Read-only MacroQuest docs researcher for TLO/datatype/command/plugin questions. Provides Lua-first examples with doc path citations.

Provide a reusable pattern for memoizing deterministic function calls to reduce latency and repeated computation. Backed by the `python` diskcache package. Use skill when updating or editing everything.

Create and manage specialized Claude Code subagents for task-specific workflows. Use when delegating work to specialized agents, configuring agent permissions, or understanding subagent architecture and best practices.

Next.js 16 Cache Components - PPR, use cache directive, cacheLife, cacheTag, updateTag

Run evaluation tests using eval sets. Two-mode execution: Direct Line API (auto) or MCS Native Eval via Gateway API upload + run (manual). Results written per-test to evalSets[].tests[].lastResult.

**Model**: Claude Haiku 4.5

auto-sync launchd管理。dotfiles自動同期の状態確認・起動・停止・ログ確認。トリガー: launchd, auto-sync, 自動同期, 同期, sync agent

Evaluates and selects the best solution from multiple developer implementations using a comprehensive scoring system. Use this skill when you need to compare competing solutions, score them objectively across multiple dimensions, or select a winning implementation for integration.

Build agent(s) in Copilot Studio using the fully API-native build stack with user-guided manual steps for OAuth connections. Reads brief.json for architecture mode (single/multi-agent).

Submit a feature suggestion conversationally — Claude gathers details, previews, and creates a GitHub issue via gh CLI.

Analyzes proposed projects before implementation, identifies issues and improvement opportunities across 8 dimensions (security, performance, requirements, etc.), presents findings to user for approval, then sends approved changes to Architecture Agent. Use this agent after research stage and before architecture stage for all non-trivial tasks.

Build Claude agents using TypeScript with the @anthropic-ai/claude-agent-sdk. Use this skill when implementing conversational agents, building tools for agents, setting up streaming responses, or debugging agent implementations. Covers the tool wrapping pattern, SDK initialization, agent architecture, and best practices.

Expert for creating and managing Claude Code Agent Skills. Create skills with git submodule + sparse-checkout for source references, write SKILL.md with proper frontmatter, and follow best practices. Use when creating new skills, adding source references to skills, or managing skill configurations.

Post-deployment fix: analyze eval set failures, classify root causes, apply targeted fixes, and re-evaluate. For initial build iteration, use /mcs-build (which has an internal fix loop). This skill handles post-deployment edge cases and regressions.

This skill should be used when the user asks to "do something simple", "perform basic task", or needs minimal guidance. Demonstrates the simplest possible skill structure.

Guide for adding and managing entries in the personality-assistant-registry. Use when adding MCP servers, skills, bundles, templates, or heartbeat tasks to the registry.

Provides Go standard testing package expertise and best practices. Ensures proper table-driven test patterns, subtests organization, benchmark implementation, and test coverage strategies. Specializes in testing.T/testing.B usage, test helpers, mock interfaces, race detection, and integration testing patterns following Go conventions. Use when: writing Go test files (_test.go), implementing table-driven tests with subtests (t.Run), creating benchmark tests (testing.B), writing example tests for documentation, implementing test helpers and fixtures, mocking interfaces for unit tests, measuring code coverage with go test -cover, detecting race conditions with -race flag, or organizing integration tests in Go projects.

Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model strategies.

Download and generate plots from Weights & Biases runs. Use when you need to: - List projects you have access to - List runs in a W&B project - Inspect available metrics for a run - Download existing plot images from a run - Generate line plots from metric history (loss, accuracy, etc.)

Break down PM story into organized tasks in a single file following UI DEVELOPMENT order: Setup → Static UI → Dynamic Logic → Interactions → Testing. UNIQUE VALUE: Creates single task file (story-{name}.md) containing all tasks for a story. Tasks are ordered by UI development layers. Use this skill when: - Running /frontend.tasks command - User asks to "break down story", "create frontend tasks", "split into tasks" - Have story at docs/reference/pm/stories/ and need organized task breakdown - Need tasks ordered by UI development layers (not random order) - Starting frontend work and want organized task list Task order is CRITICAL: Setup → Static UI → Dynamic → Interactions → Tests Output: Create single file docs/reference/frontend/tasks/story-{name}.md with all tasks