「lora」の検索結果

World-class character and art style consistency for AI-generated images and videos - ensures visual coherence across series, maintains character identity, and provides rigorous QA before deliveryUse when "character consistency, art style, same character, consistent character, visual continuity, series, turnaround sheet, character sheet, reference image, character bible, style guide, anime character, consistent look, face consistency, outfit consistency, lora training, ip-adapter, flux kontext, visual qa, art quality, generation review, style drift, character drift, character-consistency, art-style, visual-qa, ai-art, image-generation, video-generation, anime, illustration, lora, ip-adapter, flux, midjourney, stable-diffusion" mentioned.

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。

Adapts LLMs: SFT dataset loss masking, LoRA and QLoRA, full FT vs PEFT, distillation, pruning, tokenizer fragmentation. Use when fine-tuning or compressing a model.

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。

Stage exploration before instruction on complex problems. The learner produces two attempted approaches before consolidation — which builds on those attempts, not from scratch. Use for genuinely hard problems where struggle produces deeper learning.

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。

Plan and run manual tests of the project's running app. Runs a session in one of five modes: exploratory, verification, smoke, assessment (UX, localization, accessibility, improvement review), or AI probe. Also writes a manual test plan that holds only what automated tests cannot judge. Use whenever the user asks, in any language, for something to be tested by hand or for a manual test plan — "manual test", "exploratory test", "bug hunt", "verify the bug fix", "smoke test", "QA this screen", "review this screen's UX", "what would you improve", "check the localized copy", "test the AI agent's answers", "write manual test cases", "kịch bản test manual" — or assigns a test design, test plan or test-case IDs to execute by hand. Not for writing automated tests.

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。

Expert guide for synthetic dataset generation, LLM-as-a-judge filtering, QLoRA fine-tuning (Unsloth), DPO alignment, and GGUF/Ollama export for local SLMs / Panduan ahli generasi data sintetis, fine-tuning QLoRA, DPO, dan ekspor GGUF/Ollama.

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。

Apache Superset is a widely adopted open-source BI platform for SQL exploration, chart building, and dashboard delivery. This skill is useful when an agent needs to query warehouse data, assemble dashboards, or explain metrics using a mature analytics interface instead of ad hoc notebook 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。

Use when the user wants to post or schedule to Instagram through Publora: a single image, a 2-10 image carousel, a Reel or a Story. Requires a Business account and an image or video; text-only posts are rejected by the API. Not for Threads (use threads-post).

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 publish or schedule a LinkedIn post through Publora: text, a multi-image grid, a video, a PDF document, or @mentions. Not for analytics, reactions, comments or reshares (use linkedin-analytics), and not for other 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。

Use when the user wants to post or schedule to Bluesky through Publora. Handles the 300-character cap, auto-detected hashtags and links, up to 4 images, and videos. Alt text cannot be set through the API. Needs a Bluesky app password, never the main password. Not for Mastodon (use social-post).

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。

Analyze LinkedIn performance and manage engagement through Publora. Use when the user asks how a LinkedIn post or account performed (impressions, reach, reactions, comments, reshares, follower growth) or wants to react, comment, reshare or resolve an @mention. Statistics run over the REST API, engagement over MCP tools. Not for creating posts (use linkedin-post).

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 post or schedule to a Telegram channel or group through Publora, using a bot. Covers Telegram markdown, silent delivery, link previews and forward protection. Bot API caps media captions at 1,024 characters and videos at 50 MB. Not for other platforms (each has its own skill).

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 post or schedule to YouTube, a Facebook Page or Mastodon through Publora. YouTube needs a video on every post, Facebook publishes to Pages only, Mastodon caps at 500 characters. Not for the platforms that have their own skill.

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 upload or schedule a TikTok video through Publora, with privacy, comment, duet, stitch and commercial-disclosure settings. Video runs 3 seconds to 10 minutes at 23+ FPS; carousels take up to 35 images. Unaudited apps can publish private videos only. Not for Reels (use instagram-post).

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。

Code exploration strategies for understanding unfamiliar codebases. Use when exploring unknown code, debugging, or analyzing architecture.

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。

Parallel agent orchestration for OST exploration. Fan-out multiple solution explorations, fan-in results to compare and select winners.

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。

Hugging Face Hub operations, model inference, dataset management, PEFT/LoRA fine-tuning, and Spaces deployment via MCP tools and Python APIs

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。

AI intuitive exploration for approaching unknown codebases, problems, or systems without preconceptions. Adapts the Coordinate Remote Viewing protocol to AI investigation: cooldown (clear assumptions), staged data gathering (raw signals → dimensional → analytical), AOL management (separating observations from premature labels), and structured review. Use when investigating an unfamiliar codebase with unknown architecture, debugging a problem where premature hypotheses could mislead, exploring a domain with limited context, or when previous attempts have been led astray by assumptions and "beginner's mind" would be more productive.

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。

AI solution exploration using ant colony optimization — deploying scout hypotheses, reinforcing promising approaches, detecting diminishing returns, and knowing when to abandon a strategy. Use when facing a problem with multiple plausible approaches and no clear winner, when the first approach is not working but alternatives are unclear, when debugging with no obvious root cause requiring parallel hypothesis investigation, or when previous attempts have converged prematurely on a suboptimal approach.

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 ant colony optimization and foraging theory to resource search, exploration-exploitation tradeoffs, and distributed discovery. Covers scout deployment, trail reinforcement, diminishing returns detection, and adaptive foraging strategy selection. Use when searching a large solution space where brute-force enumeration is impractical, balancing investment between exploring new approaches and deepening known good ones, optimizing resource allocation across uncertain opportunities, or diagnosing premature convergence on local optima.

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。

AI unconstrained creative exploration — deliberately dropping structure to let associations form freely. The one skill that inverts the standard procedure format: instead of inputs, steps, and validation, dream opens space for emergence without evaluation. Use before design work, before naming things, before choosing between approaches, or anywhere that premature structure kills the best option.

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 polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid. Also use for Archify, interactive or animated HTML diagrams, インタラクティブ図, 動く構成図. When an editable .drawio file is required, use the draw.io workflow instead and treat Archify HTML only as a supplement.

Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.

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。

Multi-agent exploration-to-PR pipeline for safely exploring, fixing, and shipping a feature or CLI. Use when the user says: "explore X", "test and ship X", "run the pipeline on X", "run /feature-pipeline on X", "let's properly investigate X", "stress-test X and file issues", or "take X through the full pipeline." Also triggers on: "find what's broken in X", "test X end-to-end", "do a sandbox review of X", "file issues for X and fix them." Do NOT use for single-file bug fixes or one-off edits — the overhead is only justified when exploration, planning approval, and CI watching all matter. Manages state via scripts/state.sh (jq required). Five phases: LIGHTER explores → ORCHESTRATOR drafts PR → HEAVIER plans (user approves first) → ORCHESTRATOR commits → HEAVIER sandbox review → LIGHTER iterates CI → LIGHTER drift check + summary. Four mandatory stop hooks (M1–M4) gate each phase transition.

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。

Rapid UI prototyping — generates 3 visually distinct HTML/CSS components from a text prompt and serves them in a live browser gallery. Use when user runs /prototype, asks to "prototype a UI", "mock up a component", "generate HTML mockups", "create UI variations", "design exploration", "quick UI concept", or wants to see multiple visual approaches to a component. Also trigger when user says "show me different ways to build...", "explore different designs for...", or wants rapid visual exploration of a UI idea — even without saying "prototype" explicitly.

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。