caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Evidence-led UX reviews: capture, record, first clicks, pluses and deltas, Notion synthesis, rounds.
Plugin research-studio from marketplace research-studio in Kugothepup/didactic-eureka. Commands read from the repo's manifest — 13 days ago.
captureCapture every site in a Research Studio study: routes, journey runs, videos, structure crawls and reference captures, then the measured counts on each Notion row. Use when the user runs /research-studio:capture or asks to capture, record or crawl a study's sites.
cognitive-design-reviewAudit any UI, wireframe, user flow, or interface description against cognitive psychology principles. Use this skill when the user asks to review, audit, critique, or evaluate a design for cognitive issues, usability problems, or psychological friction. Also trigger when users ask 'what's wrong with
cognitive-psychology-kbAuthoritative cognitive psychology reference for UX, HCI, and behavioural design. Consult this skill whenever discussing cognitive load, working memory, attention, perception, heuristics, biases, mental models, Gestalt principles, dual-process theory, emotional design, decision-making psychology, or
hubBuild or refresh a Research Studio project's hub page in Notion: where everything is, the side-by-side stage table with pluses and deltas, the synthesis in brief, every journey video and first-click image, and next steps. Use when the user runs /research-studio:hub or asks to pull a project together
newStart a new Research Studio study: the Notion project and study from the templates, the competitor rows, and a local study folder with study.json from a journey preset. Use when the user runs /research-studio:new or asks to set up a new study, project or competitor review from scratch.
ogilvy-writing-coachAudit and sharpen business and sales writing against David Ogilvy: his 1982 \"How To Write\" memo and the Roman-Raphaelson \"Writing That Works\" principles for all writing, plus his advertising rules (one promise, a headline that sells, proof, long copy) for ads, landing pages, sales emails and pro
promoteCopy the findings, recommendations and beliefs the user has ticked in a Research Studio study's Synthesis into the shared Insights, Opportunities and Hypotheses databases. Use only when the user runs /research-studio:promote or explicitly asks to promote accepted findings.
questionOptional: develop a hunch, topic or frustration into research questions before a study starts, or rework a question mid-study. A short back-and-forth where Claude suggests questions to ask and candidate answers, and the user says yes, no or edit. Produces a Goal, research questions, beliefs, out of
retroRun a pluses-and-deltas retrospective on the Research Studio method itself after a project or round, log it, and propose concrete changes to the plugin's tools, skills, presets or templates on a branch. Use when the user runs /research-studio:retro or asks how the framework could improve.
review-writeupHouse style for every review write-up: expert reviews, audits, competitor and inspiration reviews, study synthesis, critique notes, annotated screens, Notion review pages, and review summaries in chat. Sets the tone (calibrated, never absolute) and the shape (pluses and deltas: + what's working and
reviewReview every captured site in a Research Studio study: stage checks, the expert review of the user's own site, competitor and inspiration reviews in pluses and deltas, predicted first clicks drawn on the screens, and annotated screens, all written to Notion. Use when the user runs /research-studio:r
roundRun a new capture round on a Research Studio study after changes, and compare it with the last round: re-capture, re-record, re-crawl, measured differences, re-judged stage checks, and the hub updated. Use when the user runs /research-studio:round or asks to re-check sites after changes or measure w
study-synthesisThe Research Studio method: works a study in Notion (a page in Studies made from the Study template): reviews competitors against the study's journey checks, predicts first clicks as triage, writes the Synthesis section as a Draft, and promotes accepted findings to the shared Insights, Hypotheses an
synthesiseWrite a Research Studio study's Synthesis section as a Draft: readiness check, evidence used, findings with sources and confidence, beliefs checked, compared by stage, recommendations as deltas, and open questions; then refresh the project hub. Use when the user runs /research-studio:synthesise or a
tasksSet up and record 'find X' tasks on a Research Studio study's sites: task flows with right answers, recordings with clicks counted, and predicted-journey rows. Use when the user runs /research-studio:tasks or asks whether visitors can find something on a site.
ux-business-impactAuthoritative reference for translating UX work into measurable business impact, using the 41-impact / 99-skill taxonomy from UX Skills for Business Strategy (Podmajersky, Joseph-Goteiner, Mats Mats). Consult this skill whenever UX work needs to be justified, prioritised, measured, or explained to a
ux-expert-assistantInclusive design auditor, conversational UX designer, and UX CLI toolbox. Use this skill whenever the user wants to audit a design for cognitive accessibility, exclusion, or neurodiversity support — trigger on "inclusive design", "cognitive accessibility", "exclusionary design", "neurodiversity", "s
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.