Apply continuous improvement principles to iteratively enhance processes, code quality, team practices, and system performance through small, incremental changes. Use when improving development processes, optimizing workflows, reducing waste, enhancing code quality over time, implementing retrospective learnings, or fostering a culture of continuous improvement.

Kanban QA role. USE WHEN user says /kanban-qa OR wants to review completed kanban tasks.

Kanban continuous health monitoring daemon. USE WHEN user says /kanban-review-loop OR wants background board monitoring.

Use when the user requests a repository review, code assessment, or honest evaluation of their codebase. Provides brutally honest AI-powered reviews with market-aware Karen Scores (0-100) analyzing over-engineering, completion honesty, and practical value. Available as GitHub Action or IDE tool.

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Guidelines to improve coding style and avoid common pitfalls. Use when writing, reviewing, or refactoring any kind of code.

Apply kinemotion development standards. Use when writing Python code, creating tests, modifying the kinemotion codebase, or reviewing code quality.

Principes KISS, DRY, YAGNI. Use when reviewing code quality or refactoring.

PR Review 修复模式库。在处理 PR Review 评论时自动查阅，寻找已知问题模式和解决方案。

Fix flagged Kodex topics by generating updated content

kotlin-android-reviewer

Generate comprehensive @Preview functions for Jetpack Compose composables. Analyzes component parameters, states, and dependencies to create previews covering all visual states, edge cases, and configurations.

Strict technical code review for Kotlin Jetpack Compose. Analyzes @Composable functions for recomposition issues, stability violations, memory leaks, state management antipatterns, accessibility gaps, and performance problems.

kotlin-multiplatform-reviewer

kotlin-spring-reviewer

KPI for measuring and improving code quality. Covers lint errors, type safety, test coverage, and verification pass rates. Use to ensure code meets quality standards.

Generate comprehensive Pull Request descriptions by analyzing git changes, commit history, Linear issues, and code structure for both GitLab and GitHub

Use when asked to recreate commits with narrative-quality history on the current branch.

Reviews Kubernetes manifests for best practices, security, and homelab standards compliance. Use when reviewing YAML files, K8s manifests, Helm values, or ArgoCD applications.

Kubernetes container orchestration. Use when deploying to Kubernetes, writing manifests, configuring Helm charts, or troubleshooting cluster issues.

Conduct structured portfolio health checks for existing Lagoon users, including risk assessment, performance analysis, rebalancing guidance, and forward projections. Activates for portfolio review, position check, and rebalancing requests.

Reviews AWS Lambda functions for performance, memory configuration, and cost optimization. Activates when users write Lambda handlers or discuss Lambda performance.

Audit landing page for conversion optimization including headline-ad alignment, promise-delivery consistency, trust signals, and friction points. Use when diagnosing low landing page CTR, optimizing funnels, or reviewing pages before launch.

Architect-level development, audit, and migration of multi-agent systems using LangGraph (v1+) and LangChain (v1+). Use when building or refactoring supervisor/subagent architectures, orchestrator-worker workflows, routing/hand-offs, agentic RAG, memory (short + long-term), state + context engineering, guardrails + human-in-the-loop, MCP tool integration, observability (LangSmith/OpenTelemetry), deployment, and performance/cost optimization — or when migrating off deprecated patterns like `langgraph.prebuilt.create_react_agent` and libraries like `langgraph-supervisor(-py)`, LlamaIndex agents, CrewAI, Agno, or OpenAI Agents.

Validates LangGraph implementations for correctness, consistency, and integration readiness. Use this skill when implementing, reviewing, or debugging any LangGraph code - agents, nodes, subgraphs, state schemas, or graph compositions. Prevents common LangGraph failures including orphaned nodes, state key mismatches, broken conditional edges, and integration incompatibilities. Triggers on LangGraph development tasks, code reviews, or when debugging graph execution issues.

Analyze code and documentation for non-inclusive language, understanding context and intent before flagging issues. Use when reviewing code for biased terms, gendered language, or problematic terminology.

Code quality tooling with PHPStan, Pint, and strict types. Use when working with code quality, static analysis, formatting, or when user mentions PHPStan, Pint, quality, static analysis, type safety, code style, linting.

Ensures the AI uses the latest stable versions of programming languages and adheres to current best practices in all files.

LaTeX builds with latexmk and live preview. TRIGGERS - latexmk, LaTeX build, live preview, compilation.

Say "launch a swarm" to spawn 5 parallel agents that review your work through Structure, Protection, Correctness, Evolution, and Value lenses. Use during planning, building, or validation phases.

Critique UI layouts and provide specific, actionable fixes. Use when something feels off but you can't articulate why, before finalizing designs, or after adding new components. Outputs diagnosis of visual hierarchy, spacing, alignment, color balance issues with exact CSS/Tailwind fixes.

|-

Use for implementing features, writing production TypeScript/Langium code, code review guidance, and ensuring technical quality. Activate when implementing new functionality, reviewing PRs, or optimizing performance.

'Analyze Claude Code sessions to learn what went right/wrong and suggest high-confidence improvements to skills. Use when asked to analyze a session, learn from a session, or review workflow effectiveness.'

Manage learned patterns - list, view, archive, boost or penalize confidence. Use when you want to see what patterns Claude has learned, review pattern effectiveness, or manage the pattern library.

Generate a quick compliance checklist from the Four Learning Design Pillars. Use when users want a practical checklist for reviewing content, a quick audit tool, or verification questions for specific pillars.

Review educational content against the Four Learning Design Pillars framework. Use when users want to evaluate course materials, lessons, tutorials, e-learning modules, or any instructional content for alignment with evidence-based learning design principles. Provides structured feedback with specific principle references (e.g., 1.1.1, 2.3.4) and actionable recommendations.

literature-review for evidence-based learning research and evaluation.

Create effective peer assessment that develops evaluation skills and provides feedback.

quality-assurance for learning operations and program management.

Optimize long-term retention through scientifically-spaced review schedules.

Use this skill when optimizing Leavn's App Store presence, researching keywords, or responding to reviews.

Expert system for identifying deprecated patterns, suggesting refactoring to modern standards (Python 3.12+, ES2024+), checking test coverage, and leveraging AI-powered tools. Proactively applied when users request refactoring, updates, or analysis of legacy codebases.

Provides expert legal guidance on technology law, contracts, compliance, and intellectual property matters. Specializes in data privacy regulations, software licensing, terms of service, and risk miti

Legal document analysis, contract review, and compliance guidance for business and personal legal matters

Legal and compliance expertise for corporate governance, contract analysis, regulatory compliance (SOX, GDPR, HIPAA), risk assessment, intellectual property, and litigation management. Use when reviewing contracts, ensuring compliance, or managing legal risk.

Legal Sanity Review Workflow — mandatory pre-gate in the cross-review cycle

Capture and review lessons learned from coding sessions. Use to record insights, read past lessons, and improve over time.

CREATE/REPLAN Epics from scope (3-7 Epics). Batch Preview + Auto-extraction. Decompose-First Pattern. Auto-discovers team ID.