「lab」の検索結果

Applies insights from MetaGPT paper on how structured communication, role specialization, and SOPs prevent coordination failures in multi-agent LLM systems

日本語の概要は準備中です。原文の説明を表示しています。

Comprehensive guide to designing reliable, scalable data systems covering databases, streaming, and consistency

日本語の概要は準備中です。原文の説明を表示しています。

Choose what kind of knowledge to transfer between teacher and student models: response, feature, or relational, and decide among offline, online, self, or cross-modal distillation schemes. Best for distillation strategy selection, capacity-gap diagnosis, and transfer planning. Activate on "knowledge distillation", "teacher-student", "soft labels", "feature distillation", "online distillation", or "cross-modal transfer". NOT for generic compression checklists or unrelated training work.

日本語の概要は準備中です。原文の説明を表示しています。

Comprehensive reference for inter-process communication mechanisms -- every way processes can talk on a computer. Covers sockets (TCP, UDP, Unix domain), WebSockets, SSE, pipes (named/anonymous), shared memory (mmap, shm_open), message queues, signals, D-Bus, XPC (macOS), gRPC, REST, stdin/stdout, file-based coordination, and clipboard. Performance benchmarks, platform availability, and code examples for each. Special focus on which IPC works best for AI agent coordination. Activate on: "IPC", "inter-process communication", "process communication", "how do I talk between processes", "Unix socket vs TCP", "shared memory", "named pipe", "WebSocket vs SSE", "gRPC vs REST", "agent coordination IPC", "XPC service", "message passing", "stdout pipe", "D-Bus", "mmap". NOT for: distributed systems design (use distributed-systems), network protocol design (use networking), message queue infrastructure like Kafka (use data-pipeline-engineer).

日本語の概要は準備中です。原文の説明を表示しています。

Use when building Grafana dashboards backed by Prometheus, Loki, or Tempo, designing PromQL/LogQL queries, wiring template variables, setting alert rules, building SLO dashboards, or maintaining dashboards as code. Triggers: rate() vs increase() confusion, irate vs rate, label_replace, recording rules, alerting rule expressions, multi-dimensional template variables, ad-hoc filters, dashboard JSON model, provisioning via Terraform/grafonnet, p99 / histogram_quantile usage. NOT for Datadog/New Relic dashboards (vendor-specific), Grafana plugin development, or Loki ingestion pipeline tuning.

日本語の概要は準備中です。原文の説明を表示しています。

Use when designing matrix builds (OS x version x dimension), composing reusable workflows, gating jobs on conditions, doing OIDC to AWS/GCP/Cloudflare without long-lived secrets, sharding tests across runners, or fixing cache invalidation. Triggers: workflow_call between repos, fail-fast: false tradeoffs, exclude/include matrix surgery, environment protection rules, OIDC trust policy setup, concurrency cancellation on duplicate pushes, artifact reuse across jobs, conditional job matrices computed at runtime. NOT for GitLab CI / CircleCI / Jenkins (different yaml dialects), self-hosted runner administration, or local act dev.

日本語の概要は準備中です。原文の説明を表示しています。

Design modern, intuitive DAG/workflow visual editors that feel like LEGO, not LabView

日本語の概要は準備中です。原文の説明を表示しています。

Architect scalable styling systems with Tailwind v4, CSS Modules, design tokens, dynamic theming, and container queries. Activate on: design tokens, theming system, Tailwind config, CSS architecture, container queries, dark mode. NOT for: component library creation (use design-system-creator), animation systems (use animation-system-architect).

日本語の概要は準備中です。原文の説明を表示しています。

Design decisions for when and what sounds to use in web apps, mobile apps, and desktop native apps — plus how to create them with AI. Covers UI sound vocabulary (confirms, alerts, transitions, errors), platform conventions (iOS, macOS, Material), creating sounds with AI tools (ElevenLabs, AudioCraft, Stable Audio), Web Audio API for procedural sounds, haptic-audio pairing, and the psychology of satisfying vs. annoying UI sounds. Activate on 'app sounds', 'UI sounds', 'notification sound', 'sound design app', 'earcons', 'sonic branding', 'interaction sounds', 'feedback sounds', 'app audio', 'satisfying sounds'. NOT for professional audio engineering (use sound-engineer), Windows 3.1 retro sounds specifically (use win31-audio-design), music composition (use sound-engineer).

日本語の概要は準備中です。原文の説明を表示しています。

Fetch a URL and return clean markdown, for arbitrary external pages (blog, RFC, GitHub issue, vendor doc) not covered by mk:docs-finder. Static-only by default; opt-in JS rendering available.

日本語の概要は準備中です。原文の説明を表示しています。

Multi-agent collaboration bringing 2-4 perspectives into one discussion for architecture decisions and trade-off analysis. Use for 'should we X or Y', design review, or debate before deciding.

日本語の概要は準備中です。原文の説明を表示しています。

JIRA issue CRUD via jira-as. NOT lifecycle (mk:jira-lifecycle), comments (mk:jira-collaborate), bulk (mk:jira-bulk), links (mk:jira-relationships), or time/sprint (mk:jira-time/agile).

日本語の概要は準備中です。原文の説明を表示しています。

JIRA comments, attachments, watchers, notify via jira-as. Internal-vs-public comment safety enforced. NOT issue CRUD (mk:jira-issue) or issue links (mk:jira-relationships).

日本語の概要は準備中です。原文の説明を表示しています。

GitHub project management via gh CLI: issues, Projects v2 boards, labels, milestones, handoff summaries. NOT for code review (mk:review-pr), PR creation, or git ops (mk:resolving-merge-conflicts).

日本語の概要は準備中です。原文の説明を表示しています。

Pre-ticket Fibonacci sizing for a paste-mode batch of user stories. Default mode is advisory-only (writes a Story Sizing Report). Opt-in `--auto-create` delegates ticket creation to mk:jira-issue + mk:jira-collaborate with mandatory dry-run + single batch confirmation gate. NOT for single-ticket estimation (mk:jira-estimator); NOT for sprint capacity (mk:planning-engine).

日本語の概要は準備中です。原文の説明を表示しています。

Fetch a URL and return clean markdown. Use when the agent needs an arbitrary external page (blog, RFC, GitHub issue, vendor doc) not covered by mk:docs-finder. Triggers on URLs in chat. Static-only by default; opt-in JS rendering available.

日本語の概要は準備中です。原文の説明を表示しています。

Confluence page CRUD via confluence-as: create/show/update/delete, hierarchy, copy. NOT bulk (mk:confluence-bulk), spec analysis (mk:confluence-spec-analyst), or comments (mk:confluence-collaborate).

日本語の概要は準備中です。原文の説明を表示しています。

JIRA issue CRUD via the jira-as wrapper. Triggers: 'create bug/task/story', 'show me PROJ-123', 'get/view/look up issue', 'update PROJ-123', 'delete PROJ-123'. NOT for transitions (mk:jira-lifecycle); NOT for comments/attachments (mk:jira-collaborate); NOT for bulk ops (mk:jira-bulk); NOT for issue links (mk:jira-relationships); NOT for time logging (mk:jira-time); NOT for sprint/epic (mk:jira-agile).

日本語の概要は準備中です。原文の説明を表示しています。

Multi-agent collaboration session. Brings 2-4 agent perspectives into one discussion for architecture decisions and trade-off analysis. Use when asked "should we X or Y?", "let's discuss", or "design review".

日本語の概要は準備中です。原文の説明を表示しています。

Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.

日本語の概要は準備中です。原文の説明を表示しています。

Semble (MinishLab) MCP wrapper — semantic code search via embeddings (98% token reduction vs grep+read, NDCG@10=0.854)

日本語の概要は準備中です。原文の説明を表示しています。

Show all available commands

日本語の概要は準備中です。原文の説明を表示しています。

Guide setup for and verify a reviewed, read-only Grafana Observability profile and its activated capability packs. Use when a user asks to set up Grafana access, verify profile readiness, discover available infrastructure, APM, log, IoT or business KPI packs, or troubleshoot why a Grafana pack cannot run.

日本語の概要は準備中です。原文の説明を表示しています。

Initialize or safely upgrade a processor project's root AGENTS.md from a maintained baseline. Use when starting a processor project, adding project-level Agent collaboration rules, or comparing an existing AGENTS.md with the package baseline. This skill only handles AGENTS.md; it does not scaffold documentation, inspect or configure environments, install tools, or modify processor source.

日本語の概要は準備中です。原文の説明を表示しています。