持續整合/部署

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Guides systematic code refactoring following the DRY (Don't Repeat Yourself) principle. Use when user asks to eliminate code duplication, refactor repetitive code, apply DRY principle, or mentions code smells like copy-paste, magic numbers, or repeated logic. Implements a 4-step workflow from identifying repetition to verified refactoring.

Aggregates and summarizes the latest AI news from multiple sources including AI news websites and web search. Provides concise news briefs with direct links to original articles. Activates when user asks for 'today's AI news', 'AI updates', 'latest AI developments', or mentions wanting a 'daily AI briefing'.

Systematic approach for creating minimal-change, reversible implementation plans. Claude invokes this skill when transforming requirements/research into executable blueprints. Emphasizes simplicity, safety, and clear verification steps.

Validates KCL Crossplane compositions with comprehensive checks including formatting, syntax validation, and rendering tests. Automatically activates when working with KCL files, Crossplane compositions, or before commits touching infrastructure/base/crossplane/configuration/. Prevents CI failures and catches critical bugs like the mutation pattern.

Orchestrate and run appropriate pensive review skills based on codebaseanalysis and context.Triggers: code review, unified review, full review, review orchestration,multi-domain review, intelligent review, auto-detect reviewUse when: general review needed without knowing which specific skill applies,full multi-domain review desired, integrated reporting neededDO NOT use when: specific review type known - use bug-review, test-review, etc.DO NOT use when: architecture-only focus - use architecture-review.Use this skill when orchestrating multiple review types.

Architecture-aware project initialization combining online research with archetype selection.Triggers: project initialization, new project, architecture decision, project setup,which architecture, choose architecture, project architectureUse when: initializing a new project and need to select an appropriate architecturebased on project type, team size, domain complexity, and current best practicesDO NOT use when: architecture is already decided - use project-init instead.DO NOT use when: exploring multiple architectures - use architecture-paradigms instead.

Create clear, testable specifications with user stories and acceptance criteria.Triggers: spec writing, feature specification, requirements, user storiesUse when: creating new specifications or writing acceptance criteriaDO NOT use when: generating implementation tasks - use task-planning.

Design and construct virtual memory palaces for spatial knowledge organizationusing mnemonic techniques.Triggers: memory palace, spatial organization, mnemonic, knowledge architecture,domain mapping, layout design, memory structure, recall enhancementUse when: creating new memory palace structures, organizing complex domains,designing spatial layouts for knowledge retentionDO NOT use when: quick knowledge search - use knowledge-locator instead.DO NOT use when: session-specific context - use session-palace-builder.Consult this skill when designing permanent memory palace structures.

Reusable patterns and templates for Claude Code skill and hook development.Triggers: validation patterns, error handling, testing templates, workflow patterns,shared patterns, reusable templates, DRY patterns, common workflowsUse when: creating new skills or hooks that need consistent patterns, implementingvalidation logic, setting up error handling, creating test scaffolding,referencing standard workflow structuresDO NOT use when: pattern is specific to one skill only.DO NOT use when: pattern is still evolving - wait for stability.DO NOT use when: pattern is context-dependent requiring variations.Reference these patterns to validate consistency across the ecosystem.

Shared infrastructure and patterns for spec-kit specification-driven development.Triggers: spec-kit patterns, tech-stack patterns, checklist dimensions,artifact structure, specification infrastructure, shared templatesUse when: developing new spec-kit skills, referencing standard patterns,ensuring consistency across specification workflowsDO NOT use directly: this skill is infrastructure for other spec-kit skills.Provides reusable patterns consumed by all spec-kit commands and skills.

Compose processing stages using a pipes-and-filters model for ETL, mediaprocessing, or compiler-like workloads.Triggers: pipeline architecture, pipes and filters, ETL, data transformation,stream processing, CI/CD pipeline, media processing, batch processingUse when: data flows through fixed sequence of transformations, stages can beindependently developed and tested, parallel processing of stages is beneficialDO NOT use when: selecting from multiple paradigms - use architecture-paradigms first.DO NOT use when: data flow isn't sequential or predictable.DO NOT use when: complex branching/merging logic dominates.Consult this skill when designing data pipelines or transformation workflows.

Serverless FaaS for event-driven workloads with minimal infrastructure management.Triggers: serverless, FaaS, Lambda, event-driven, pay-per-useUse when: workloads are event-driven with bursty trafficDO NOT use when: long-running processes or stateful operations required.

Guide to deciding whether to escalate from a lower model (haiku/sonnet) toa higher model (sonnet/opus).Triggers: model escalation, haiku to sonnet, sonnet to opus, reasoning depth,task complexity, model selection, capability trade-offUse when: evaluating whether to escalate models, facing genuine complexityrequiring deeper reasoning, novel patterns with no existing solutions,high-stakes decisions requiring capability investmentDO NOT use when: thrashing without investigation - investigate root cause first.DO NOT use when: time pressure alone - urgency doesn't change task complexity.DO NOT use when: "just to be safe" - assess actual complexity instead.NEVER escalate without investigation first. This is the Iron Law.

Python testing with pytest, fixtures, mocking, and TDD workflows.Triggers: pytest, unit tests, test fixtures, mocking, TDD, test suite, coverage,test-driven development, testing patterns, parameterized testsUse when: writing unit tests, setting up test suites, implementing TDD,configuring pytest, creating fixtures, async testingDO NOT use when: evaluating test quality - use pensive:test-review instead.DO NOT use when: infrastructure test config - use leyline:pytest-config.Consult this skill for Python testing implementation and patterns.

Coarse-grained service architecture for deployment independence without microservices complexity.Triggers: service-based, SOA, coarse-grained services, domain servicesUse when: teams need deployment independence without microservices complexityDO NOT use when: fine-grained scaling needed - use microservices.

Employ the Hexagonal (Ports & Adapters) pattern to decouple domain logic frominfrastructure, maximizing flexibility and testability.Triggers: hexagonal architecture, ports and adapters, infrastructure independence,dependency inversion, clean architecture, domain isolation, adapter pattern,infrastructure abstraction, database independence, framework independenceUse when: designing systems with strong business logic separation, anticipatinginfrastructure changes, needing easy mocking for tests, building portable domain codeDO NOT use when: selecting from multiple paradigms - use architecture-paradigms first.DO NOT use when: building simple CRUD apps without complex domain logic.Consult this skill when implementing hexagonal patterns or migrating to port-based design.

Design skills as modular building blocks for predictable token usage.Triggers: skill design, skill architecture, modularization, token optimization,skill structure, refactoring skills, new skill creation, skill complexityUse when: creating new skills that will be >150 lines, breaking down complexmonolithic skills, planning skill architecture, refactoring overlapping skills,reviewing skill maintainability, designing skill module structureDO NOT use when: evaluating existing skill quality - use skills-eval instead.DO NOT use when: writing prose for humans - use writing-clearly-and-concisely.DO NOT use when: need improvement recommendations - use skills-eval.Use this skill BEFORE creating any new skill. Check even if unsure.

Shared infrastructure and reusable modules for all pensive review skills.Triggers: pensive patterns, review workflow, output templates, quality checklists,pensive infrastructure, shared review patternsUse when: other pensive skills need common patterns, creating new review skills,ensuring consistency across pensive pluginDO NOT use directly: this skill is infrastructure for other pensive skills.This skill provides shared patterns consumed by other pensive skills.

CI/CD and operations practices including GitHub Actions, Kubernetes, and operational tooling. Use when working with deployment and infrastructure.