caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Four skills in two pairs. Compares a stated mental model of a codebase against reality and grounds implementation plans in it, reporting the gaps as graded Mermaid diagrams (architecture, deployment, or data-flow). Reviews the comments already in the code and reports which to cut, worst first, and keeps new ones from being written where the code could say it instead.
Plugin lumberjack from marketplace lumberjack in AntonyM71/Lumberjack. Commands read from the repo's manifest — 1 month ago.
comment-disciplineWrites code that explains itself, so comments stay rare and true. Before any comment gets written it climbs a ladder — can the code say it (rename, extract, name the constant)? is this just the what? is it a why the code cannot hold? — and stops at the first rung that holds. Stays active across the
grounded-planPlans a change to a codebase's architecture, deployment, or data flow by first grounding it in how the relevant part of the system actually works today, then bakes a before/after diagram pair into the implementation plan so the change is visibly justified rather than just described in prose. Use thi
prune-commentsReviews the comments already in code and reports which ones to cut, worst first: comments that lie about what the code now does, commented-out code, changelogs and bylines git already keeps, banner markers, and restatements of the line below. Each finding climbs a fix ladder — delete it, make the co
reality-checkCompares what a developer currently believes (or what an existing doc/wiki claims) about a codebase area — architecture, deployment, or data flow — against what the code actually does today, then writes a graded Mermaid comparison report (a "your model" diagram next to a red/amber/green-outlined "re
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.