wiki-toolkit
claudeSkills for maintaining a Karpathy-style LLM wiki: ingest knowledge, look it up, run checkpoints, and lint the wiki
4 skills · hooks
Thinking-style skills and an agent: first-principles analysis, YAGNI scope review, sequential decision analysis, and a What Would Elon Do lens
Plugin funzies from marketplace marjo-claude-plugins in MarjovanLier/claude-plugins. Commands read from the repo's manifest — 13 days ago.
first-principlesNeutral first-principles decomposition: separate the assumptions behind a decision from the constraints that actually bind, then rebuild. Use when someone says 'challenge the assumptions', 'reason from first principles', 'rethink this from the ground up', asks which constraints are genuinely fundame
sequential-thinkingBreak a problem into numbered reasoning steps, each carrying its evidence, assumptions, and a stated confidence, with support for revising and branching earlier steps. Use only on explicit request: \"use sequential thinking\", \"number the reasoning steps with confidence\", \"show the revision branc
what-would-elon-doWhat Would Elon Do? Analyse a problem through Elon Musk's decision-making style: the 5-step process, physics-first thinking, aggressive deletion. Use only on explicit request: when someone says 'what would elon do', 'WWED', 'give me the Elon take', or asks for a deliberately bold or contrarian readi
yagniApply YAGNI (You Aren't Gonna Need It) to a feature, plan, design, or diff: classify each element as needed now or speculative, and cut the speculation. Use when someone says 'yagni', 'do we really need this', 'is this premature', asks to trim speculative scope, or when a plan adds functionality for
elonWhat Would Elon Do? Elon-style decision adviser for consequential architecture, scope, strategy, and rewrite decisions, which reads the actual codebase before answering and keeps persistent decision memory. Use when the user explicitly asks for the Elon take on a consequential decision, or asks for
Skills for maintaining a Karpathy-style LLM wiki: ingest knowledge, look it up, run checkpoints, and lint the wiki
4 skills · hooks
Git workflow skills: Conventional Commit messages and merge request contribution descriptions
2 skills
Agent that simplifies and refines PHP code for clarity, consistency, and maintainability while preserving functionality
1 agent
PHP language server: intelephense, phpactor, phpantom-lsp, and phpforge fanned out via the bundled lspfan multiplexer for completion, diagnostics, and refactoring
LSP
Opt-in companion to wiki-toolkit: checks each turn for durable findings, queues drafts, and starts the wiki checkpoint when the session goes idle
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.