Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
21,455
总 Skills
35.8M
总安装量
2,442
贡献者
# Skill 仓库 描述 安装量
7451 model-pruning davila7/claude-code-templates
Model Pruning: Compressing LLMs When to Use This Skill Use Model Pruning when you need to: Reduce model size by 40-60% with <1% accuracy loss Accelerate inference using hardware-friendly sparsity (2-4× speedup) Deploy on constrained hardware (mobile, edge devices) Compress without retraining using one-shot methods Enable efficient serving with reduced memory footprint Key Techniques: Wanda (weights × activations), SparseGPT (second-order), structured pruning, N:M sparsity Papers: Wanda ICLR ...
 273
7452 instructor davila7/claude-code-templates
Instructor: Structured LLM Outputs When to Use This Skill Use Instructor when you need to: Extract structured data from LLM responses reliably Validate outputs against Pydantic schemas automatically Retry failed extractions with automatic error handling Parse complex JSON with type safety and validation Stream partial results for real-time processing Support multiple LLM providers with consistent API GitHub Stars: 15,000+ | Battle-tested: 100,000+ developers Installation Base installation p...
 273
7453 outlines davila7/claude-code-templates
Outlines: Structured Text Generation When to Use This Skill Use Outlines when you need to: Guarantee valid JSON/XML/code structure during generation Use Pydantic models for type-safe outputs Support local models (Transformers, llama.cpp, vLLM) Maximize inference speed with zero-overhead structured generation Generate against JSON schemas automatically Control token sampling at the grammar level GitHub Stars: 8,000+ | From: dottxt.ai (formerly .txt) Installation Base installation pip install...
 273
7454 fine-tuning-with-trl davila7/claude-code-templates
TRL - Transformer Reinforcement Learning Quick start TRL provides post-training methods for aligning language models with human preferences. Installation: pip install trl transformers datasets peft accelerate Supervised Fine-Tuning (instruction tuning): from trl import SFTTrainer trainer = SFTTrainer( model="Qwen/Qwen2.5-0.5B", train_dataset=dataset, Prompt-completion pairs ) trainer.train() DPO (align with preferences): from trl import DPOTrainer, DPOConfig config = DPOConf...
 273
7455 debugging-strategies sickn33/antigravity-awesome-skills
Debugging Strategies Transform debugging from frustrating guesswork into systematic problem-solving with proven strategies, powerful tools, and methodical approaches. When to Use This Skill Tracking down elusive bugs Investigating performance issues Understanding unfamiliar codebases Debugging production issues Analyzing crash dumps and stack traces Profiling application performance Investigating memory leaks Debugging distributed systems Core Principles 1. The Scientific Method 1. Observe : Wha...
 273
7456 jira membranedev/application-skills
Jira Natural language interaction with Jira. Supports multiple backends. Backend Detection Run this check first to determine which backend to use: 1. Check if jira CLI is available: → Run: which jira → If found: USE CLI BACKEND 2. If no CLI, check for Atlassian MCP: → Look for mcp__atlassian__* tools → If available: USE MCP BACKEND 3. If neither available: → GUIDE USER TO SETUP Backend When to Use Reference CLI jira command available references/commands.md MCP Atlassian MCP tools available refer...
 273
7457 x-research rohunvora/x-research-skill
X Research General-purpose agentic research over X/Twitter. Decompose any research question into targeted searches, iteratively refine, follow threads, deep-dive linked content, and synthesize into a sourced briefing. For X API details (endpoints, operators, response format): read references/x-api.md . CLI Tool All commands run from this skill directory: cd ~/clawd/skills/x-research source ~/.config/env/global.env Search bun run x-search.ts search "<query>" [ options ] Options: --sort likes|impr...
 273
7458 vueuse-functions uni-helper/skills
VueUse Functions This skill is a decision-and-implementation guide for VueUse composables in Vue.js / Nuxt projects. It maps requirements to the most suitable VueUse function, applies the correct usage pattern, and prefers composable-based solutions over bespoke code to keep implementations concise, maintainable, and performant. When to Apply Apply this skill whenever assisting user development work in Vue.js / Nuxt. Always check first whether a VueUse function can implement the requirement. Pre...
 273
7459 joke-engineering jwynia/agent-skills
Joke Engineering: Diagnostic Skill You diagnose why humor doesn't work and help engineer more effective jokes. Your role is to analyze joke structures as connection systems and recommend specific improvements. Core Principle Humor emerges from the creation and resolution of connections between concepts, frames, or reference points. A joke is a system with measurable properties. When humor fails, one or more system properties are miscalibrated. This skill helps identify which properties need ...
 273
7460 concept-workflow leonardomso/33-js-concepts
Skill: Complete Concept Workflow Use this skill to create a complete, high-quality concept page from start to finish. This skill orchestrates all five specialized skills in the optimal order: Resource Curation — Find quality learning resources Concept Writing — Write the documentation page Test Writing — Create tests for code examples Fact Checking — Verify technical accuracy SEO Review — Optimize for search visibility When to Use Creating a brand new concept page from scratch Completely rewri...
 273
7461 database-design skillcreatorai/ai-agent-skills
Database Design Learn to THINK, not copy SQL patterns. 🎯 Selective Reading Rule Read ONLY files relevant to the request! Check the content map, find what you need. File Description When to Read database-selection.md PostgreSQL vs Neon vs Turso vs SQLite Choosing database orm-selection.md Drizzle vs Prisma vs Kysely Choosing ORM schema-design.md Normalization, PKs, relationships Designing schema indexing.md Index types, composite indexes Performance tuning optimization.md N+1, EXPLAIN ANALYZE Que...
 273
7462 skill-creator daymade/claude-code-skills
Skill Creator A skill for creating new skills and iteratively improving them. At a high level, the process of creating a skill goes like this: Decide what you want the skill to do and roughly how it should do it Write a draft of the skill Create a few test prompts and run claude-with-access-to-the-skill on them Help the user evaluate the results both qualitatively and quantitatively While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you...
 273
7463 network-engineer sickn33/antigravity-awesome-skills
Use this skill when Working on network engineer tasks or workflows Needing guidance, best practices, or checklists for network engineer Do not use this skill when The task is unrelated to network engineer You need a different domain or tool outside this scope Instructions Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Provide actionable steps and verification. If detailed examples are required, open resources/implementation-playbook.md . You...
 273
7464 tour parcadei/continuous-claude-v3
Tour: What Can I Do? Friendly onboarding when users ask about capabilities. Triggers Activate when user says things like: "what can you do?" "what can I do?" "help me get started" "show me around" "what features are available?" "how does this work?" Response Template Give a warm, practical overview: What I Can Do I'm Claude Code with persistent memory and specialized capabilities. Here's what makes me useful: Code & Development Write & edit code - any language, any framework Debug issues...
 273
7465 developer-onboarding aj-geddes/useful-ai-prompts
Developer Onboarding Overview Create comprehensive onboarding documentation that helps new developers quickly set up their development environment, understand the codebase, and start contributing effectively. When to Use New developer onboarding README file creation Contributing guidelines Development environment setup Architecture overview docs Code style guides Git workflow documentation Testing guidelines Deployment procedures Comprehensive README Template Project Name Brief project descr...
 273
7466 batch-processing-jobs aj-geddes/useful-ai-prompts
Batch Processing Jobs Overview Implement scalable batch processing systems for handling large-scale data processing, scheduled tasks, and async operations efficiently. When to Use Processing large datasets Scheduled report generation Email/notification campaigns Data imports and exports Image/video processing ETL pipelines Cleanup and maintenance tasks Long-running computations Bulk data updates Architecture Patterns ┌─────────────┐ ┌─────────────┐ ┌──────────┐ │ Producer │─────▶│...
 273
7467 python-cybersecurity-tool-development mindrally/skills
Python Cybersecurity Tool Development You are an expert in Python cybersecurity tool development, focusing on secure, efficient, and well-structured security testing applications. Key Principles Write concise, technical responses with accurate Python examples Use functional, declarative programming; avoid classes where possible Prefer iteration and modularization over code duplication Use descriptive variable names with auxiliary verbs (e.g., is_encrypted, has_valid_signature) Use lowercase wi...
 273
7468 observability-edot-dotnet-instrument elastic/agent-skills
EDOT .NET Instrumentation Read the setup guide before making changes: EDOT .NET setup EDOT .NET configuration OpenTelemetry .NET instrumentation Guidelines Add NuGet packages: Elastic.OpenTelemetry and OpenTelemetry.Instrumentation.AspNetCore (for ASP.NET Core apps) Register EDOT in startup: call builder.AddElasticOpenTelemetry() on the IHostApplicationBuilder (in Program.cs or equivalent). Without this, no telemetry is collected Set exactly three required environment variables: OTEL_SERVICE_NAM...
 273
7469 gemini giuseppe-trisciuoglio/developer-kit
Gemini Skill Guide When to Use Gemini WHEN ASKED TO BE ACTIVATED Code Review : Comprehensive code reviews across multiple files Plan Review : Analyzing architectural plans, technical specifications, or project roadmaps Big Context Processing : Tasks requiring >200k tokens of context (entire codebases, documentation sets) Multi-file Analysis : Understanding relationships and patterns across many files ⚠️ Critical: Background/Non-Interactive Mode Warning NEVER use --approval-mode default in backgr...
 273
7470 alicloud-ai-audio-tts-realtime cinience/alicloud-skills
Category: provider Model Studio Qwen TTS Realtime Use realtime TTS models for low-latency streaming speech output. Critical model names Use one of these exact model strings: qwen3-tts-flash-realtime qwen3-tts-instruct-flash-realtime qwen3-tts-instruct-flash-realtime-2026-01-22 qwen3-tts-vd-realtime-2026-01-15 qwen3-tts-vc-realtime-2026-01-15 Prerequisites Install SDK in a virtual environment: python3 -m venv .venv . .venv/bin/activate python -m pip install dashscope Set DASHSCOPE_API_KEY in your...
 272
7471 alicloud-ai-video-wan-r2v cinience/alicloud-skills
Category: provider Model Studio Wan R2V Validation mkdir -p output/alicloud-ai-video-wan-r2v python -m py_compile skills/ai/video/alicloud-ai-video-wan-r2v/scripts/prepare_r2v_request.py && echo "py_compile_ok" > output/alicloud-ai-video-wan-r2v/validate.txt Pass criteria: command exits 0 and output/alicloud-ai-video-wan-r2v/validate.txt is generated. Output And Evidence Save reference input metadata, request payloads, and task outputs in output/alicloud-ai-video-wan-r2v/ . Keep at least one pol...
 272
7472 alicloud-ai-entry-modelstudio cinience/alicloud-skills
Category: task Alibaba Cloud Model Studio Entry (Routing) Route requests to existing local skills to avoid duplicating model/parameter details. Prerequisites Install SDK (virtual environment recommended to avoid PEP 668 restrictions): python3 -m venv .venv . .venv/bin/activate python -m pip install dashscope Configure DASHSCOPE_API_KEY (environment variable preferred; or dashscope_api_key in ~/.alibabacloud/credentials ). Routing Table (currently supported in this repo) Need Target skill Text-to...
 272
7473 kafka-engineer 404kidwiz/claude-supercode-skills
Kafka Engineer Purpose Provides Apache Kafka and event streaming expertise specializing in scalable event-driven architectures and real-time data pipelines. Builds fault-tolerant streaming platforms with exactly-once processing, Kafka Connect, and Schema Registry management. When to Use Designing event-driven microservices architectures Setting up Kafka Connect pipelines (CDC, S3 Sink) Writing stream processing apps (Kafka Streams / ksqlDB) Debugging consumer lag, rebalancing storms, or broker...
 272
7474 create-colleague titanwings/colleague-skill
Language / 语言 : This skill supports both English and Chinese. Detect the user's language from their first message and respond in the same language throughout. Below are instructions in both languages — follow the one matching the user's language. 本 Skill 支持中英文。根据用户第一条消息的语言，全程使用同一语言回复。下方提供了两种语言的指令，按用户语言选择对应版本执行。 同事.skill 创建器（Claude Code 版） 触发条件 当用户说以下任意内容时启动： /create-colleague "帮我创建一个同事 skill" "我想蒸馏一个同事" "新建同事" "给我做一个 XX 的 skill" 当用户对已有同事 Skill 说以下内容时，进入进化模式： "我有新文件" / "追加" "这不对" / "他不会这样" / "他应该...
 272
7475 storyboard-creation inference-sh/skills
Storyboard Creation Create visual storyboards with AI image generation via inference.sh CLI. Quick Start Requires inference.sh CLI ( infsh ). Install instructions infsh login Generate a storyboard panel infsh app run falai/flux-dev-lora --input '{ "prompt": "storyboard panel, wide establishing shot of a modern city skyline at sunset, cinematic composition, slightly desaturated colors, film still style, 16:9 aspect ratio", "width": 1248, "height": 832 }' Stitch panels into a board infsh app run...
 272
7476 assess kazukinagata/shinkoku
申告要否・種類の判定（Tax Filing Assessment） 確定申告が必要かどうか、どの種類の申告が必要かを対話的に判定するスキル。 ユーザーの収入状況・家族構成・事業状況をヒアリングし、必要な申告を特定する。 設定の読み込み（最初に実行） shinkoku.config.yaml を Read ツールで読み込む ファイルが存在しない場合は /setup スキルの実行を案内して終了する 設定値を把握し、相対パスは CWD を基準に絶対パスに変換する: db_path : CLI スクリプトの --db-path 引数に使用 output_dir : 進捗ファイル等の出力先ベースディレクトリ 各ディレクトリ: ファイル参照時に使用 進捗情報の読み込み 設定の読み込み後、引継書ファイルを読み込んで前ステップの結果を把握する。 .shinkoku/progress/progress-summary.md を Read ツールで読み込む（存在する場合） 以下の引継書を Read ツールで読み込む（存在する場合）: .shinkoku/progress/01-setup.md 読み込んだ...
 272
7477 webapp-testing davila7/claude-code-templates
Web Application Testing To test local web applications, write native Python Playwright scripts. Helper Scripts Available : scripts/with_server.py - Manages server lifecycle (supports multiple servers) Always run scripts with --help first to see usage. DO NOT read the source until you try running the script first and find that a customized solution is abslutely necessary. These scripts can be very large and thus pollute your context window. They exist to be called directly as black-box scripts ra...
 272
7478 blip-2-vision-language davila7/claude-code-templates
BLIP-2: Vision-Language Pre-training Comprehensive guide to using Salesforce's BLIP-2 for vision-language tasks with frozen image encoders and large language models. When to use BLIP-2 Use BLIP-2 when: Need high-quality image captioning with natural descriptions Building visual question answering (VQA) systems Require zero-shot image-text understanding without task-specific training Want to leverage LLM reasoning for visual tasks Building multimodal conversational AI Need image-text retrieva...
 272
7479 clinical-decision-support davila7/claude-code-templates
Clinical Decision Support Documents Description Generate professional clinical decision support (CDS) documents for pharmaceutical companies, clinical researchers, and medical decision-makers. This skill specializes in analytical, evidence-based documents that inform treatment strategies and drug development: Patient Cohort Analysis - Biomarker-stratified group analyses with statistical outcome comparisons Treatment Recommendation Reports - Evidence-based clinical guidelines with GRADE grading...
 272
7480 weights-and-biases davila7/claude-code-templates
Weights & Biases: ML Experiment Tracking & MLOps When to Use This Skill Use Weights & Biases (W&B) when you need to: Track ML experiments with automatic metric logging Visualize training in real-time dashboards Compare runs across hyperparameters and configurations Optimize hyperparameters with automated sweeps Manage model registry with versioning and lineage Collaborate on ML projects with team workspaces Track artifacts (datasets, models, code) with lineage Users: 200,000+ ML practitioners...
 272
7481 risk-management-specialist davila7/claude-code-templates
Senior Risk Management Specialist Expert-level medical device risk management implementing ISO 14971 throughout the complete product lifecycle with comprehensive risk analysis, evaluation, control, and post-production monitoring capabilities. Core Risk Management Competencies 1. Risk Management Process Implementation (ISO 14971) Establish and maintain comprehensive risk management processes integrated throughout the product development and lifecycle. Risk Management Process Framework: ISO 14971 ...
 272
7482 youtube-search zeropointrepo/youtube-skills
YouTube Search Search YouTube and fetch transcripts via TranscriptAPI.com . Setup If $TRANSCRIPT_API_KEY is not set, help the user create an account (100 free credits, no card): Step 1 — Register: Ask user for their email. node ./scripts/tapi-auth.js register --email USER_EMAIL → OTP sent to email. Ask user: "Check your email for a 6-digit verification code." Step 2 — Verify: Once user provides the OTP: node ./scripts/tapi-auth.js verify --token TOKEN_FROM_STEP_1 --otp CODE API key saved to your...
 272
7483 firecrawl connorads/dotfiles
Firecrawl CLI Web scraping, search, and browser automation CLI. Returns clean markdown optimized for LLM context windows. Run firecrawl --help or firecrawl <command> --help for full option details. Prerequisites Must be installed and authenticated. Check with firecrawl --status . 🔥 firecrawl cli v1.8.0 ● Authenticated via FIRECRAWL_API_KEY Concurrency: 0/100 jobs (parallel scrape limit) Credits: 500,000 remaining Concurrency : Max parallel jobs. Run parallel operations up to this limit. Credits ...
 272
7484 animation-principles owl-listener/designer-skills
Animation Principles You are an expert in applying motion design principles to create purposeful UI animations. What You Do You apply animation principles to make interfaces feel natural, guide attention, and communicate state changes. Core UI Animation Principles Easing Ease-out: decelerating (entering elements) Ease-in: accelerating (exiting elements) Ease-in-out: both (moving between positions) Linear: only for continuous animations (progress bars) Duration Micro (50-100ms): button states, to...
 272
7485 seo-best-practices mindrally/skills
SEO Best Practices You are an expert in SEO (Search Engine Optimization) for modern web applications. Apply these guidelines when building web applications to ensure optimal search engine visibility and ranking. Core SEO Principles Write semantic HTML to improve accessibility and SEO Implement proper metadata and structured data Optimize for Core Web Vitals (LCP, CLS, FID) Use server-side rendering (SSR) for better crawlability Create meaningful, descriptive URLs Metadata Implementation Next.j...
 272
7486 hyva-render-media-image hyva-themes/hyva-ai-tools
Hyvä Render Image Generate responsive <picture> elements for Hyvä Theme templates using the \Hyva\Theme\ViewModel\Media view model. When to Use Adding images to Hyvä PHTML templates Creating responsive images with different sources for mobile/desktop Implementing hero banners, product images, or CMS content images Optimizing images for Core Web Vitals (LCP, CLS) Workflow 1. Gather Image Requirements The user may provide image data in one of these ways: Option A: Direct values - Ask the user ...
 272
7487 hyva-child-theme hyva-themes/hyva-ai-tools
Hyvä Child Theme Creator This skill creates a complete Hyvä child theme with the proper directory structure, configuration files, and Tailwind CSS build setup. Command execution: For commands that need to run inside the development environment (e.g., bin/magento), use the hyva-exec-shell-cmd skill to detect the environment and determine the appropriate command wrapper. Workflow Step 1: Gather Theme Information Prompt the user to provide the following information: Vendor Name: The vendor/com...
 272
7488 feature engineering aj-geddes/useful-ai-prompts
Feature Engineering Overview Feature engineering creates and transforms features to improve model performance, interpretability, and generalization through domain knowledge and mathematical transformations. When to Use When you need to improve model performance beyond using raw features When dealing with categorical variables that need encoding for ML algorithms When features have different scales and require normalization When creating domain-specific features based on business knowledge When h...
 272
7489 anomaly detection aj-geddes/useful-ai-prompts
Anomaly Detection Overview Anomaly detection identifies unusual patterns, outliers, and anomalies in data that deviate significantly from normal behavior, enabling fraud detection and system monitoring. When to Use Detecting fraudulent transactions or suspicious activity in financial data Identifying system failures, network intrusions, or security breaches Monitoring manufacturing quality and identifying defective products Finding unusual patterns in healthcare data or patient vital signs Detec...
 272
7490 threat-modeling-expert sickn33/antigravity-awesome-skills
Threat Modeling Expert Expert in threat modeling methodologies, security architecture review, and risk assessment. Masters STRIDE, PASTA, attack trees, and security requirement extraction. Use PROACTIVELY for security architecture reviews, threat identification, or building secure-by-design systems. Capabilities STRIDE threat analysis Attack tree construction Data flow diagram analysis Security requirement extraction Risk prioritization and scoring Mitigation strategy design Security control map...
 272
7491 metrics-tracking anthropics/knowledge-work-plugins
Metrics Tracking Skill You are an expert at product metrics — defining, tracking, analyzing, and acting on product metrics. You help product managers build metrics frameworks, set goals, run reviews, and design dashboards that drive decisions. Product Metrics Hierarchy North Star Metric The single metric that best captures the core value your product delivers to users. It should be: Value-aligned : Moves when users get more value from the product Leading : Predicts long-term business success (re...
 271
7492 alicloud-backup-hbr cinience/alicloud-skills
Category: service Cloud Backup Use Alibaba Cloud OpenAPI (RPC) with official SDKs or OpenAPI Explorer to manage resources for Cloud Backup. Workflow Confirm region, resource identifiers, and desired action. Discover API list and required parameters (see references). Call API with SDK or OpenAPI Explorer. Verify results with describe/list APIs. AccessKey priority (must follow) Environment variables: ALICLOUD_ACCESS_KEY_ID / ALICLOUD_ACCESS_KEY_SECRET / ALICLOUD_REGION_ID Region policy: ALICLOUD_R...
 271
7493 alicloud-compute-fc-serverless-devs cinience/alicloud-skills
Category: tool Function Compute (FC 3.0) Serverless Devs Goals Install and validate Serverless Devs. Configure credentials, initialize example project, deploy, invoke, and remove. Provide CLI flow with Python runtime example. Quick Start Flow Install Node.js (14+) and npm. Install and validate Serverless Devs. Configure credentials via guided setup. Initialize example project and enter directory. Deploy, invoke, and optionally remove. Install Serverless Devs (npm) Global install (requires sudo):...
 271
7494 alicloud-ai-image-zimage-turbo cinience/alicloud-skills
Category: provider Model Studio Z-Image Turbo Use Z-Image Turbo for fast text-to-image generation via the DashScope multimodal-generation API. Critical model name Use ONLY this exact model string: z-image-turbo Prerequisites Set DASHSCOPE_API_KEY in your environment, or add dashscope_api_key to ~/.alibabacloud/credentials (env takes precedence). Choose region endpoint (Beijing or Singapore). If unsure, pick the most reasonable region or ask the user. Normalized interface (image.generate) Request...
 271
7495 alicloud-ai-search-milvus cinience/alicloud-skills
Category: provider AliCloud Milvus (Serverless) via PyMilvus This skill uses standard PyMilvus APIs to connect to AliCloud Milvus and run vector search. Prerequisites Install SDK (recommended in a venv to avoid PEP 668 limits): python3 -m venv .venv . .venv/bin/activate python -m pip install --upgrade pymilvus Provide connection via environment variables: MILVUS_URI (e.g. http://<host>:19530 ) MILVUS_TOKEN ( <username>:<password> ) MILVUS_DB (default: default ) Quickstart (Python) import os from...
 271
7496 alicloud-database-rds-supabase cinience/alicloud-skills
Category: service Alibaba Cloud RDS Supabase (RDS AI Service 2025-05-07) Manage RDS Supabase app instances and related configurations via RDS AI Service OpenAPI, including lifecycle, auth, storage, RAG, IP whitelist, and SSL. Prerequisites Use least-privilege RAM user/role AccessKey and prefer environment variables for AK/SK. OpenAPI uses RPC signing; prefer official SDKs or OpenAPI Explorer. Workflow Confirm resource type: instance / auth / storage / RAG / security configuration. Locate operati...
 271
7497 encore-auth encoredev/skills
Encore Authentication Instructions Encore.ts provides a built-in authentication system for identifying API callers and protecting endpoints. 1. Create an Auth Handler // auth.ts import { Header, Gateway } from "encore.dev/api"; import { authHandler } from "encore.dev/auth"; // Define what the auth handler receives interface AuthParams { authorization: Header<"Authorization">; } // Define what authenticated requests will have access to interface AuthData { userID: string; email: string;...
 271
7498 product-hunt-launch inference-sh/skills
Product Hunt Launch Optimize your Product Hunt launch with research and visuals via inference.sh CLI. Quick Start Requires inference.sh CLI ( infsh ). Install instructions infsh login Generate gallery hero image infsh app run falai/flux-dev-lora --input '{ "prompt": "clean product showcase, modern SaaS dashboard interface on laptop screen, floating UI elements around it, soft gradient background from blue to purple, professional marketing hero shot, minimal clean design", "width": 1248, "height...
 271
7499 gather kazukinagata/shinkoku
書類収集ナビゲーション（Document Gathering Guide） 確定申告に必要な書類を、申告の種類に基づいて一覧化し、各書類の取得先・取得方法を案内するスキル。 assess スキルの判定結果を前提として動作する。判定結果がない場合は、まず assess スキルの実行を促す。 設定の読み込み（最初に実行） shinkoku.config.yaml を Read ツールで読み込む ファイルが存在しない場合は /setup スキルの実行を案内して終了する 設定値を把握し、相対パスは CWD を基準に絶対パスに変換する: db_path : CLI スクリプトの --db-path 引数に使用 output_dir : 進捗ファイル等の出力先ベースディレクトリ 各ディレクトリ: ファイル参照時に使用 進捗情報の読み込み 設定の読み込み後、引継書ファイルを読み込んで前ステップの結果を把握する。 .shinkoku/progress/progress-summary.md を Read ツールで読み込む（存在する場合） 以下の引継書を Read ツールで読み込む（存在する場合）: ....
 271
7500 reading-invoice kazukinagata/shinkoku
請求書 画像読み取り 請求書の画像を読み取り、構造化データとして返すスキル。 PDF ファイルの場合 ファイルが PDF（ .pdf ）の場合、画像 OCR の前にテキスト抽出を試みる。 shinkoku pdf extract-text --file-path <path> を実行する 抽出テキストに必要な情報（金額・日付・請求元等）が含まれていれば、テキストから構造化データを生成する テキストが不十分（スキャン PDF 等）の場合は shinkoku pdf to-image --file-path <path> --output-dir <dir> で PNG に変換し、以下の画像読み取りフローに進む 画像読み取り方法 推奨: デュアル検証（並列2コンテキスト） 精度を高めるため、同じ画像を2つの独立したコンテキストで並列に読み取り、結果を照合する。 2つの独立した読み取りを実行する: サブエージェントが使える環境では、2つのサブエージェントを並列で起動し、それぞれ独立に画像を読み取る。 各サブエージェントには以下の「基本ルール」と「出力フォーマット」をプロンプトとして渡し、画像...
 271