swe
claudecodexSWE 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
Plugin uni 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.
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.
learn-feynmanCheck and improve the learner's own from-memory explanation of a concept they have already met. Use when the learner wants to explain an idea back to you, or asks \"check my understanding\" or \"did I get this right?\".
learn-geneticLead the learner to rediscover why an idea exists, from a concrete problem where familiar approaches fail. Use when the learner asks why a concept, rule, or representation is needed, or how someone could have invented it.
learn-quizQuiz the learner with one source-grounded question at a time, graded fairly, with feedback and adaptive follow-up. Use when the user says \"quiz me\" or \"test me\" on a topic or a source.
learn-refuteTest and repair the learner's claim, proof sketch, argument, or algorithm with counterexamples and checks of its assumptions. Use when the learner asks you to critique or check their proof, argument, or solution (\"is my solution wrong?\").
learn-reviewReview concepts that the user selects or met earlier in the chat, with active recall and focused drills, one answer at a time. Use when the user asks to review, drill, or refresh what they learned.
learn-transferPractice how to select and apply a learned idea in a new situation: a changed context, a changed structure, or a choice between methods. Use when the learner asks where else an idea applies, how to use it in practice, or when to pick one method over another.
learn-worked-exampleTeach a procedure through a small worked example, then completion problems, then an independent attempt. Use when the learner is stuck, lacks a prerequisite, or asks \"show me how\" or for an example.
learnTutor the user through an interactive lesson with questions, active recall, and exercises that build understanding. Use when the user asks to learn a topic, to be taught, or to understand how or why something works (\"teach me\", \"help me understand\", \"I am rusty on\"). Answer coding and direct-a
teachBuild a persistent learning workspace in this folder: mission, HTML lessons, references, and learning records, gated by a tech tree.
tech-treeBuild a course as a prerequisite graph (tech tree) before any lesson, then gate each topic on mastered prerequisites, place the learner, remediate failures, and schedule reviews. Use when a course, curriculum, or multi-session lesson series starts, or when a course folder has a tech-tree.json.
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
Source-backed research, reproducible experiment loops, and data visualization guidance
6 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.