caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Seven reasoning and evidence-reading skills, with a public source catalog and an evaluation protocol. No measured outcome gains are claimed.
Plugin mindforge from marketplace mindforge in owencrabbe/MindForge-Skills. Commands read from the repo's manifest — 1 month ago.
cross-pollinateGenerates non-obvious insight by importing models, mechanisms, and solved problems from distant disciplines into the user's problem, finding the deep structural analogies that spark breakthroughs. Use this skill whenever the user wants to "think differently about," "find a fresh angle on," "get unst
decision-forgeStructures a hard decision under uncertainty into a rigorous, defensible analysis: options, criteria, probabilities, expected value, reversibility, and a clear recommendation. Use this skill whenever the user is "trying to decide," "weighing options," "torn between," "not sure whether to," "should I
deep-researchRuns a source-linked research investigation and returns a structured, citation-backed synthesis instead of a shallow summary. Use this skill whenever the user wants to "research," "dig into," "find the literature on," "get up to speed on," "write a report on," "do a deep dive," "review the evidence
first-principlesDecomposes any hard problem, plan, or belief down to its fundamental truths and rebuilds it from the ground up, stripping out assumptions inherited by habit or convention. Use this skill whenever the user says "think from first principles," "break this down," "why do we even do it this way," "reason
fitness-evidenceRead general adult fitness claims against public evidence, retaining population, outcomes, provenance and limitations. Use for evidence questions, source review, or fitness-content drafting; not for individualized medical, nutrition or dosing decisions.
socratic-partnerActs as a rigorous thinking partner that sharpens the user's own reasoning through pointed questions instead of handing over answers, surfacing hidden assumptions, undefined terms, and blind spots. Use this skill whenever the user wants to "think through," "talk out," "work out," "reason about," or
steelman-redteamStress-tests an argument, plan, belief, or decision to its breaking point by first building the strongest possible version of it (steelman) and then attacking it as hard as an intelligent adversary would (red team). Use this skill whenever the user wants to "pressure-test," "poke holes in," "stress
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.