npx claudepluginhub oxhagolli/clawdskillz --plugin setup-skillsUse this skill when writing or reviewing code to ensure changes are minimal, clear, and spec-aligned. Catches scope creep in code, removes unnecessary additions, and enforces repo standards. Trigger during code review or before committing changes.
Use this skill after design decisions or major code changes to update documentation. Creates per-directory CLAUDE.md files and maintains top-level CLAUDE.md and ARCHITECTURE.md. Trigger after completing features, refactoring, or architectural changes.
Use this skill when installing libraries, choosing dependencies, or integrating with external APIs and frameworks. Activates research mode to find the latest maintained libraries, discover deprecations, and gather current best practices. Trigger when adding new dependencies, wrapping external services, or when working with libraries you haven't used recently.
Use this skill after every code change to run linting and type checking. Ensures code passes all lint checks, types are correct and consistent, and typing patterns match repo conventions. Trigger after writing or modifying code.
Use this skill after a plan has been approved and development is about to start. Breaks down the implementation into independent work streams that can be executed by subagents in parallel. Each subagent has access to all available skills. Trigger when transitioning from planning to implementation, especially for multi-file or multi-component work.
Use this skill when defining requirements, scoping features, or clarifying what to build and why. Activates a product manager mindset focused on business alignment, scope control, and clarity. Trigger when starting a new feature, refining requirements, or when scope seems to be expanding.
Use this skill when creating a new Python project or setting up tooling for an existing one. Runs pyscaffold, configures pre-commit with comprehensive hooks, and sets up CLAUDE.md for documentation. Trigger when starting new projects or adding standard tooling.
Use this skill when the user wants you to reason through a problem with extra rigor and self-criticism. Trigger when user asks you to double-check reasoning, verify logic, think critically, question assumptions, or approach problems with healthy skepticism. Also use when solving complex problems where errors would be costly.
Use this skill when planning implementations, reviewing proposals, or evaluating technical approaches. Activates a skeptical senior engineer mindset that pokes reasonable holes in plans before execution. Trigger when user is planning features, designing systems, proposing solutions, or wants a critical review of an approach.
Use this skill during the planning stage to surface edge cases, boundary conditions, and testable scenarios. Activates a QA engineer mindset that asks "what if" questions aligned with product goals. Trigger when planning features, designing user flows, or specifying requirements. This is for planning only - not for writing actual tests.
Use this skill when writing unit tests or integration tests for code. Prefers integration tests that reflect real usage, keeps tests fast and simple, and avoids over-mocking. Trigger after implementing features or when adding test coverage.
Use this skill when evaluating business ideas, product directions, or market opportunities. Plays devil's advocate, researches competitors, analyzes market fit, and challenges weak thinking. Trigger when proposing new products, pivots, or major strategic decisions.
Engineering mindset skills for Claude Code. These skills activate different professional personas - skeptical engineers, pragmatic PMs, rigorous thinkers - to improve the quality of AI-assisted development.
| Skill | Phase | Purpose |
|---|---|---|
| self-doubt | Meta | Question your reasoning step-by-step |
| venture-capitalist | Pre-product | Validate business ideas, research competitors |
| product-manager | Planning | Scope features, clarify requirements |
| skeptic-engineer | Planning | Poke holes in technical approaches |
| test-engineer | Planning | Surface edge cases and scenarios |
| parallel-orchestrator | Plan→Impl | Break work into parallel subagent streams |
| framework-engineer | Implementation | Research libraries, find deprecations |
| brevity-engineer | Implementation | Ensure minimal, spec-aligned code |
| linting-engineer | Implementation | Run linters, enforce type consistency |
| test-writer | Implementation | Write fast, meaningful tests |
| documentation-engineer | Implementation | Maintain CLAUDE.md and docs |
| scaffold-engineer | Setup | Initialize projects with proper tooling |
Add the marketplace to Claude Code:
/plugin marketplace add oxhagolli/clawdskillz
Then install the plugin set you want:
# Install all skills
/plugin install all-skills@clawdskillz
# Or install by category
/plugin install planning-skills@clawdskillz
/plugin install implementation-skills@clawdskillz
/plugin install setup-skills@clawdskillz
/plugin install thinking-skills@clawdskillz
Install a specific plugin directly:
/plugin install all-skills@oxhagolli/clawdskillz
Copy the skills you want into your project's .claude/skills/ directory:
# Clone the repo
git clone https://github.com/oxhagolli/clawdskillz.git
# Copy specific skills
cp -r clawdskillz/skills/skeptic-engineer .claude/skills/
cp -r clawdskillz/skills/product-manager .claude/skills/
Copy the content of any SKILL.md directly into your project's CLAUDE.md:
cat clawdskillz/skills/skeptic-engineer/SKILL.md >> CLAUDE.md
self-doubt - Rigorous step-by-step reasoning with self-questioningventure-capitalist - Business validation, competitor research, market analysisproduct-manager - Requirements, scope control, clarityskeptic-engineer - Technical approach critique, architecture riskstest-engineer - Edge cases, scenarios to handle during planningparallel-orchestrator - Break approved plans into parallel subagent work streamsframework-engineer - Library selection, deprecation checks, best practicesbrevity-engineer - Code minimalism, repo standards, scope in codelinting-engineer - Lint execution, type checking, type consistencytest-writer - Integration tests, fast tests, pragmatic coveragedocumentation-engineer - CLAUDE.md per directory, ARCHITECTURE.mdscaffold-engineer - Project initialization with pyscaffold, pre-commitAll of the above.
Once installed, skills activate automatically based on context. You can also invoke them explicitly:
Apply the skeptic-engineer skill: I'm planning to rewrite our auth system to use JWTs...
Use self-doubt: Walk me through why this algorithm is O(n log n)...
Apply venture-capitalist: I want to build a new SaaS for...
Each skill has a clear domain and explicitly defers to other skills:
Idea & Design:
venture-capitalist → "Should this exist?" (market, competition)
↓
product-manager → "What exactly should it do?" (scope, requirements)
↓
skeptic-engineer → "Will this approach work?" (architecture, risks)
↓
test-engineer → "What scenarios must we handle?" (edge cases)
Plan to Implementation:
parallel-orchestrator → "How do we parallelize this?" (subagent coordination)
↓
┌────┴────┐
▼ ▼
[Subagent] [Subagent] → Each runs implementation skills
└────┬────┘
▼
Integration
Implementation (per subagent):
framework-engineer → "Which libraries should we use?" (dependencies)
↓
brevity-engineer → "Is this code minimal?" (scope in code)
↓
linting-engineer → "Does this pass checks?" (lint, types)
↓
test-writer → "Are tests meaningful and fast?" (test implementation)
↓
documentation-engineer → "Is this documented?" (CLAUDE.md, docs)
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Creative skill for generating algorithmic and generative art. Produces visual designs using mathematical patterns, fractals, and procedural generation.
Frontend design skill for UI/UX implementation
Humanise text and remove AI writing patterns. Detects and fixes 24 AI tell-tales including inflated language, promotional tone, AI vocabulary, filler phrases, sycophantic tone, and formulaic structure.
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). Proactively activates in projects with cacheComponents: true, providing patterns for 'use cache' directive, cacheLife(), cacheTag(), cache invalidation, and parameter permutation rendering.