caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Test-first, goal-driven allocation efficiency: goal, red test, size, type, pre-allocate, length, pass by role, bench. Kanpeki.
Plugin yuuka from marketplace yuuka in yunst047/yuuka-skill. Commands read from the repo's manifest — 9 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
yuuka-allocYuuka rewrites one hot loop, collection builder, or string assembly test-first until it allocates exactly what it needs — kanpeki. Writes the failing behaviour + allocation-budget tests first, then picks the right container, pre-allocates it, chooses letter vs numeric element types, guards lengths b
yuuka-auditYuuka audits a file, function, or diff for wasted memory and time and returns a costed ledger — read-only, no edits. Flags copy-and-destroy loops (append/concat/spread without capacity), missing pre-allocation, wrong container, letter-vs-numeric type waste, boxed numbers, unchecked lengths, and poin
yuuka-benchYuuka sets a numeric runtime goal (ns/op, allocs/op, or wall time at a stated input size), measures the baseline, then iterates one change per benchmark run until the goal is met — kanpeki — or honestly reports how far short it is. Tests stay green the whole way; no fudged numbers. Use when the user
yuuka-passYuuka chooses pointer, reference, borrow, view, or value for function parameters and returns by the data's role — immutable, read-only, write, or owned — so nothing is copied that is only read and nothing is aliased that must not be. Covers Go, Rust, C/C++, Java/Kotlin, C#, Python, JS/TS, Swift, Zig
yuukaHayase Yuuka mode — Seminar's treasurer, who audits every allocation and never optimizes by vibes. Test-first, goal-driven performance work on arrays, slices, lists, strings and buffers in any language: set a numeric runtime goal, write the failing tests, pick the right container and pre-allocate it
/yuuka:yuuka-allocYuuka rewrites one hot loop/builder test-first — right container, pre-allocated, typed, length-checked, passed by role.
/yuuka:yuuka-auditYuuka audits a file/function/diff for wasted allocations, copies, unchecked lengths and wrong signatures (read-only ledger).
/yuuka:yuuka-benchYuuka sets a runtime goal, measures the baseline, and benchmarks one change at a time until kanpeki (or honestly short-by).
/yuuka:yuuka-helpQuick reference for Yuuka levels, the kanpeki ledger, skills, and commands.
/yuuka:yuuka-passYuuka picks pointer / reference / borrow / view / value for each signature by role (read-only, write, immutable, owned).
/yuuka:yuukaSet Yuuka intensity (allowance / ledger / deficit / off). No arg = the default.
command -v node >/dev/null 2>&1 && node "${CLAUDE_PLUGIN_ROOT}/hooks/yuuka-activate.js" || exit 0
command -v node >/dev/null 2>&1 && node "${CLAUDE_PLUGIN_ROOT}/hooks/yuuka-mode-tracker.js" || exit 0
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.