By bcbeidel
Skills for the full work lifecycle — scope, plan, start, verify, finish, audit, and retro.
Use when implementation is complete and validated, to decide how to integrate the work. Presents structured options for merge, PR, keep, or discard with safety verification. Use when the user wants to "finish", "done", "merge this", "create PR", "wrap up", "ship it", or after completing all tasks and validation in a plan.
Use when the user has a spec or requirements for a multi-step task, before touching code. Creates structured implementation plans with explicit lifecycle management and verification criteria. Use when the user wants to "plan", "make an implementation plan", "break this down into tasks", or needs to turn a design into actionable work items.
Use before creating implementation plans. Explores user intent, requirements, and design through structured divergent-then-convergent thinking. Produces a design document, not code. Use when the user wants to "brainstorm", "explore", "design", "figure out what to build", or needs to think through a problem before planning.
Use when you have an approved implementation plan to execute. Handles sequential execution, progress tracking, and recovery. Enforces the approval gate. Use when the user wants to "execute the plan", "run the plan", "implement this plan", "start work", or "start building".
Verifies completed work against validation criteria. Works in two modes: with a plan (runs the plan's Validation section) or ad-hoc (builds checks from git diff, project config, and project docs). Use when the user wants to "validate the work", "verify the work", "check my work", "verify my changes", "does this look right", "run checks", "check if done", "are we done", "did it work", or after completing all tasks in a plan.
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.
Experimental — This project is under active development. APIs, skill interfaces, and document conventions may change without notice.
A Claude Code plugin marketplace for building and maintaining structured project context, with AI-assisted research, source verification, and quality validation.
Note: GitHub repo rename from
wos→toolkitis a pending manual step.
Five self-contained plugins, each independently installable:
| Plugin | Install | Skills |
|---|---|---|
wiki | claude plugin install bcbeidel/toolkit --plugin wiki | setup, research, ingest, lint |
build | claude plugin install bcbeidel/toolkit --plugin build | build-skill, build-rule, build-hook, build-subagent, refine-prompt |
check | claude plugin install bcbeidel/toolkit --plugin check | check-skill, check-rule, check-hook, check-subagent, check-skill-chain |
work | claude plugin install bcbeidel/toolkit --plugin work | scope-work, plan-work, start-work, verify-work, finish-work |
consider | claude plugin install bcbeidel/toolkit --plugin consider | 16 mental models + meta |
Knowledge — build and maintain project context documents:
claude plugin install bcbeidel/toolkit --plugin wiki
Build tooling — create and audit Claude Code skills and rules:
claude plugin install bcbeidel/toolkit --plugin build
claude plugin install bcbeidel/toolkit --plugin check
Full suite — complete toolkit for AI-assisted project work:
claude plugin install bcbeidel/toolkit --plugin wiki
claude plugin install bcbeidel/toolkit --plugin build
claude plugin install bcbeidel/toolkit --plugin check
claude plugin install bcbeidel/toolkit --plugin work
claude plugin install bcbeidel/toolkit --plugin consider
# Install Python packages and dev dependencies
pip install -e plugins/wiki -e plugins/check -e ".[dev]"
# Run tests
python -m pytest plugins/wiki/tests/ plugins/check/tests/ -v
# Lint
ruff check plugins/
plugins/
build/ # Plugin: create skills, rules, hooks, subagents
check/ # Plugin: audit skills, rules, hooks, subagents
wiki/ # Plugin: setup, research, ingest, lint
wiki/ # Python package
scripts/ # Shared CLI scripts
skills/ # Skill definitions
tests/ # Tests
work/ # Plugin: scope-work, plan-work, start-work, verify-work, finish-work
consider/ # Plugin: structured mental models
docs/ # Documentation, plans, and research
context/ # Topic areas
plans/ # Design docs and implementation plans
research/ # Research artifacts
.claude-plugin/
marketplace.json # Plugin marketplace manifest
gh CLI (for work:finish-work skill)npx claudepluginhub bcbeidel/toolkit --plugin workSkills for creating and refining Claude Code skills, rules, hooks, and subagents.
Structured mental models for decision-making — first principles, Occam's razor, inversion, and more.
Skills for building and maintaining structured project context — setup, research, ingest, and lint.
Structured implementation planning, interactive annotation review, and autonomous plan execution
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns