2,888 件 ・ 関連度順
概要と使いどころ
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
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。
Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
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。
Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.
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。
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.
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。
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.
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 putting data into cognee memory with remember() — choosing inputs (text, files, folders, URLs, repos, databases), datasets and node_sets, loaders, ontologies, the graph extractor (LLM or GLiNER), chunking, dry-run cost estimates, or when remember() raises on a keyword argument.
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 the user wants to connect cognee to external services — switching LLM or embedding providers (OpenAI, Azure, Gemini, Anthropic, Ollama, OpenRouter), changing databases (Postgres, PGVector, Neo4j, Neptune, Turso), S3 storage, or the MCP server for IDE integration.
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 cognee is slow, expensive, or hitting rate limits — speeding up or throttling ingestion (remember/cognify batching, chunk size, LLM and embedding rate limits, per-stage models), cutting read latency, estimating cost before ingesting, running work in the background, or planning how to scale a deployment.
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。
Share brain pages as beautiful password-protected HTML with zero LLM 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。
Author an eval for an existing skill from its REAL usage history, not its spec. Mine invocations from the brain's conversation archive (conversations/) and per-harness session transcripts — a user correction after an invocation is the gold signal — then synthesize an eval_contract plus 4-8 replayable cases with honesty labels (SPEC-DERIVED vs HISTORY-IMPLIED) and stage the result at skills/<name>/eval/autobench-<date>.md as PENDING-HUMAN-APPROVAL. Never rewrites SKILL.md. Ships two guard companions: panel integrity (multi-model judging must prove each provider actually responded) and the fail-improve taxonomy (logged LLM-fallback cases convert to deterministic code over time).
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。
Unified Minions skill for both deterministic shell jobs and LLM subagent orchestration. Replaces the older `gbrain-jobs` routing intent. Use when: submitting gbrain jobs, shell/background tasks, spawning subagents, checking progress, steering running work, pausing/resuming, parallel fan-out. One durable, observable, steerable queue interface. Also carries the durable-execution doctrine for any operation expected to exceed ~2 minutes: capability ladder, deadman checks that verify the result was reported, and content-addressed stage checkpoints for expensive pipelines.
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。
Compress an agent's routing file (RESOLVER.md or AGENTS.md) by converting granular skill-per-row tables into functional-area dispatchers. Each area lists sub-skills in a "(dispatcher for: ...)" clause. The LLM reads one area entry and routes to the correct sub-skill. Proven via held-out A/B eval: dispatcher pattern outperforms naive pipe-table compression.
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。
When the user corrects a factual error, root-cause it immediately. Don't just note the correction — trace the error to its source, fix the source, and prevent recurrence. Every factual error is either a data error (bad brain page, bad memory file, bad rendered SOUL/USER identity, bad facts row) or a hallucination (LLM confabulated from partial signals).
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 TYPED citation/reference graph over an ingested corpus — not just embeddings. Flat similarity retrieval cannot tell you that document A *overrules* B, *distinguishes* C, or *relies_on* D. This skill extracts every inter-document reference, classifies the edge TYPE with LLM judgment, and writes first-class typed edges via `gbrain link`, so `gbrain graph-query --type` can walk the argument ("everything this brief relies on, minus anything overruled since"). Every cite-heavy corpus is the same shape: law, academic papers, patents, regulatory filings, a book's bibliography.
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。
Chat / code generation via 9Router using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through 9Router.
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。
Find leads matching criteria and bulk-add them to an Apollo outreach sequence. Handles enrichment, contact creation, deduplication, and enrollment in one flow.
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。
Audits and fixes both halves of being found — classic search and AI answers. Search side: rankings, site structure, page speed, titles and descriptions, and content that answers what customers search for. AI side: whether assistant crawlers can reach the site, pages render without JavaScript, an llms.txt file, schema.org data, and presence in the directories assistants read. For online stores it also runs a bulk catalog cleanup, rewriting product titles, descriptions, alt text, and SEO fields in approved batches. Works on any public website with no connector. Use this whenever the owner talks about being found online, including "nobody finds us on Google," "how do I show up in ChatGPT," "make my website AI friendly," "SEO audit," "GEO," "AEO," "AI search visibility," "my competitor ranks above me," "fix my product listings," or "I asked an AI about my industry and we weren't in the answer."
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。
Watches what customers are saying in public and in private, then does something about it. Aggregates Google, Yelp, and Facebook reviews alongside disputes, tickets, and email into themes backed by verbatim quotes; drafts a reply to every review in the owner's own voice for approval; spots customers who have gone quiet or look likely to leave; and drafts win-back offers for the ones worth keeping. With Shopify connected, order and fulfillment patterns become a sentiment signal too. Works from pasted or exported reviews when nothing is connected. Use this whenever the owner asks about reviews, ratings, reputation, complaints, or repeat business — including "what are people saying about us," "did we get any bad reviews," "how do I respond to this one-star," "our rating dropped," "which customers have gone quiet," "who hasn't ordered in a while," "how do I win them back," or "are customers happy."
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。
Maintain the supported LLM model list: add a new model, or run routine maintenance to verify availability and discover new models worth adding. Use when the user asks to add/support a model, update the model list, or check model availability.
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。
Turns marketing prompts into tested, versioned production assets: A/B prompt evaluation against structured test cases, immutable prompt version history with diffs, ready-to-use marketing prompt templates (ad copy, email campaigns, social posts, landing pages, SEO meta), and an LLM-governance playbook for marketing teams (claim discipline, disclosure rules, human-review gates). Use when a marketing team relies on AI-generated content and needs prompt quality to be measurable and safe — or when the user mentions 'prompt engineering,' 'improve my prompts,' 'prompt templates,' 'prompt versioning,' 'AI content workflow,' or 'AI governance for marketing.'
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-production audit that scans a codebase for security, database, deployment, code quality, AI/LLM, dependency, frontend, and observability issues. Intercepts deploy commands and blocks until critical items pass. Stack-agnostic. Use for "run ship gate", "am I ready to ship", "pre-launch audit", "can I deploy", "push to production", "go live checklist", "preflight check". Not for CI/CD setup or infra provisioning.
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 the user asks to optimize prompts, design prompt templates, evaluate LLM outputs with an eval set, measure RAG retrieval quality, validate agent/tool configurations, analyze token usage, or design structured-output contracts. Covers eval-driven prompt iteration, RAG metrics (relevance, faithfulness, coverage), agent workflow validation, and token/cost budgeting — all model-agnostic, with three stdlib Python tools.
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 production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs.
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 engine and version. Pins it in CLAUDE.md; WebSearch fills reference docs when the version is beyond LLM training data.
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。