224 skills · sorted by relevance
Autonomous iterative refactoring workflow. Scans for tactical code quality improvements (DRY, dead code, naming, complexity), implements through SMEs, verifies with QA, commits atomically, and loops until no improvements remain.
The English summary is being prepared. Showing the original description.
Applies safe auto-fixes for low-risk audit findings (unused imports, dead code, commented-out code). Confidence >=90% only. Creates single commit with summary.
The English summary is being prepared. Showing the original description.
Post-build pass reducing complexity without changing behavior. Catches dead code, needless abstractions, over-engineering. NOT for style (mk:clean-code) or diff review (mk:review).
The English summary is being prepared. Showing the original description.
Post-implementation simplification pass. Reduces complexity without changing behavior. Use after Phase 3 (Build GREEN) and before Phase 4 (Review). Catches dead code, unnecessary abstractions, over-engineering, and redundant patterns. Triggers on "simplify", "clean up", "reduce complexity", "too complex". NOT for style/convention enforcement (see mk:clean-code); NOT for reviewing diffs or PRs (see mk:review).
The English summary is being prepared. Showing the original description.
Audit one or all supported agent harnesses (claude, codex, opencode, pi, omp, antigravity, cursor, grok) for config efficiency, hook overhead, permission friction, plugin and MCP cost, skill metadata portability, dead config, and measured session friction. Use when invoked as `$optimize-harness [harness ...] [focus]`, or when the user asks to optimize or compare agent harness configuration.
The English summary is being prepared. Showing the original description.
Sistema autônomo multi-agente para startups em Claude Code. Ativado com "Loki Mode". Orquestra 100+ agentes especializados em engenharia, QA, DevOps, segurança, dados/ML, operações comerciais, marketing, RH e sucesso do cliente. Vai de PRD para produto totalmente implantado e gerando receita com zero intervenção humana. Inclui ferramenta Task para despacho de subagentes, revisão de código paralela com 3 revisores especializados, triagem de problemas baseada em severidade, fila de tarefas distribuída com tratamento de dead letter, implantação automática em provedores de nuvem, testes A/B, loops de feedback de clientes, resposta a incidentes, circuit breakers e auto-recuperação. Gerencia limites de taxa via checkpoints de estado distribuído e retomada automática com backoff exponencial. Requer flag --dangerously-skip-permissions.
The English summary is being prepared. Showing the original description.
Use between coding-agent runs (Codex, Claude Code, Cursor, Aider, etc.) to stop the project from drifting, overbuilding, or accumulating dead weight. Forces a read-only audit that classifies every active item as KEEP / DELAY / REMOVE and ends with a single, unambiguous next action. Trigger on "audit before continuing", "what should I do next", "this project got too big", "between runs", "trim scope", "stop adding stuff", or any signal that the project feels noisy and the next step is unclear. Do NOT load for trivial one-line fixes, when the next action is already obvious, or when you're mid-run and just need to keep going.
The English summary is being prepared. Showing the original description.
Use when asking project status, next priority, sprint health, blockers, deadlines, risk register, or daily brief generation.
The English summary is being prepared. Showing the original description.
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.
The English summary is being prepared. Showing the original description.
Deprecate APIs, features, or systems safely — announce, migrate consumers, sunset on a timeline, and document alternatives. Load when removing an old API, migrating users between implementations, sunsetting a feature, or the user asks about deprecation policy, migration guides, or breaking changes. Not for deleting dead code with zero consumers (use code-simplification). Distinct from meta `deprecate-skill` (skill library retirement).
The English summary is being prepared. Showing the original description.
Review MySQL and MariaDB database designs and production problems, including slow queries, locking, connection pools, and replica delays. Get concrete SQL or code changes and a validation plan that accounts for differences between engines and versions.
Build AWS applications with managed services that reduce server administration. Follow patterns for Lambda functions, HTTP APIs, database access, and queued background processing, with guidance on deployment and delays when functions first start.
Review a sprint or milestone by comparing planned work with actual results. Summarize completion, estimation gaps, and blockers, then produce a retrospective with specific improvement actions, owners, and deadlines for the next iteration.
Write and improve Go code with clear error handling, interface design, and tests. Build concurrent workflows, where tasks run independently, with controlled worker counts, cancellation, and explicit shutdown paths for background work.
Guide an AI agent through research, implementation, and verification with fewer interruptions. The skill emphasizes evidence, concise reporting, and saved progress notes, with three working modes that adjust how closely the user follows the work.
Create and manage tables in Feishu Bitable, including searching, adding, updating, and deleting rows. The skill covers 27 column types, advanced filters, batch operations, and views that provide different ways to display table data.
Make specific C# behavior testable by adding a minimal way to replace time, randomness, or other external dependencies. Preserve public APIs and production behavior, then run repeatable tests without real file access or waiting.
Investigate slow PostgreSQL and MySQL queries using execution plans, which show how queries run, and performance measurements. Develop index changes, SQL rewrites, and configuration adjustments, then validate their effects with measurements and monitoring.
Multi-stage pipeline for validating that vulnerability findings are real, reachable, and exploitable, preventing wasted effort on hallucinated findings, dead code paths, or findings with unrealistic preconditions.
The English summary is being prepared. Showing the original description.
Idiomatic context.Context usage in Golang — propagation through API boundaries, cancellation, timeouts and deadlines, request-scoped values, context.WithoutCancel for background work outliving requests. Apply when designing context propagation across layers, debugging leaked or unexpired contexts, choosing between context.Background/TODO/WithoutCancel, or storing values in context. Not for code that merely accepts ctx as first parameter.
The English summary is being prepared. Showing the original description.
Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.
The English summary is being prepared. Showing the original description.
Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.
The English summary is being prepared. Showing the original description.
Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) into a prioritized digest plus a referee-obligations tracker — classifying referee requests, R&R and editor correspondence, co-author threads, seminar and conference invites, and grant/admin deadlines, and proposing a human-gated action for each (draft reply, calendar hold, scaffold a project, snooze). Use when user says "triage my inbox", "check my academic email", "what needs my attention this week", "go through my mail", or when run as a scheduled routine. NEVER auto-sends or auto-accepts anything.
The English summary is being prepared. Showing the original description.
Batch-generate and compare visual design directions so a user can choose the style they actually want. Use when the user says they cannot describe an abstract visual style, asks for many style options, wants to choose from generated UI/design-system images, rejects outputs as too colorful/too dead/too generic, or needs an existing UI/design system evolved without discarding current assets.
The English summary is being prepared. Showing the original description.