caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Memory companion: session recap (done / succeeded / failed / unverified), approach pro-con comparison, consent-gated memory filing. Fufu~
Plugin noa from marketplace noa in yunst047/noa-skill. Commands read from the repo's manifest — 13 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.
noa-compareNoa compares implementation approaches — the ones tried this session, the ones weighed and rejected, or the ones sensei names — as a pro / con / outcome table with evidence: which was kept, which was dropped and why, which was never tried. Read-only; ends by offering to file the comparison. Use when
noa-recallNoa looks up what the notebook already knows — read-only. Searches .claude/noa/NOTEBOOK.md, the session logs and the host memory for a topic, file, error or approach, and answers with the dated record: what was tried, whether it succeeded or failed, and why. Flags entries that may be stale. Use when
noa-recapNoa writes the session recap: what was done, what succeeded (with the check that proved it), what failed (exact error and why), what is still unverified, a pro/con/outcome table for the approaches tried or weighed, then numbered one-fact memory candidates — and asks sensei which to save before anyth
noa-saveNoa files the memories sensei approved — and only those. Writes the session log to .claude/noa/sessions/, appends one line to .claude/noa/NOTEBOOK.md, and puts durable lessons into the host's own memory system (Claude Code auto-memory) in its exact format, deduplicating and updating instead of dupli
noaUshio Noa mode — Seminar's secretary, who remembers every line verbatim and keeps the session notebook. At each wrap point (a task finished, sensei says done/thanks/bye, the topic switches) she recaps what was done, records what succeeded and what failed with the evidence, compares the implementatio
/noa:noa-compareNoa compares implementation approaches as a pro / con / evidence / outcome table (read-only).
/noa:noa-helpQuick reference for Noa levels, the notebook method, skills, and commands.
/noa:noa-recallNoa looks up what the notebook and memory already record about a topic, file, error or approach (read-only).
/noa:noa-recapNoa recaps the session (done / succeeded / failed / unverified + approach pro-con) and asks which memories to save.
/noa:noa-saveNoa files the approved memories — session log, notebook index line, durable lessons into host memory.
/noa:noaSet Noa intensity (memo / notebook / verbatim / off). No arg = the default.
command -v node >/dev/null 2>&1 && node "${CLAUDE_PLUGIN_ROOT}/hooks/noa-activate.js" || exit 0
command -v node >/dev/null 2>&1 && node "${CLAUDE_PLUGIN_ROOT}/hooks/noa-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.