The work loop on top of core: pick a task up, hand it back, file what you spot, drive the task engine and a project's release, keep personal todos and reminders. Ships the session hooks that stamp a run, cue a pickup and gate the hand-back.
Plugin vitrinka-pm from marketplace kit in henderson-tech/vitrinka-kit. Commands read from the repo's manifest — 2 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.
meUse for personal todos, reminders, milestones and the agenda in vitrinka — '/me [add|list|done|drop|remind|milestone|agenda]', 'remind me', 'add a todo', 'what is ripe', 'add to today's todos <task>', 'plan X for tomorrow', 'what's on my agenda'.
tasksUse when working a project's task engine or release from the repo — '/tasks [list|intake|file|epic|rule|release]', 'file a task', 'find the X epic', 'plan the epic', 'triage intake', 'sprint start', 'add an automation rule', 'cut the release', 'write the release notes'.
workUse when a vitrinka task id or URL arrives in the prompt (work pickup), when work on a bound task ends or the Stop gate asks for a hand-back (work handoff), and when a 'later', 'out of scope' or 'someone should decide' thought appears mid-task (work spot).
vitrinka hook-context start 2>/dev/null || true
vitrinka hook-context task-end 2>/dev/null || true
vitrinka hook-context stop 2>/dev/null || true
vitrinka hook-context touch 2>/dev/null || true
The vitrinka experience: capture UI work as journeys and walkthroughs, author documents, pages and diagrams, brainstorm on a decision board, and service a board's annotation queue — live, as a backlog, or paired with a human testing the app. Registers nothing itself — `vitrinka setup` adds the MCP endpoint.
3 skills · 1 agent · hooks
Flows still proving themselves, beside core: build-idea takes a committed brief to a draft PR with one quick check, make-idea runs a brainstorm into it, test asks which lanes and device checks to run, cleanup reconciles a project's tasks against reality. Claude Code only; opt in with `vitrinka setup --experimental`.
3 skills
Hlídač on top of core: ask whether prod is OK after a deploy, investigate a prepared problem from its brief and groups, and set up the sources Hlídač reads.
3 skills
The testing pipeline on top of core: test like a user, review a board's screens or a journey, and turn recorded sessions into fixes and tests.
1 skill
A Claude Code mod: the session's board, epic and task in the prompt footer as links, and /vt to open them, the work tree, brainstorms and both inbox lanes without spending a model turn.
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.