Development

Reduce context usage with MECW principles (keep under 50% of total window).Triggers: context pressure, token usage, MECW, context window, optimization,decomposition, workflow splitting, context management, token optimizationUse when: context usage approaches 50% of window, tasks need decomposition,complex multi-step operations planned, context pressure is highDO NOT use when: simple single-step tasks with low context usage.DO NOT use when: already using mcp-code-execution for tool chains.Use this skill BEFORE starting complex tasks. Check context levels proactively.

Master Python asyncio, concurrent programming, and async/await patternsfor high-performance applications.Triggers: asyncio, async/await, coroutines, concurrent programming, async API,I/O-bound, websockets, background tasks, semaphores, async context managersUse when: building async APIs, concurrent systems, I/O-bound applications,implementing rate limiting, async context managersDO NOT use when: CPU-bound optimization - use python-performance instead.DO NOT use when: testing async code - use python-testing async module.Consult this skill for async Python patterns and concurrency.

Use a Layered (N-Tier) architecture to separate presentation, domain logic, anddata access responsibilities within a system.Triggers: layered architecture, n-tier, separation of concerns, presentation layer,data access layer, service layer, traditional architecture, monolith structure,layer enforcement, dependency directionUse when: building traditional applications with clear boundaries, working withmoderate-sized teams, needing familiar and well-understood patterns, compliancerequirements demand clear separationDO NOT use when: selecting from multiple paradigms - use architecture-paradigms first.DO NOT use when: high scalability needs independent component scaling.DO NOT use when: teams need independent deployment cycles - use microservices.Consult this skill when implementing layered patterns or enforcing layer boundaries.

Prevents overengineering through worthiness scoring, opportunity cost comparison,and branch threshold monitoring.Triggers: scope creep, overengineering, worthiness score, branch size, YAGNI,feature evaluation, scope validation, anti-overengineering, opportunity costUse when: evaluating features during brainstorming, planning new functionality,branches approach size limits (1000/1500/2000 lines, 15/25/30 commits)DO NOT use when: feature is already approved and in progress.DO NOT use when: simple bug fixes with clear scope.Use this skill BEFORE implementing any new feature. This is NON-NEGOTIABLEfor scope control.

Decompose systems into a suite of small, independently deployable services alignedto specific business capabilities.Triggers: microservices, service decomposition, independent deployment, team autonomy,distributed system, API gateway, service mesh, bounded contexts, polyglot persistenceUse when: teams need high autonomy and independent releases, different capabilitieshave distinct scaling needs, strong DevOps/SRE maturity exists, polyglot tech stacks neededDO NOT use when: selecting from multiple paradigms - use architecture-paradigms first.DO NOT use when: small team with low organizational complexity.DO NOT use when: lack of DevOps maturity or limited platform engineering resources.DO NOT use when: strong transactional consistency required across operations.Consult this skill when designing or evolving microservices architectures.

Enforces "prove before claim" discipline - validation, testing, and evidencerequirements before declaring work complete.Triggers: completion, finished, done, working, should work, configured,ready to use, implemented, fixedUse when: claiming ANY work is complete, recommending solutions, statingsomething will work, finishing implementationsDO NOT use when: explicitly asking questions or requesting clarificationDO NOT use when: work is clearly in-progress and not claiming completionCRITICAL: This skill is MANDATORY before any completion claim. Violationsresult in wasted time and eroded trust.

Guide to effective Claude Code skill authoring using TDD methodology andpersuasion principles.Triggers: skill authoring, skill writing, new skill, TDD skills, skill creation,skill best practices, skill validation, skill deployment, skill complianceUse when: creating new skills from scratch, improving existing skills withlow compliance rates, learning skill authoring best practices, validatingskill quality before deployment, understanding what makes skills effectiveDO NOT use when: evaluating existing skills - use skills-eval instead.DO NOT use when: analyzing skill architecture - use modular-skills instead.DO NOT use when: writing general documentation for humans.YOU MUST write a failing test before writing any skill. This is the Iron Law.

Fix GitHub issues using subagent-driven-development with parallel executionwhere appropriate.Triggers: fix issue, github issue, issue resolution, subagent development,parallel execution, issue workflow, gh issue, fix githubUse when: addressing GitHub issues systematically, multiple related issuesneed fixing, tasks can be parallelized across subagents, quality gates neededbetween task batchesDO NOT use when: single simple fix - just implement directly.DO NOT use when: issue needs clarification - comment first to clarify scope.Uses subagents for parallel execution with code review gates between batches.

Intensive mathematical analysis for numerical stability, algorithm correctness,and alignment with authoritative standards.Triggers: math review, numerical stability, algorithm correctness, mathematicalverification, scientific computing, numerical analysis, derivation checkUse when: reviewing math-heavy code, verifying algorithm correctness, checkingnumerical stability, aligning with mathematical standardsDO NOT use when: general algorithm review - use architecture-review.DO NOT use when: performance optimization - use parseltongue:python-performance.Use this skill for mathematical code verification.

Methodology for summarizing changes, extracting insights, and identifying follow-up actions.Triggers: catchup, what changed, summarize changes, context acquisition, handoff,progress review, recent changes, git log analysis, sprint summaryUse when: resuming work after absence, preparing handoff documentation, reviewingsprint progress, analyzing git history for contextDO NOT use when: doing detailed diff analysis - use diff-analysis instead.DO NOT use when: full code review needed - use review-core instead.Use this skill to quickly understand "what changed and what matters".

Workflow for capturing evidence and citations to create reproducible analysesand audit trails.Triggers: evidence capture, citations, reproducible analysis, audit trail,documentation, evidence logging, findings documentationUse when: conducting any review that needs evidence trails, creating auditdocumentation, ensuring reproducibility of analysesDO NOT use when: quick informal checks without documentation needs.DO NOT use when: structured output is the focus - use structured-output.Use this skill as foundation for all evidence-based review workflows.

Transform tool-heavy workflows into MCP code execution patterns for token savings and optimized processing.Triggers: MCP, code execution, tool chain, data pipeline, tool transformation, batch processing, workflow optimizationUse when: >3 tools chained sequentially, large datasets (>10k rows), large files (>50KB), context usage >25%DO NOT use when: simple tool calls that don't chain.DO NOT use when: context pressure is low and tools are fast.Use this skill BEFORE building complex tool chains. Optimize proactively.

Communicating the intended behavior and context of code through clear documentation and comments, and sharing knowledge with the team.

Incorporating security at every step of software development – writing code that defends against vulnerabilities and protects user data.

OWASP API Security Top 10 (2023) と Rust セキュリティベストプラクティス。脆弱性検出。Use when: セキュリティ、脆弱性、OWASP、認証、認可、監査を依頼された時。

Ensuring software correctness and reliability by writing automated tests, using quality assurance tools, and systematically debugging issues.

Competence in data analytics and machine learning, enabling developers to build data-driven features and integrate AI/ML capabilities.

Writing clean, understandable, and self-documenting code that is easy to review and maintain over time.

Skill in automating software deployment pipelines and managing cloud infrastructure for scalable, reliable systems.

Working effectively with others in coding projects – including code reviews, clear communication, and contributing to shared or open-source codebases.