3,918 件 ・ 関連度順
概要と使いどころ
Add WebMCP tools to a website codebase so browser agents can act through the site's own logic instead of scraping the page. Use when asked to make a site agent-ready, add WebMCP or document.modelContext tools, or implement site tools with @nekuda/webmcp-sdk.
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。
Check that a locally running site's WebMCP tools register and execute correctly. Use to verify WebMCP tools, confirm document.modelContext tools appear on the right pages and auth states, or test @nekuda/webmcp-sdk tools in a browser.
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。
Protocol for task synchronization, context handoff, and cross-session coordination using Claude Code task tools. Ensures agents properly update tasks with findings and enables seamless work continuation.
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。
Initiate a session handoff to transfer context and pending actions to a new terminal session. Executing this skill safely drains tasks and launches a new cross-platform window natively.
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。
Parses and merges Claude .jsonl transcripts with debug logs to generate a timeline heuristics report of API limits, context overflows, hook blocks, and tool failures.
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。
Workflow recovery protocol for resuming workflows after context loss, session interruption, or errors. Handles state reconstruction, artifact recovery, and seamless workflow continuation.
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。
Manus-style file-based planning for complex tasks. Use task_plan.md, findings.md, and progress.md to maintain persistent context. Use for multi-step tasks, research, or work spanning many tool calls.
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。
Shell out to Claude Code CLI to invoke a second Claude session headlessly. Useful for cross-validation, second opinions, and isolated analysis without sharing current agent context. Requires Anthropic account.
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。
Entity and relation tracking skill using MCP memory server patterns and local knowledge graph storage. Build persistent knowledge graphs of entities, relationships, and observations across agent sessions. Covers the MCP memory server (@modelcontextprotocol/server-memory), local JSON-based graphs, and entity-relation querying patterns for long-running agents.
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。
Records atomic learned behaviors with confidence scores. Project-scoped instincts are isolated per project and auto-promote to global scope at confidence threshold 0.8. Stores instincts in .claude/context/memory/instincts.jsonl
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。
Master on-call shift handoffs with context transfer, escalation procedures, and documentation. Use when transitioning on-call responsibilities, documenting shift summaries, or improving on-call processes.
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。
Kubernetes cluster management and troubleshooting. Query pods, deployments, services, logs, and events. Supports context switching, scaling, and rollout management. Use for Kubernetes debugging, monitoring, and operations.
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。
Auto-evolution skill to initialize a new repository with AGENTS.md localized context.
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。
Focuses on routing, CSRF protection, context handling, and template usage within the internal handlers directory.
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。
Background orchestrator that drains the system-wide cron-actions-queue.jsonl queue safely, preventing LLM context pollution in the primary router.
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。
Detect Claude Code context compaction events in session JSONL logs. Identifies compaction boundaries, measures token delta before/after, reports compaction events with timestamps and token impact.
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。
Expert Electron desktop application development — main/renderer process architecture, IPC communication, native OS APIs (menus, tray, notifications, dialogs), auto-updates, code signing, packaging with electron-builder/forge, security hardening (contextIsolation, sandbox), and performance optimization. Use for building cross-platform desktop apps.
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 you need semantic retrieval from perpetual memory at query time. Parses query intent, searches vector store, ranks by relevance and recency, and injects context. Complements memory-search.cjs with the perpetual_memory LanceDB table.
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。
Two-step self-review at every task lifecycle phase. Step 1 (this skill) runs in-context to gather session signals — files read vs grepped, user pushback, build evidence, degradation signs. Step 2 launches a forked subagent for unbiased code/plan review with fresh eyes. Combined report classifies findings as hard blocks or soft warnings.
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。
Process external specifications through transformation, classification, gap analysis, component discovery, and decomposition. Creates workflow items with classified context.
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。
Set up a construction project — inventories files, classifies drawings/specs/schedules/registers, detects AgentCM mode, appends construction context to CLAUDE.md. Triggers: 'set up project', 'construction setup', 'classify documents'.
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。
Phase 4 of 5 — implements tasks from TASKS-<N>-<slug>.md (with ARCH-<N>-<slug>.md as architecture-only context) using mode-appropriate verification (tdd, test-after, ui, checklist); pass 'auto' to run without stepping. Use only when the user asks to run Phase 4 or implement tasks from an ARCH doc — never trigger automatically from a coding request.
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。
Render a dashboard of the current Claude Code session — message counts, token usage, cache read/write, dollar cost, context %, lines changed, cost-per-turn sparkline, and a tool-call histogram — parsed from the session transcript JSONL by a bundled bash script. One bash call, zero analysis, zero confirmation. Optionally pass a session id to inspect a different session. Use when the user asks for session stats, usage, token or cost breakdown, or a session dashboard.
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。
One-shot conventional commit; bundled scripts adaptively gather diff context, draft the message, and stage+commit — pass `ask` to confirm first or add a hint for the title. Use only when the user asks for a commit.
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。