meldwerkes
claudeMeldwerkes: multi-agent cognitive architecture that builds a personalized decision model through PAHF loops, distillation, and multi-brain orchestration.
10 skills · hooks
Brief interview skills for candidates in AI-assisted technical interviews: configure, clarify, plan, direct, review, verify, build integration tests with a dashboard, and narrate.
Plugin interview-skills from marketplace eukota-claude-marketplace in eukota/claude-marketplace. Commands read from the repo's manifest — yesterday.
clarifyUse at the start of an AI-assisted interview, when the candidate has just been given a prompt and needs to turn it into clarifying questions, stated assumptions, and a scope narrow enough to finish in the time available.
configureUse before an AI-assisted interview or practice run, or whenever the candidate wants to change how the other interview skills behave, to set time, level, stack, AI tool, voice, narration and which skills to use in a short config file the other skills read.
directUse when the candidate in an AI-assisted interview is about to ask the AI to write code, to build a brief that carries the plan, constraints and real data shapes so the AI does not invent them.
integration-testsUse when the candidate in an AI-assisted interview wants integration tests for their app. This is a meta-skill; it instructs Claude to build the integration tests plus an observability dashboard with click-triggered test runs, every time.
narrateUse at any point in an AI-assisted interview when the candidate needs a short script to explain a decision aloud, handle an AI mistake, or wrap up with what they would do next.
planUse after requirements are clarified in an AI-assisted interview and before any code is written, when the candidate needs a short, time-boxed design they have shaped themselves.
reviewUse right after the AI generates code in an AI-assisted interview, when the candidate must read it critically and show they did not accept it blindly.
verifyUse when the candidate in an AI-assisted interview needs to show that the code works, with quick unit checks and edge cases, before or alongside integration tests.
Meldwerkes: multi-agent cognitive architecture that builds a personalized decision model through PAHF loops, distillation, and multi-brain orchestration.
10 skills · hooks
Personalized Agents from Human Feedback — PAHF loop for Meldwerkes: pre-action clarify, ground in memory, post-action correct, compress to principles.
4 skills
Tracks Claude account rate-limit usage (5-hour and 7-day windows) from the status line, and reports whether your plan is the constraint on your work.
1 skill · 2 commands
Tools for building Claude marketplace plugins — choosing primitives, checking name availability, smoke-testing hooks, scaffolding structure, and following conventions.
2 skills
Personal project context management system for engineers – structured Markdown + YAML that gives your AI assistant persistent, organized memory across sessions and machines. Auto-maps each project's workspace folders into per-project permissions.
1 skill
Enforces standard local development practices — git worktrees, containerized package installs, Makefile start/stop targets, and hot reload.
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.