caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Find stocks the market has punished for years, then interrogate each from four adversarial angles to tell temporary impairment from permanent breakage.
Plugin templeton from marketplace templeton in ccomkhj/stock_interogation. Commands read from the repo's manifest — 1 month ago.
huntRun the full templeton contrarian hunt — screen an index for multi-year wrecks, then interrogate each deep-dive candidate with a four-persona adversarial panel and a judge, producing a dated HTML report. Use when the user explicitly asks for a contrarian stock hunt or full persona analysis.
screenRun only the deterministic contrarian stock screen — rank an index's constituents by multi-year CAGR and show the worst performers with hard hits (CAGR ≤ -20%/yr) flagged. Use when the user wants the ranked candidate table of beaten-down stocks without spending tokens on agent analysis.
contrarianTempleton-contrarian persona for a templeton hunt. Researches one ticker via web search, builds the strongest possible maximum-pessimism buy case, then reports where it honestly lands as a structured TEMPORARY/PERMANENT verdict with cited evidence. Use when stress-testing the bear case on a beaten-d
forensic-accountantForensic accountant persona for a templeton hunt. Researches one ticker's debt load, cash burn and dilution risk via web search and returns a structured SURVIVES/DIES survival verdict with cited evidence. Use when asking whether a beaten-down company can fund itself long enough for any recovery to m
judgeJudge persona for a templeton hunt. Takes the four panel verdicts for one ticker (forensic-accountant, moat-analyst, short-seller, contrarian) and synthesizes them into a structured TEMPORARY | PERMANENT | UNCLEAR verdict with rationale, preserved dissent, and the accountant veto applied. Use after
moat-analystMoat analyst persona for a templeton hunt. Researches one ticker via web search to decide whether its business model is structurally broken or merely cyclically depressed, returning a structured TEMPORARY/PERMANENT verdict with cited evidence. Use when asking whether a beaten-down company's competit
short-sellerShort-seller persona for a templeton hunt. Researches one ticker via web search, builds the strongest possible permanent-impairment case against it, then reports where it honestly lands as a structured TEMPORARY/PERMANENT verdict with cited evidence. Use when stress-testing the bull case on a beaten
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.