesign or review statistical plots and plotting code for honest scales and accessibility. Not for conversational diagrams, simulations, or UI mockups.
cat "$CLAUDE_PLUGIN_ROOT"/hooks/session-start.md
SWE skills for AI coding agents: an SWE router that runs a task through a step-by-step playbook, design interviews, short handoff plans, behavioral verification, CI triage and verified landing, and more
59 skills · 2 agents · hooks
Interactive lessons, quizzes, reviews, and prerequisite-gated courses
11 skills · hooks
A live pane of this session's tool calls, colored by tool and status, each expandable to its full input; open it with /activity
A control panel for this session: an overview with a timeline, subagents with their prompt, trace and answer, shell commands with their output, and files touched; open it with /panel
An animated pane of this session's subagents: a walking Clawd per agent with its type, task and latest tool call; open it with /subagents
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.