「prompt」の検索結果

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。

Legacy compatibility entry for prompts or documentation that explicitly name `using-superpowers`. Route new skill-discovery workflows to `using-skills`; do not activate both entrypoints for the same task.

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。

Run an iterative Stitch website-building loop using `.stitch/next-prompt.md`, SITE.md, DESIGN.md, generated pages, and verification checkpoints.

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。

Create opinionated premium DESIGN.md guidance for Stitch, emphasizing calibrated typography, restrained color, layout discipline, motion, and anti-generic UI rules.

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。

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.

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。

**MANDATORY prerequisite** — you MUST invoke this skill BEFORE calling the `get_design_context` Figma MCP tool. You MUST trigger this skill whenever the user wants to implement, build, port, or code up a Figma design as code. Example prompts (not exhaustive) are 'implement this Figma design', 'build this screen from Figma', 'turn this Figma into code', 'design to code'. This skill provides critical instructions and steps to the agent on how to correctly implement Figma designs in code and must NOT be skipped.

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。

LLMs, prompt engineering, RAG systems, LangChain, and AI application development

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。

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

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。

Scan agent skills for security issues before adoption. Detects prompt injection, malicious code, excessive permissions, secret exposure, and supply chain risks.

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。

Develops an implementation plan ready for wave-orchestration to execute. Takes the user's goal or rough plan as input, mines the codebase for facts, grills the user one question at a time for the decisions, drafts the planning/ artifacts (task DAG, wave table, worker prompt template, state file), then reviews its own plan on two axes before seeking approval. Use when the user wants to turn a feature idea, master plan, or backlog into a wave-orchestration execution plan.

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。

Solves UI lock-in. Reverse engineers your existing UI, strips all layout/token decisions, preserves every hook, handler, and API call untouched, then rebuilds the UI from scratch with a fresh design system. Use /ui-restructure to fully redesign, --style apple|linear|minimal|dashboard for named styles, --mode layout|theme|grid for partial rebuilds, --god-mode to redesign from the user's perspective using 100-user mindset simulation and 6 UX principles, --keep-tokens to preserve your token system, --prompt for custom redesigns. Applies mandatory world-class polish: spring motion, 5-state micro-interactions, 8pt spacing grid, WCAG accessibility. Supports Next.js, React, Vue 3, Tailwind, CSS Modules, styled-components, shadcn.

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。

Run a prompt repeatedly on an interval, using the harness built-in plus loop templates. Generated from plugin-commands.json; invoke as $bdb-aos:loop.

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。

Orchestrates the tdmcp feature team end-to-end: design/wireframe → build → integrate → QA → release. Use whenever the user wants to build, implement, develop, ship, or add one or more tdmcp features/tools/effects/controls/AI-prompts for TouchDesigner, or to run them through a coordinated design→develop→QA→deploy pipeline. Also use for follow-ups: re-run, continue, update, fix, or improve a feature/batch, ship the next version, or rebuild just one part of a previous run. Single feature or a whole batch.

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 a tdmcp feature into an implementable spec before any code is written — choose the layer, define the Zod input schema, lay out the TD network topology, plan the bridge/Python approach, sketch a UI wireframe when relevant, and list probe-first risks + the test plan. Use whenever a tdmcp feature idea needs a design/wireframe/spec, or when someone asks to plan/scope/architect a new tool, generator, effect, control, or AI prompt for the TouchDesigner 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。

Survey the whole tdmcp project and produce a prioritized list of NEW features it could implement — across artist controls, CLI/DX, AI/LLM integration, and TouchDesigner depth. Use whenever the user wants to brainstorm, discover, survey, list, or audit what features/tools/effects/controls/commands/prompts/capabilities tdmcp *could* add, asks 'what could we build / what's missing / what are the opportunities / ideas for the project', or wants a feature backlog or gap analysis. Also for follow-ups: re-run, refresh, update, re-survey, deepen, or re-prioritize the backlog, or survey just one surface (e.g. 'CLI ideas only'). This is the IDEATION harness — it produces a list to decide from; it does NOT build. When the user has already chosen a feature and wants it implemented/shipped/added, use tdmcp-pipeline instead.

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 task should repeat on a schedule or until a condition holds (CI until green, follow a PR to merge, review rounds until no blockers, daily session summary). Ships ready prompt templates with run and duration limits, stop conditions and go-gate safety rules, and per-harness loop invocation.

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。

Linear multi-agent build pipeline with file hand-offs in production_artifacts/, run after /bdbrainstorm or /grill-me. This is the linear variant — no state.json, no repair loop, no dispatcher graph — distinct from startcycle-graph, which adds durable state and automated escalation. Use when an approved plan should be built, when the user types /startcycle or "run a startcycle", or when you pick a startcycle variant from the situation yourself (no user prompt needed).

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。

agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.

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。

Interactive 9-step prompt crafting and delegation protocol for autonomous multi-agent teams. Enforces objective verification, integrity modes, and acceptance criteria across Antigravity, Claude Code, Cursor, OpenCode, Codex, and Roo Code.

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。

LLM Agent engineering: pattern selection (12-mode matrix), data simulation, convergence iteration. Covers intent routing, function calling, ReAct, MCP, prompt chaining, guardrails, 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。

Convert changelogs, release notes, and version updates into Ozor.ai video prompts. Use this skill whenever the user has a CHANGELOG.md, release notes, GitHub release, version bump summary, or any list of product changes and wants to turn them into a video. Trigger on phrases like 'video from my changelog', 'release notes video', 'make a video from this update', 'announce this release', 'version update video', 'what's new video', 'product update video', 'feature release video', or any request to transform a list of product changes into video format using Ozor.

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 an AI video end-to-end on Ozor.ai from a short text brief. Use this skill whenever the user wants to actually create a video (not just write a prompt) from a creative description, idea, or short brief — e.g. 'make me a video about X', 'generate a launch video for Y', 'create an explainer for Z', 'render a video', 'produce a 30s ad about ...', 'spin up a quick video for our new feature'. This skill runs the full Ozor MCP pipeline: generate_video → wait_for_job → export_video → wait_for_export → get_embed_code, and returns the shareUrl, editorUrl, downloadUrl, and a ready-to-paste <iframe> embed. Do NOT use this skill when the input is a document/PDF/PPTX/deck/URL — use ozor-document-video or ozor-url-to-video instead.

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。

Convert any landing page or website into an Ozor.ai video prompt. Use this skill whenever the user provides a URL, landing page content, or website copy and wants to turn it into a video. Trigger on phrases like 'make a video from my website', 'video from this landing page', 'turn my homepage into a video', 'video from this URL', 'product page to video', 'website to video', 'marketing video from my site', 'convert this page to video', or any request to transform web content into video format using Ozor.

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。