「prompt」の検索結果

Design deployment-focused distillation systems that balance model size, accuracy, calibration, and cascade escalation under real resource limits. Best for teacher-student compression, threshold design, and failure-aware deployment. Activate on "model compression", "teacher- student", "distillation score", "cascade model", "edge deployment", or "model calibration". NOT for generic deep-learning overviews, prompt optimization, or training work without a concrete distillation objective.

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。

Apply rapport-based elicitation to resistant or semi-cooperative humans and agents. Use when coercive prompting or brittle handoffs damage cooperation. NOT for routine cooperative tasks, pure technical debugging, or already reliable exchanges.

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。

Cooperative vibe coding across machines — real-time collaborative development with humans and AI agents. Covers current tools (Live Share, Code With Me, Zed, Cursor multiplayer, tmux), git-based async patterns, AI agent coordination, and the aspirational future of multi-human multi-agent development. Activate on: "pair programming", "vibe coding together", "collaborative coding", "mob programming", "remote pairing", "code together", "multiplayer coding", "Live Share", "Code With Me", "ensemble programming", "cooperative development". NOT for: building a real-time collaboration ENGINE (use real-time-collaboration-engine), git workflow mechanics (use git-best-practices), single-user AI coding assistance (use prompt-engineer).

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。

Choose multi-agent architectures using environment-first analysis, coordination pressure, commitment tuning, and knowledge levels. Use for autonomy design, protocol choice, and coordination failures. NOT for single-agent planning, centralized schedulers, or prompt-only swarms.

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 and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.

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。

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

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。

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

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。

Operational skill hub for LLM system architecture, evaluation, deployment, and optimization (modern production standards). Links to specialized skills for prompts, RAG, agents, and safety. Integrates recent advances: PEFT/LoRA fine-tuning, hybrid RAG handoff (see dedicated skill), vLLM 24x throughput, multi-layered security (90%+ bypass for single-layer), automated drift detection (18-second response), and CI/CD-aligned evaluation.

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。

Assesses that CGM low- and high-glucose alarm thresholds are individualized to optimize patient benefit and minimize alarm fatigue. Triggered by clinician prompts to 'Review low-glucose alarm thresholds' or 'Ensure alarms are individualized and not excessive'.

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。

Assesses patient’s knowledge of diabetic ketoacidosis prevention, recognition, and treatment. Triggered by clinician prompts such as 'Review sick-day rules and DKA signs' or 'Ensure patient knows when to seek help for hyperglycemia'.

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。

This skill recommends bilateral adrenalectomy for occult or metastatic ectopic ACTH secretion or as a life-preserving emergency treatment in patients with very severe ACTH‑dependent Cushing’s syndrome who cannot be promptly controlled by medical therapy. It is triggered by life‑threatening complications of uncontrolled hypercortisolism such as infection, pulmonary thromboembolism, cardiovascular catastrophe, or acute psychosis.

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。

DSPy: declarative LM programs, auto-optimize prompts, RAG.

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。

Decomposition playbook + specialist-roster conventions + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.

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。

Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).

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。

Songwriting craft and Suno AI music prompts.

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。

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

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。

Forensic root cause analyzer for Antigravity sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.

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。

Marc Andreessen-mode decision and productivity skill. A blunt, market-first operator that pressure-tests ideas, ventures, features, and career bets through Andreessen's actual frameworks — market dominates team and product; the only milestone that matters is product/market fit; bias to build over deliberate. Use when the user says 'andreessen', 'pmarca mode', 'should I build this', 'is there a market', 'are we at product/market fit', 'pmf check', 'pressure-test this idea', 'be brutal about this venture', 'market-first take', or wants a no-disclaimers, no-hedging, confidence-leveled verdict on whether something is worth pursuing. Also provides the 3x5-card + Anti-Todo personal productivity routine. Runs on a fixed anti-sycophancy operating prompt: leads with the strongest counterargument, never validates premises, uses explicit confidence levels, never apologizes for disagreeing. Not for polite brainstorming — this skill exists to tell you the market is dead when it is.

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 natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into wallet-signed txs on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. 40+ apps: Uniswap, Aave, Lido, Morpho, GMX, Hyperliquid, Polymarket.

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 assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS technique mapping, injection signature detection, and adversarial robustness scoring.

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。

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.

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 design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).

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。

Local-only regression / benchmark skill for ui-clone-skills maintainers. Drives the standard ui-reverse-engineering pipeline against the canonical reference site (https://realfood.gov) and records AE/SSIM, iteration count, gate fail counts, and outcome to benchmark/history.csv so prompt / sub-doc / model-version drift surfaces as a trend. Trigger phrases: "run benchmark" / "regression benchmark" / "benchmark clone". The Makefile no longer has a `benchmark` target — setup is inline bash in this skill (Step 1 below). Internal: NOT registered in `.claude-plugin/plugin.json` `skills`. Not part of the public 3-skill marketplace surface. Maintainer tooling only.

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。

Rewrite AI-sounding prose so it reads as considered human writing — cut the tells (em-dash pile-ups, "it's not X, it's Y" antitheses, inflated vocabulary, uniform rhythm, empty uplift) while preserving every fact, claim, and the author's own voice. Use when the user says "make this not sound like AI", "de-AI this", "humanize/humanise this", "this reads like ChatGPT", "remove the AI tells", "it sounds robotic/generic", or shares a draft (post, email, essay, docs, cover letter) to sharpen into a more human voice. Ships a stdlib scanner that flags the mechanical tells.

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。