4.2K skills · sorted by relevance
Learn how instructions, documents, tool results, and conversation history form an AI model’s context. Understand attention limits, why information in the middle can be missed, and how relevance and placement inform decisions about what to include.
Fetch current library documentation with the ctx7 CLI to check API usage while coding. The skill also guides Context7 MCP setup, which connects documentation access to Claude Code, Cursor, or OpenCode, and covers login and authentication options.
Update context-mode from GitHub, rebuild and reinstall it, and configure hooks that connect it to the agent environment. Review the actual version and upgrade results in a checklist, then restart the session.
Check how much conversation capacity context-mode has saved during the current session. View token consumption, the context savings ratio, and a breakdown by tool in full tables, with one sentence highlighting the main savings figure.
Design how an AI agent edits its own working conversation history, choosing what to retain, rewrite, or remove. Covers safeguards, capacity monitoring, recovery after overflow, and the computing cost of changing earlier context.
Explore the context-matic MCP server through an interactive tour. Discover available APIs, choose one, and review authentication, data structures, and example calls in your project's programming language, with guidance matched to the SDK version.
Audit Claude Code agents, skills, rules, and MCP tool configurations to estimate how much space they consume in the model's context. Identifies oversized and overlapping components, then ranks recommendations by potential token savings.
Resume interrupted work by loading the latest state saved with /context-save. The skill prefers a save from the current branch, falls back to other branches, and supports handoffs between Conductor workspaces.
Manage OmniRoute context settings from the command line, including token budgets and RTK filters for processing context. Switch saved server connections, import or export configurations, and inspect or expire conversation sessions.
Guides users through removing a stored fact with Codewhale’s Context Lens memory controls. It identifies the intended fact, explains the forget action, and distinguishes confirmed deletion from an action that has not yet completed.
Manage the limited information an LLM can process at once. Use importance-based summaries, selective trimming, token counting, and content placement to plan what stays in context and address information loss during long conversations.
Run context-mode diagnostics to check runtimes, hooks, full-text search support, plugin registration, and npm and marketplace versions. Results appear directly in the conversation with clear status labels, with a CLI fallback if the MCP call fails.
/context-builder と入力されたときだけ起動する、コンテキストドキュメント作成インタビュースキル。人・プロジェクト・プロダクトなどの対象について、1問ずつ掘り下げる対話を通じて情報を集め、今後 Claude との対話の冒頭に貼り付けるための context.md（自分についてなら aboutme.md）を作り上げる。/context-builder me（自分＝aboutme）/ project / product のように対象を指定できる。「aboutme を作りたい」「プロジェクトのコンテキストをまとめたい」「プロダクトの前提情報を用意したい」ときに使う。自動起動はせず、ユーザーが /context-builder と明示的に入力した場合のみ使用すること。
The English summary is being prepared. Showing the original description.
Diagnose why an AI agent becomes less reliable as conversations and documents accumulate. Distinguish missed information, persistent false claims, irrelevant material, mixed tasks, and conflicting sources, then choose ways to clean, reorganize, or separate the context.
Strategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rotUse when "context window, token limit, context management, context engineering, long context, context overflow, llm, context, tokens, memory, summarization, optimization" mentioned.
The English summary is being prepared. Showing the original description.
Manages context passing between DAG nodes and spawned agents. Handles context summarization, selective forwarding, and token budget optimization. Activate on 'bridge context', 'pass context', 'summarize context', 'context management', 'agent context'. NOT for execution (use dag-parallel-executor) or aggregation (use dag-result-aggregator).
The English summary is being prepared. Showing the original description.
Context and scope-tagging UI. Use when adding a context picker to a surface, tagging an entity to scopes, setting or filtering by the active (working) context, showing per-entity context status, prompting for context on upload, or editing context-assignment/**, active-context/**, or appContextSlice.
The English summary is being prepared. Showing the original description.
Look up current library and framework documentation through Context7 MCP, a connection to live documentation tools. Supports setup questions, API references, and code examples, using version-specific sources when available to ground answers in retrieved material.
Create a standard folder layout for a DDD bounded context, a module organized around one business area. Generate TypeScript export files, keep infrastructure outside the public exports, and record the context in a domain model graph.
Find current documentation and code examples through the Context7 MCP server. Look up library setup, API usage, migration steps, and library-specific problems, using documentation for the requested version when available.
Retrieve current documentation and code examples from Context7 for libraries, frameworks, and developer tools. Use the results to answer questions about API syntax, configuration, installation, version migration, and library-specific problems.
Refactor state held in Redux or React Context by separating API data, URL settings, shared interface state, and local component state. Move each part to React Query, nuqs, Zustand, or React’s local state hooks.
Route data analysis, large-file processing, and web retrieval through context-mode tools, returning only relevant results to the conversation. This helps preserve the context window, the limited amount of information an AI can work with at once.
Find previously indexed project files, documentation, and session memory in context-mode's persistent full-text search database. Search related questions together and narrow results to a named project or source without rereading raw material into the conversation.