「wan」の検索結果

Read GitHub Actions CI for the current branch or open PR, triage failing checks, reproduce locally, and fix scoped issues until green. Use whenever the user mentions CI failures, red checks, failed pipeline, GitHub Actions, merge blocked, fix the build, babysit CI, gh run failed, ruff/ty errors, failing pytest, example run failed, or asks to check CI on this branch — even if they only paste a log snippet. Also use after implementing a feature when tests, lint, or typecheck might have broken.

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 contribute a fix or roadmap item back to the Hedgehog project itself (skyf0xx/hedgehog) rather than their own project. Triggers on "let's fix that in Hedgehog", "I want to contribute", "let's pick up a roadmap item", or when `tweaker` offers this at the end of a build and the user says yes. Covers forking/branching, making the change under Hedgehog's own repo rules, committing with Conventional Commits, and opening the PR.

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 Claude Code plugins into generic, platform-agnostic format. Supports full conversion (skills, agents, hooks), flatten mode (skills only — agents converted to skills, hooks absorbed), or nested mode (agents nested as pure markdown within parent skills, hooks absorbed). Full mode supports per-group or unified output layouts — unified merges all groups into a single directory organized by component type. Strips Claude Code-specific implementation details to produce clean markdown files preserving only the intent and instructions. Use when asked to "make this portable", "convert to generic format", "export plugin", "create universal skills", "strip platform dependencies", "make harness-agnostic", "decouple from Claude Code", "flatten to skills only", "nest agents in skills", or when the user wants their plugin content usable outside Claude Code. Also use when the user wants to share skills with teams using different agent frameworks.

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。

Conduct an adaptive interactive interview on any topic and produce a structured markdown report, summary, or implementation plan. Use when the user says "interview me", "interview me about", "run an interview on", "help me think through", or wants guided discovery on any subject. Also triggers on "talk me through", "explore X with me", "help me plan Y", or "walk me through my thinking on Z" when the user wants a guided conversation rather than a direct answer. Applies broadly — career decisions, project ideas, product direction, personal goals, research questions, team problems — not just technical topics.

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 Agnes AI text, image, or video generation and should execute it through the agnes-ai-cli command line instead of hand-writing raw HTTP requests.

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 technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants measurable accessibility, performance, responsive, theming, or anti-pattern findings—not when they mainly want an overall UX critique or final visual/detail polish.

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-pipeline aggregator that scans AI agent cache directories (.claude, .cursor, .antigravity, .openclaw) or any user-specified directory for experimentation logs, extracts insights and numeric results, and formats them as PaperOrchestra-ready inputs (idea.md + experimental_log.md). TRIGGER when the user says "aggregate my agent logs for paper writing", "extract experiments from my coding agent history", "prepare PaperOrchestra inputs from my cache", "turn my agent logs into a paper", mentions a folder or directory they want to use as the basis for a paper, or wants to run PaperOrchestra but only has scattered agent experiment histories rather than structured inputs. Run this BEFORE paper-orchestra. Also called automatically by paper-orchestra when workspace/inputs/idea.md or workspace/inputs/experimental_log.md are missing.

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。

Research a topic and create a new note in the vault. Use this skill whenever the user wants to learn about a topic they don't know yet, investigate a question, explore an idea, or asks "what is X", "research X", "tell me about X", "I want to understand X", "look into X". Also triggers on /research. This is for BROAD research (web + vault) — for academic papers specifically, use /paper-discover 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。

CORE learning workflow — use this whenever the user has a source note open (paper, post, book, lecture, course, clipping) and wants to extract knowledge, understand what they just read, or build it into their vault. Triggers on "process this note", "process this paper", "extract concepts", "what can I learn from this", "atomize this", "add this to my vault", "what's important here", or when the user shares a note and asks for help understanding it. Do NOT wait for an explicit /process command — if the user is engaging with a source note and wants to go deeper, this skill applies.

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。

Conversational profile builder. Produces validated JSON config files for any rootnode Skill that consumes profile-shaped configuration (handoff trigger check, mode router, critic gate, future Skills). Reads a target JSON Schema (draft-07), conducts a progressive-depth interview using plain-language questions, validates answers, and writes the resulting JSON to a destination path. Schema-agnostic — works with any profile schema conforming to draft-07. Use when a user needs to create, clone, or revise a profile and you do not want them hand-editing JSON. Trigger on: "build me a profile," "create a profile," "I need a profile for X," "set up my profile," "edit my profile," "clone the X profile," "walk me through making a profile." Do NOT use when the user already has a working profile and only wants to invoke the consuming Skill, when the schema cannot be located, or for non-profile JSON config work. Always validate before writing.

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。

Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related small-molecule or protein modeling tasks. Ideal for programmatic batch screening, multi-step chemistry pipelines, and workflows that would otherwise require maintaining local HPC/GPU infrastructure.

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。

Generalised autonomous optimisation loop — soft RLVR for any artifact a user can measure. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning from each attempt. Triggers include: "optimise this", "keep improving until it's good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles. Also use when the user wants to improve a system prompt, a data pipeline, a writing style, or any artifact where quality can be decomposed into measurable tracks. For inference optimisation tasks (model latency, throughput, quantization, GPU deployment), a* delegates the low-level tuning to AITune while maintaining quality tracking and 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。

iOS/Android シミュレーターのスクリーンショットから macOS ウィンドウのタイトルバー （"iPhone 16 Pro / iOS 18.6" 等のシミュレーター chrome）を自動検出して除去するスキル。 alpha チャンネルを利用してバーの高さを自動検出するため、1x/2x/3x どの解像度でも動作する。 Use this skill when the user wants to crop simulator screenshots, remove the simulator title bar, clean up Xcode simulator captures, or prepare app screenshots for App Store. Triggers: "シミュレーターのスクショからバーを除去", "simulator chrome crop", "タイトルバー除去", "スクショのクロップ", "simulator screenshot crop", "シミュレーターのヘッダー消して", "スクショ切り抜き", "crop simulator".

Design and build runnable iOS UI mockups in SwiftUI, including UI direction, multiple visual or interaction variants, realistic sample data, state switching, Xcode Previews, and Simulator validation. Use when the user wants to explore what an iOS screen should look like, compare SwiftUI UI ideas, create a clickable native prototype, validate an app flow before production implementation, or asks for a SwiftUI mock, iOS mockup, native prototype, 画面モック, UI案, SwiftUIで動くモック, or 実際に触れるiOSモック.

Convert SVG files to high-quality PNG images with precise control over dimensions, background color, and CSS rendering (including mix-blend-mode, filters, gradients). Use this skill when the user wants to: (1) convert SVG to PNG, (2) generate app icons or splash screens from SVG source, (3) batch-generate multiple PNG sizes from a single SVG, (4) render SVG with advanced CSS features like mix-blend-mode or filters to PNG. Triggers: "SVG to PNG", "SVG変換", "PNG変換", "アイコン生成", "スプラッシュ生成", "app icon from SVG", "favicon generation", "splash screen generation".

Create or improve a Senpai target repository's program.md. Use this skill whenever the user wants to point Senpai at a fresh ML or research target repository, define the research objective, primary metric, benchmark contract, allowed edit boundaries, W&B reporting contract, or prepare a repo for autonomous advisor/student experiment loops.

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。

Comprehensive primary skill for agents working with Weights & Biases. Covers both the W&B SDK (training runs, metrics, artifacts, sweeps) and the Weave SDK (GenAI traces, evaluations, scorers). Includes helper libraries, gotcha tables, and data analysis patterns. Use this skill whenever the user asks about W&B runs, Weave traces, evaluations, training metrics, loss curves, model comparisons, or any Weights & Biases data — even if they don't say "W&B" 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。

Use when the user wants to run SQL - especially analytical SQL - on local files (parquet/csv/json), URLs, S3 paths, or remote databases (Postgres, MySQL, MongoDB, ClickHouse Cloud, Iceberg, Delta Lake) without setting up a server. Provides chDB - embedded ClickHouse SQL in Python with 1000+ functions, Session for stateful multi-step pipelines, parametrized queries, and cross-source joins via `s3()`, `mysql()`, `postgresql()`, `iceberg()`, `deltaLake()`, `remoteSecure()` table functions. TRIGGER when: user wants SQL on parquet/csv/files or across remote analytical sources; uses ClickHouse SQL features (window functions, windowFunnel, geoToH3, JSON path ops, Session, parametrized queries); imports `chdb` or calls `chdb.query()`. SKIP this skill for pandas-style DataFrame method-chaining (use chdb-datastore instead) or ClickHouse server administration.

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。

对 DiT（扩散/多模态生成）模型执行 W8A8 动态（data-free）或 W8A8 MXFP8（data-free）量化。覆盖 HunyuanVideo、Wan2.2-T2V/I2V/TI2V、FLUX.1-dev（已迁移）、SD3、Sana、HunyuanDiT、CogViewX 等。YAML apiversion 固定 multimodal_sd_modelslim_v1，统一 MultimodalPipelineInterface 重构路径（不再保留 LegacyMultimodalPipelineInterface）。模板与字段以 msmodelslim/model/hunyuan_video/model_adapter.py（唯一已迁移到重构路径且 lab_practice YAML 已 validated 的 DiT）为参考；其它 DiT 需按各自推理仓的 `parse_args` 调整字段集合。data-free 指不引入外部激活校准数据，spec.dataset（校准集短名，短名如 wan2_2_t2v；enable_dump: false 时不参与 dump）仍必填；精度调优通过下游经验库 L2 §7 + 直接调 `quantization-expert-experience-tuning-rules/scripts/apply_rollback.py`（整层回退）扩展 exclude 列表，闭环由 `quantization-accuracy-tuning-orchestrator` 调度。

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。

Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.

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。

Launch a product across 56 platforms — generates all copy, tracks submissions, and guides launch day operations. Use this skill whenever someone wants to submit to directories, get backlinks, launch on Product Hunt or Hacker News, run an AppSumo campaign, or needs help getting their product in front of users. Also triggers on: 'I just built something and want people to know', 'how do I get users', 'where can I submit my SaaS', 'get backlinks for my product', 'multi-platform launch', 'directory submissions', 'startup launch playbook', 'submit everywhere', 'launch across platforms'. This is the operational launcher — it does the work. For high-level launch strategy and phased planning, see launch-strategy.

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 wants to audit, review, or diagnose SEO issues, plan site architecture, or implement schema markup. Use when someone says 'SEO audit', 'technical SEO', 'site architecture', 'schema markup', 'internal linking', 'why isn't my site ranking', 'site health check', 'crawl issues', 'fix my SEO', 'my traffic dropped', 'rankings fell', or 'site not ranking'. Also trigger when someone wants to plan URL structure, design navigation, add structured data, or review any website for search performance. Three modes: Full Audit (comprehensive health check), Architecture (URL structure and internal linking), Schema (JSON-LD structured data). Covers crawlability, indexation, Core Web Vitals, and on-page factors.

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。

Creates high-converting 'X vs Y' and 'X alternatives' SEO pages that capture comparison search traffic. Researches competitors, writes honest comparison content, and adds schema markup (FAQPage, ItemList). Use when someone needs alternatives pages, comparison content, or says 'alternatives page', 'vs page', 'comparison', 'competitor alternatives', 'X vs Y page', or wants to capture competitor brand search traffic with SEO content. Also trigger when someone wants to rank for competitor brand names, capture competitor search traffic, create a compare page, or build a competitive content hub. Even if they just say 'how do we compete with X' or 'we need to show up when people search for [competitor]', this skill applies. Owns the individual alternatives / vs / comparison page. For a batch roadmap of many pages with a phase tracker, see /seo-machine. For programmatic SEO and templated content at scale, see /seo-content.

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 train a reusable face-faithful Soul Character identity on Higgsfield. One-time training returns a reference_id passed to Soul models in higgsfield-generate via `--soul-id`. Use this skill whenever: "train soul character", "create my Soul", "train my face", "make my digital twin", "build me an avatar", "create a character of me", "set up identity for video", "I want my face in generated images", "face-faithful character", "reusable character", "brand character training", "build a character from photos", "soul training", "soul-id create". After training, logs the soul_reference_id to `brand/assets.md`. NOT for: one-shot face swaps (use higgsfield-generate with --image), fictional/non-photo avatars (use higgsfield-generate with a prompt). Requires Higgsfield CLI + Basic plan or higher.

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。