caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Plan large, foggy efforts as a map of decision tickets, steered through lavish artifacts. Bundles the brainstorm, grilling, domain-modeling, research, divide-n-rule, and sakshi (code review) skills plus the wait-what utility (each callable on its own, e.g. /sarathi:brainstorm); needs lavish installed separately.
Plugin sarathi from marketplace magentaworks in pinugit/AIatMagenta. Commands read from the repo's manifest — 1 month ago.
brainstormBrainstorm an idea, a problem space, or one ticket with a sharp thinking partner — open ideas up before grilling narrows them down. Use before charting a Sarathi map when an idea is still foggy, or to enrich a ticket before grilling it.
divide-n-ruleTurn a settled engineering handoff into an ordered set of development slices, where each slice cuts top-to-bottom through every layer so you can test and ship it on its own, and no slice depends on one that comes later. Use after a Sarathi map reaches its destination — decisions are clear, but the b
domain-modelingBuild and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
grillingGrill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
researchInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
sakshiReview code against the effort's spec (the map's decisions) and for plain bugs. Uses the `ocr` CLI from alibaba/open-code-review with its configured LLM and project rules to perform the review; the agent drives the flow and gates findings. Use after implementation is done — at handoff, or when the u
sarathiPlan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets kept in local markdown, and resolve them one at a time through lavish review artifacts — questions, prototypes, the map, the pending task list — until the way to the destination is clear.
wait-whatStop — that last message didn't land. Re-pitch it in plain, simple language. Call it when Sarathi (or any skill) said something you didn't follow.
/sarathi:against-productionReview the production→HEAD diff for spec violations and plain bugs (sakshi, full mode)
/sarathi:bugsReview uncommitted changes for plain bugs only — no spec check (sakshi, bugs mode)
/sarathi:reviewReview uncommitted changes for spec violations and plain bugs (sakshi, full mode)
/sarathi:spec-checkReview uncommitted changes against the effort's spec only (sakshi, spec mode)
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.