Skill Creator
TheBushidoCollective
322 published skills · 15,134 GitHub stars across the catalog. View on GitHub ↗
architecture-design
Use when designing system architecture, making high-level technical decisions, or planning major system changes. Focuses on structure, patterns, and long-term strategy.
baseline-restorer
Use when multiple fix attempts fail and you need to systematically restore to a working baseline and reimplement instead of fixing broken code.
boy-scout-rule
Use when modifying existing files, refactoring, improving code quality, or touching legacy code by applying the Boy Scout Rule to leave code better than you found it.
code-reviewer
Use during verification phase when conducting thorough code reviews and providing constructive feedback based on universal software quality principles.
debugging
Use when investigating bugs, diagnosing issues, or understanding unexpected behavior. Provides systematic approaches to finding root causes.
documentation
Use when creating or updating documentation including READMEs, API docs, inline comments, or technical guides. Focuses on clarity and usefulness for the intended audience.
explainer
Use when explaining code, technical concepts, or implementation decisions. Provides structured approach to creating clear, understandable explanations tailored to the audience.
legacy-code-safety
Use when modifying, removing, or refactoring code that lacks test coverage. Emphasizes the danger of untested changes and the RGR workflow to add characterization tests before modifications.
orthogonality-principle
Use when designing modules, APIs, and system architecture requiring independent, non-overlapping components where changes in one don't affect others.
performance-optimization
Use when optimizing code for performance, reducing bundle size, improving load times, or fixing performance bottlenecks. Emphasizes measurement-driven optimization.
professional-honesty
Use when responding to questions or providing information requiring professional honesty and directness over excessive agreeableness.
project-memory
Use when setting up or organizing Claude Code project memory (CLAUDE.md, .claude/rules/) for better context awareness, consistent behavior, and project-specific instructions.
proof-of-work
Use automatically during development workflows when making claims about tests, builds, verification, or code quality requiring concrete evidence to ensure trust through transparency.
refactoring
Use when restructuring code to improve quality without changing external behavior. Emphasizes safety through tests and incremental changes.
simplicity-principles
Use when designing solutions, adding features, or refactoring by applying KISS, YAGNI, and Principle of Least Astonishment to write simple, predictable code.
solid-principles
Use during implementation when designing modules, functions, and components requiring SOLID principles for maintainable, flexible architecture.
structural-design-principles
Use when designing modules and components requiring Composition Over Inheritance, Law of Demeter, Tell Don't Ask, and Encapsulation principles that transcend programming paradigms.
technical-planning
Use when creating implementation plans for features or tasks. Focuses on tactical execution planning with clear tasks, dependencies, and success criteria.
sre-incident-response
Use when responding to production incidents following SRE principles and best practices.
sre-monitoring-and-observability
Use when building comprehensive monitoring and observability systems.
sre-reliability-engineering
Use when building reliable and scalable distributed systems.
sop-authoring
Use when writing or creating new Standard Operating Procedures (SOPs) for AI agents. Covers effective SOP writing, clarity principles, and actionable instruction design.
sop-maintenance
Use when updating, versioning, deprecating, or maintaining existing Standard Operating Procedures. Covers keeping SOPs accurate, relevant, and synchronized with implementation changes.
sop-rfc2119
Use when writing SOPs that require precise requirement levels using RFC 2119 constraint keywords (MUST, SHOULD, MAY). Covers proper usage of requirement keywords for deterministic agent behavior.