3,891 件 ・ 関連度順
概要と使いどころ
Lightweight build: explore → plan → approve → implement in a single Opus context, no sub-agent fan-out. Verifies build + tests, optionally commits, and offers a separate /code-review pass at the end. Use by default for everyday features; reach for /build only when the work needs parallel fan-out or exceeds one 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。
Lightweight build: explore → plan → approve → implement in a single Opus context, no sub-agent fan-out. Verifies build + tests, optionally commits, and offers a separate /code-review pass at the end. Use by default for everyday features; reach for /claude-setup:build only when the work needs parallel fan-out or exceeds one 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。
Work with the @upstash/workflow TypeScript/JavaScript SDK for durable, long-running workflows in serverless functions, multi-step processes that survive timeouts, retries, and restarts (built on QStash). Use when defining a workflow endpoint with serve(), running steps with context.run, sleeping for minutes to days without holding a function open, calling external APIs with context.call, waiting for an external event or webhook, invoking other workflows, configuring retries, failure callbacks, and a DLQ, controlling concurrency, rate, and parallelism, triggering, cancelling, or inspecting runs with the Workflow client, building AI agents and orchestrators, human-in-the-loop approvals, realtime updates, local development with the QStash dev server, adding middleware, or migrating workflows safely. Also use when the user asks for durable execution, step functions, saga or orchestration patterns, background jobs with checkpoints, or long-running tasks on Vercel, Next.js, Cloudflare Workers, or other serverless platforms.
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。
Sets up a file-based memory system so Cowork always knows who you are, how you work, and where your projects stand. For eliminating repetitive re-introductions at session start, when building persistent context across multiple projects, or during initial Cowork onboarding. Use when the user says "claude doesn't remember me", "memory system", "persistent context", "why does it forget", "remember my preferences", "I keep re-explaining myself", or "how do I make Claude remember things".
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。
Teaches you how to break large tasks into stages, save your place between sessions, and recover smoothly when a task gets interrupted. Use when planning a multi-day project, for breaking down large work into manageable stages, during recovery from an interrupted session, when managing complex ongoing work, or when the user says "cowork stopped in the middle", "token limit", "task too large", "context management", "how to do big tasks", "session got cut off", "cowork forgot what we were doing", "how do I work on something over multiple days", "it lost track of the project", or "my task is too big for one session".
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。
Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current 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。
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。
Use when integrating or optimizing Model Context Protocol (MCP) servers and clients. Keywords: MCP, Model Context Protocol, tool discovery, lazy loading, sampling, resource subscription, MCP server.
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。
Guides agents and users to create standards-compliant agent definitions using templates in markdown frontmatter format, ensuring context gathering, clarity, and proper metadata. Forces agents to ask clarifying questions when context is insufficient. Token-efficient documentation required. All content must be in English. Trigger: When creating a new agent definition, setting up project agents, or documenting agent workflows.
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。
Agent Context Isolation
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 GTM, sales, growth, or launch work needs a canonical product-marketing context document instead of ad hoc assumptions.
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。
Optimize oversized agent instruction files using progressive disclosure. Handles CLAUDE.md (Claude Code), AGENTS.md (OpenAI Codex / GitHub Copilot agents), and copilot-instructions.md (GitHub Copilot). Auto-detects all three formats in your repo, analyzes content tiers, creates sub-documents using each format's native mechanism, and rewrites the main file with zero information loss. Triggers: optimize CLAUDE.md, AGENTS.md too long, reduce copilot-instructions.md, agent instructions file too large, shrink context file, apply progressive disclosure, instructions file bloated
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。
Super Base Context — project doc loader & synchronizer. Triggers even without explicit "load docs"/"sync docs." READ MODE — load architecture/modules/coding/decision docs when work references project state: code work (write/modify/remove); design (features/APIs/schemas/architecture); review (modules, past solutions); tech selection; ADR research; migration/refactor planning; performance/security analysis; tests; code reviews; any spec/plan/design/ADR referencing project. WRITE MODE — NET DELTA vs. last doc sync: additions/modifications/REMOVALS/deprecations of previously-synced code or decisions (docs revert: delete BCU file/ADR), AND rollbacks. User signals: sync docs/done/ready to commit/pre-commit/record decision. Auto-fires before final task-completion reply. WRITE MODE does NOT fire on: brainstorming, generic/read-only Q&A, in-session try-and-undo with no net change, already-synced.
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。
Save working context. (gstack).
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 LLM context budgets—prioritization, summarization, compaction, and what to load vs reference. Use for long sessions, large repos, or multi-doc tasks.
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。
Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid 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。
Idiomatic Go concurrency - sync primitives, channel semantics, the select statement, and the standard channel patterns (cancellation/done-channel, fan-out/fan-in, pipeline, or-done, context, worker-pool). Use when writing or reviewing Go that spawns goroutines, shares state, or coordinates over channels, even if the user never says "concurrency" - e.g. data races, deadlocks, goroutine leaks, sync/context/select usage, or "make this parallel". Distilled from luk4z7/go-concurrency-guide.
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。
Draft clear, professional business emails from rough notes, context, or instructions. Handles cold outreach, internal updates, client responses, and escalation drafts. Use when the work is routine email writing with known context and audience. Do not use for sensitive legal notices, formal regulatory correspondence, or board-level communication without 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。
Build a custom session search tool that indexes and queries past Claude Code CLI chat logs to retrieve historical findings, techniques, and context. Based on Critical Thinking Bug Bounty Podcast Episode 166.
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。
White-box source code security review structured around OWASP ASVS 5.0 (427 verification requirements across 16 chapters). Reads and understands application source code to build a security-aware knowledge base that enriches all downstream skills. Covers: tech stack identification, route/endpoint mapping, authentication and authorization architecture, dangerous function patterns, source-to-sink data flow tracing, IaC review, dependency analysis, ASVS compliance mapping, and LLM integration security (prompt injection, tool abuse, output handling, RAG poisoning, MCP server patterns). When LLM/AI framework usage is detected, automatically reviews OWASP LLM Top 10 patterns from source code and chains into /ai-redteam with white-box context for live endpoint testing. Chains into /pentester, /threat-modeling, /web-exploit, /api-security, /cloud-security, /analyze-cve, /credential-audit, and /ai-redteam — providing white-box context that transforms black-box testing into targeted, informed assessment.
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。
Configure Claude as a "Pair Hunter" — autonomous overnight hacking, context management via per-target .claudemd files, sub-agent compaction avoidance, and scope enforcement. Based on Critical Thinking Bug Bounty Podcast Episode 166.
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 researching external libraries/frameworks (React, Radix, Tailwind, etc.) — reach for the Context7 MCP to get up-to-date docs. Not for internal codebase or design-system-token questions.
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 a component has a `disabled` state/variant, or when building a compound component that owns a disabled state — inherit/provide it via the shared disabled context so state flows from parent to sub-components.
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。
Re-inject Synapse A2A initial instructions after context has been cleared. Use this skill when the agent has lost its identity, A2A communication protocol, or configuration after /clear or context reset, when synapse send/reply commands stop working, or when the agent no longer recognizes its SYNAPSE_AGENT_ID. Triggered by /synapse-reinst command.
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。