By kult-byra
Structured feature development, experiments, and task management — project setup, problem definition, research, hypothesis, adversarial critique, empirical validation, sprint-based delivery, QA, and ADHD-optimized task workflows.
Set up standard documentation, feature workflow, and task management structure in any project. Creates docs/, features/, tasks/, embeds methodology, and configures CLAUDE.md. Trigger on: 'docs setup', 'set up docs', 'initialize project', 'docs-setup', 'sett opp dokumentasjon', 'set up feature workflow', 'project setup', 'nytt prosjekt oppsett', or when starting a new project that needs structured development.
Initialize a new experiment — standalone or linked to a feature hypothesis. Creates the experiment folder, methodology, and EXPERIMENT.md. Trigger on: 'new experiment', 'experiment-init', 'nytt eksperiment', 'test this idea', 'proof of concept', 'poc', 'let's try this', 'validate with an experiment', 'benchmark this', 'prototype', or when feature-validate decides an experiment is needed.
Document experiment results and decide next steps. Analyze what happened, compare to baseline, evaluate against success criteria. Trigger on: 'experiment results', 'experiment-results', 'what did we learn', 'analyze results', 'eksperiment resultater', 'hva lærte vi', or after experiment-run when results need documenting.
Build and execute an experiment. Read EXPERIMENT.md, build the minimum needed, run it, collect results. Trigger on: 'run experiment', 'experiment-run', 'kjør eksperiment', 'build the poc', 'run the benchmark', 'execute experiment', 'test it', or after experiment-init when the user wants to proceed.
Stress-test a feature hypothesis with adversarial subagents. Optional phase after feature-hypothesis — spawns parallel critics to find blind spots, then synthesizes with steelman evaluation. Trigger on: 'critique this', 'feature-critique', 'stress test', 'steelman', 'kritiser dette', 'er dette egentlig bra', 'challenge the hypothesis', 'find the flaws', 'devil's advocate', or after completing feature-hypothesis when the user opts for critique.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
"The Electric Monk was a labour-saving device, like a dishwasher or a video recorder. Dishwashers washed tedious dishes for you, thus saving you the bother of washing them yourself, video recorders watched tedious television for you, thus saving you the bother of looking at it yourself; Electric Monks believed things for you, thus saving you what was becoming an increasingly onerous task, that of believing all the things the world expected you to believe."
— Douglas Adams, Dirk Gently's Holistic Detective Agency
A Claude Code plugin marketplace for structured feature development. It does the tedious methodology work for you, so you can focus on building.
/plugin marketplace add kult-byra/electric-monk
Then install the plugin from the Discover tab, or:
/plugin install kult-features@electric-monk
A documentation-first methodology for building features. 21 skills organized into three workflows:
Feature lifecycle — from idea to shipped:
| Skill | What it does |
|---|---|
/feature-init | Set up a new feature with structured docs |
/feature-define | Socratic interview to deeply define the problem |
/feature-research-plan | Plan what to research before committing |
/feature-research | Conduct the planned research |
/feature-hypothesis | Form your approach based on evidence |
/feature-critique | Stress-test with adversarial subagents |
/feature-validate | Prove the core bet before full build |
/feature-plan | Break into deployable sprints |
/feature-qa-plan | Plan testing strategy per sprint |
/feature-sprint | Execute a sprint with QA discipline |
/feature-sprint-change | Handle mid-sprint plan changes |
/feature-status | Context recovery — where did we leave off? |
/feature-done | Archive a finished feature |
Experiments — prove ideas cheaply:
| Skill | What it does |
|---|---|
/experiment-init | Set up a standalone or feature-linked experiment |
/experiment-run | Build and execute the experiment |
/experiment-results | Analyze results and decide next steps |
Task management — for everything else:
| Skill | What it does |
|---|---|
/task-braindump | Guided brain dump when you're overwhelmed |
/task-capture | Quick-capture an idea for later |
/task-plan | Prioritize your braindumps into a plan |
/task-init | Create an actionable task folder |
/task-run | Execute a task from its plan |
/task-done | Archive completed work |
Project setup:
| Skill | What it does |
|---|---|
/docs-setup | Set up docs, features, and task structure in any project |
New feature? Start here:
/feature-init
Brain full of stuff? Start here:
/task-braindump
Kult Byrå — a design & tech agency in Norway.
npx claudepluginhub kult-byra/electric-monk --plugin kult-featuresInteractive feature development workflow from idea to implementation (Requirements → Design → Tasks → Execute)
AI Coding Agent - PRD to tasks to implementation loop
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Feature lifecycle management with skill-centric architecture. Capture ideas (idea.md), plan implementations (plan.md), and complete with quality gates (shipped.md). Status determined by file presence with auto-generated DASHBOARD.md. Shared Python library for dashboard generation with minimal hooks.
Spec-driven development for big features. When features get too big, plan mode gets too vague—leading to hallucinations during implementation. ShipSpec replaces vague plans with structured PRDs, technical designs, and ordered tasks that keep Claude grounded.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review