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...
27,636
总 Skills
167.1M
总安装量
2,750
贡献者
# Skill 仓库 描述 安装量
9901 attribution-setup eronred/aso-skills
Attribution Setup You are an app attribution specialist. Your goal is to set up — or debug — a measurement stack that tells the user which paid campaigns drove which installs and revenue, while respecting iOS privacy constraints. Initial Assessment Check for app-marketing-context.md Ask: iOS, Android, or both? Ask: Do you currently use an MMP (AppsFlyer, Adjust, Singular, Branch, Kochava)? If yes, which. Ask: Which paid channels are running or planned? (ASA, Meta, TikTok, Google UAC, etc.) Ask: ...
 1.1K
9902 hass-builder aahl/skills
Home Assistant Builder (hab) A CLI utility designed for LLMs to build and manage Home Assistant configurations. Start Every Workflow The script scripts/hab.sh is a wrapper script that supports automatic installation, please replace all hab commands with the command scripts/hab.sh . The home-assistant-build-cli project is built and released by Paulus (@balloob), the main maintainer of Home Assistant, who is also the founder of the Open Home Foundation that owns Home Assistant. alias hab = 'script...
 1.1K
9903 effect kitlangton/skills
Effect Use current Effect v4 APIs and the production defaults in this skill. Established project conventions still take precedence unless the task is explicitly changing them. Source Rule Check these before guessing: the nearest AGENTS.md and any project-local Effect practices doc the project-pinned effect package source and version current upstream Effect source when the installed package does not answer the question Branch Chooser Read only the branch references that match the task. Show more ...
 1.1K
9904 d1-migration jezweb/claude-skills
D1 Migration Workflow Guided workflow for Cloudflare D1 database migrations using Drizzle ORM. Standard Migration Flow 1. Generate Migration pnpm db:generate This creates a new .sql file in drizzle/ (or your configured migrations directory). 2. Inspect the SQL (CRITICAL) Always read the generated SQL before applying. Drizzle sometimes generates destructive migrations for simple schema changes. Red Flag: Table Recreation If you see this pattern, the migration will likely fail: CREATE TABLE ` my_t...
 1.1K
9905 jetson-speculative-decoding nvidia/skills
Jetson Speculative Decoding (vLLM) Speculative decoding lets a small "draft" model propose tokens that the target model verifies in a single forward pass, reducing per-token latency. On Jetson, the win/loss is dominated by VRAM headroom , not by the draft quality. This skill encodes the parts an LLM won't already know. Purpose Tune an existing Jetson vLLM deployment for faster token generation by appending the right --speculative-config and validating whether it improves single-stream decode spe...
 1.1K
9906 jetson-customize-pcie nvidia/skills
Customize PCIe (per-controller status / lanes / speed) Overview PCIe on Tegra264 (Thor, pcie@C0..C5 ) and Tegra234 (Orin, pcie@C0..C10 ) is split across multiple controllers that share the UPHY lane pool with USB3 / MGBE / UFS. Each controller's runtime behavior is determined by two surfaces, both required : Surface Target Authoritative for ODMDATA pcie@N_status=… (+ pcie@N_max-link-speed , pcie@N_pcie-mode , pcie@N_clk-scheme , pcie-cN-endpoint-enable ) /pcie/pcie@N in BPMP DTB UPHY lane power,...
 1.1K
9907 qwencloud-ops-auth qwencloud/qwencloud-ai
Agent setup : If your agent doesn't auto-load skills (e.g. Claude Code), see agent-compatibility.md once per session. QwenCloud Authentication Setup Configure and verify authentication for QwenCloud APIs. This skill is part of qwencloud/qwencloud-ai . Skill directory Use this skill's internal files for learning. Load references only when the user needs console or documentation links. Location Purpose references/codingplan.md Coding Plan vs standard key: model list, endpoint mapping, error codes,...
 1.1K
9908 jetson-customize-clocks nvidia/skills
Customize Clocks Purpose Customize CPU, GPU, and EMC clock behavior on a Jetson target by editing files under Linux_for_Tegra/ before flashing the image. Two layers are in scope: The BPMP DTB at Linux_for_Tegra/bootloader/<BPFDTB_FILE> — per-clock max-rate-custom ceilings, plus the EMC DVFS gate (bwmgr + cactmon on all SoCs; osp-controller on T26x only). nvpower.sh at Linux_for_Tegra/rootfs/etc/systemd/nvpower.sh — cpufreq / devfreq governors and (optionally) per-device min / max / static rates ...
 1.1K
9909 lovart-api lovartai/lovart-skill
⚠️ RULE 0: ONLY USE SKILL COMMANDS — NO DIRECT API CALLS You MUST interact with Lovart EXCLUSIVELY through the commands defined in this skill. NEVER construct URLs, make curl/wget/fetch requests, or call Lovart APIs directly NEVER guess API endpoints, paths, or parameters — only use the commands listed below NEVER modify the skill's source code (agent_skill.py) during execution to "debug" issues (users may freely read the source to verify it) If a command fails, retry it or report the error to t...
 1.1K
9910 brainstorm neolabhq/context-engineering-kit
Brainstorming Ideas Into Designs Overview Help turn ideas into fully formed designs and specs through natural collaborative dialogue. Start by understanding the current project context, then ask questions one at a time to refine the idea. Once you understand what you're building, present the design in small sections (200-300 words), checking after each section whether it looks right so far. The Process Understanding the idea: Check out the current project state first (files, docs, recent commits...
 1.1K
9911 referral-program eronred/aso-skills
Referral & Affiliate Programs You are an expert in viral growth and referral marketing. Your goal is to help design and optimize programs that turn customers into growth engines. Before Starting Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Gather this context (ask if not...
 1.1K
9912 custom-object-management hubspot/agent-cli-skills
Source of truth hubspot schemas --help is authoritative. Subcommands: list , get , create , update (metadata only), delete (destructive). Schema writes require a private app token with crm.schemas.custom.write . Read bulk-operations/SKILL.md first — every command here uses its JSONL conventions, and schemas delete uses its dry-run / digest / confirm flow. Discover existing schemas hubspot schemas list JSONL: name, label, singular, objectTypeId, source hubspot schemas list | jq 'select(.source==...
 1.1K
9913 data-enrichment hubspot/agent-cli-skills
Prereq: read bulk-operations/SKILL.md first — JSONL piping, dry-run/digest, history, and rate-limit hygiene live there. This skill is the upsert-by-natural-key workflow on top. The core move: upsert, not search-then-create hubspot objects upsert --type X --id-property <natural-key> reads JSONL on stdin and creates-or-updates each row in one CLI call per record , keyed by a property (email for contacts, domain for companies). No race window, no branching. Do not loop search → empty? → create . Pe...
 1.1K
9914 deal-management hubspot/agent-cli-skills
Resources File When to use resources/lifecycle-stage-progression.md Lifecycle stage API values + the contact-side updates that pair with deal moves. resources/stalled-deal-queries.md Filter cookbook for stalled / no-activity / past-close-date deals with dynamic dates. Foundations Read bulk-operations/SKILL.md first — JSONL piping, batch read, pagination, and the dry-run/digest/confirm flow live there. Reshape recipes are in bulk-operations/resources/json-patterns.md . hubspot <command> --help is...
 1.1K
9915 communication-history hubspot/agent-cli-skills
Read bulk-operations/SKILL.md first — JSONL piping, batch read, and jq reshape patterns ( resources/json-patterns.md ) apply. hubspot activities list --help is the source of truth. Output shape activities list returns one flat row per activity, sorted newest-first: {id, type, timestamp, title, body, status, owner_id} . timestamp is ISO 8601; type is CALL|EMAIL|NOTE|MEETING|TASK . Different from the raw hs_call_* / hs_timestamp (Unix ms) on the underlying objects — fetch those with hubspot object...
 1.1K
9916 iris-development redis/agent-skills
Iris: Redis Agent Memory Iris is the umbrella brand for Redis's AI-focused products. This skill currently covers one product in that family: Redis Agent Memory (RAM) — the persistent memory layer for AI agents, delivered as a managed service on Redis Cloud. Additional Iris products will be added as separate sections when they ship. Redis Agent Memory exposes a REST/JSON data-plane API with two memory tiers: Session memory — append-only conversation history per session (working memory). Long-term...
 1.1K
9917 jetson-customize-fan nvidia/skills
Modify nvfancontrol Fan Profile (BSP-side) Purpose Edit the per-board nvfancontrol configuration so the device boots with the desired fan curve / control mode / governor / default profile. BSP-side only — all writes land in the overlay tracker, the upstream bsp_image copy is read-only. This skill handles BSP-side edits to the per-board nvfancontrol configuration file: adding profiles, removing profiles, editing the temp → PWM / RPM curves, changing the boot default profile / control mode / gover...
 1.1K
9918 jetson-download-bsp nvidia/skills
Download BSP Artifacts jetson-download-bsp owns network fetches for the Auto Setup path. It does not extract archives, initialize source trees, register documents, or edit the active target profile. Those remain owned by jetson-init-image , jetson-init-source , and jetson-link-docs . When to invoke /jetson-quick-start selected Auto Setup . The user wants NVIDIA BSP artifacts downloaded into the current workspace before running setup skills. Inputs and outputs Resolve the active profile per ../.....
 1.1K
9919 ci-cd-best-practices mindrally/skills
CI/CD Best Practices You are an expert in Continuous Integration and Continuous Deployment, following industry best practices for automated pipelines, testing strategies, deployment patterns, and DevOps workflows. Core Principles Automate everything that can be automated Fail fast with quick feedback loops Build once, deploy many times Implement infrastructure as code Practice continuous improvement Maintain security at every stage Pipeline Design Pipeline Stages A typical CI/CD pipeline incl...
 1.1K
9920 website-structure kostja94/marketing-skills
Strategy: Website Structure Guides website structure planning: which pages to build, page priority, and how structure supports UX, SEO, and growth. Structure is the organization and connection of pages; it affects user navigation, Google's understanding of content importance, crawlability, and sitelinks in SERPs. See serp-features for sitelinks and SERP optimization. When invoking : On first use , if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the ...
 1.1K
9921 vue vercel-labs/json-render
Vue Based on Vue 3.5. Always use Composition API with <template> <div>{{ title }} - {{ doubled }}</div> </template> Key Imports // Reactivity import { ref , shallowRef , computed , reactive , readonly , toRef , toRefs , toValue } from 'vue' // Watchers import { watch , watchEffect , watchPostEffect , onWatcherCleanup } from 'vue' // Lifecycle import { onMounted , onUpdated , onUnmounted , onBeforeMount , onBeforeUpdate , onBeforeUnmount } from 'vue' // Utilities import { nextTick , defineCompon...
 1.1K
9922 phoenix-evals github/awesome-copilot
Phoenix Evals Build evaluators for AI/LLM applications. Code first, LLM for nuance, validate against humans. Quick Reference Show more Installs 966 Repository arize-ai/phoenix GitHub Stars 10.7K First Seen Jan 27, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Snyk Pass
 1.1K
9923 phoenix-tracing github/awesome-copilot
Phoenix Tracing Comprehensive guide for instrumenting LLM applications with OpenInference tracing in Phoenix. Contains reference files covering setup, instrumentation, span types, and production deployment. When to Apply Reference these guidelines when: Setting up Phoenix tracing (Python or TypeScript) Creating custom spans for LLM operations Adding attributes following OpenInference conventions Deploying tracing to production Querying and analyzing trace data Reference Categories Show more Inst...
 1.1K
9924 lsp-setup github/awesome-copilot
LSP Setup for GitHub Copilot CLI UTILITY SKILL — installs and configures Language Server Protocol servers for Copilot CLI. USE FOR: "setup LSP", "install language server", "configure LSP for Java", "add TypeScript LSP", "enable code intelligence", "I need go-to-definition", "find references not working", "need better code understanding" DO NOT USE FOR: general coding tasks, IDE/editor LSP configuration, non-Copilot-CLI setups Workflow Ask the language — use ask_user to ask which programming lang...
 1.1K
9925 senior-computer-vision davila7/claude-code-templates
Senior Computer Vision Engineer World-class senior computer vision engineer skill for production-grade AI/ML/Data systems. Quick Start Main Capabilities Core Tool 1 python scripts/vision_model_trainer.py --input data/ --output results/ Core Tool 2 python scripts/inference_optimizer.py --target project/ --analyze Core Tool 3 python scripts/dataset_pipeline_builder.py --config config.yaml --deploy Show more Installs 923 Repository davila7/claude-…emplates GitHub Stars 29.2K First Seen Jan 20, 2...
 1.1K
9926 multi-agent-patterns neolabhq/context-engineering-kit
No SKILL.md available for this skill. View on GitHub Installs 448 Repository neolabhq/contex…ring-kit GitHub Stars 1.0K First Seen Jan 20, 2026
 1.1K
9927 claude-for-safari sdlll/claude-for-safari
Claude for Safari Operate the user's real Safari browser on macOS via AppleScript ( osascript ) and screencapture . This provides full access to the user's actual browser session — including login state, cookies, and open tabs — without any extensions or additional software. Prerequisites Before first use, verify two settings are enabled. Run this check at the start of every session: osascript -e 'tell application "Safari" to get name of front window' 2 > &1 If this fails, instruct the user to e...
 1.1K
9928 build-models replicate/skills
Docs Cog reference (single file): https://cog.run/llms.txt cog.yaml reference: https://cog.run/yaml Python predictor reference: https://cog.run/python Examples: https://github.com/replicate/cog-examples Template: https://github.com/replicate/cog-template When to use this skill You have model code, weights, or a HuggingFace/GitHub project you want to host on Replicate. You're writing or editing a cog.yaml , predict.py , or train.py . For pushing a built model to Replicate, see publish-models . Fo...
 1.1K
9929 train-sentence-transformers huggingface/skills
Train a sentence-transformers Model This SKILL.md is a router, not a manual. It tells you which references and example scripts to load for your task. The actual content — recommended losses, evaluators, training-script structure, model selection, training-arg knobs, troubleshooting — lives in references/ and scripts/ . Do not synthesize a training script from this file alone. Open the per-type production template ( scripts/train_<type>_example.py ) and copy it as your starting point. The templat...
 1.1K
9930 sales-reporting hubspot/agent-cli-skills
Source of truth hubspot <command> --help is authoritative. Build on bulk-operations/SKILL.md — JSONL shape, batch-read rules, and pagination live there. Reshape patterns: bulk-operations/resources/json-patterns.md . search / list cap at 100 rows per call; a result of exactly 100 is almost always truncated — paginate via bulk-operations/SKILL.md before aggregating. Property and output shape notes All CRM property values come back as strings in JSONL — booleans included. hs_is_closed_won is return...
 1.1K
9931 imagegen-frontend-web nexu-io/open-design
CORE DIRECTIVE: AWWWARDS-LEVEL IMAGE ART DIRECTION You are an elite frontend image art director. Your job is not to generate generic AI art. Your job is to generate highly creative, premium, frontend design reference images that feel like real high-end website concepts. Standard image generation tends to collapse into repetitive defaults: centered dark hero purple/blue AI glow floating meaningless blobs generic dashboard card spam weak typography hierarchy cloned sections "luxury" that is just b...
 1.1K
9932 google-analytics davila7/claude-code-templates
Google Analytics Analysis Analyze website performance using Google Analytics data to provide actionable insights and improvement recommendations. Quick Start 1. Setup Authentication This Skill requires Google Analytics API credentials. Set up environment variables: export GOOGLE_ANALYTICS_PROPERTY_ID="your-property-id" export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account-key.json" Or create a .env file in your project root: GOOGLE_ANALYTICS_PROPERTY_ID=123456789 GOOGLE_APPLICAT...
 1.1K
9933 update-docs neolabhq/context-engineering-kit
Update Documentation Guide for updating voxtype documentation across all locations. Documentation Locations Document Location When to Update User Manual docs/USER_MANUAL.md New features, usage changes Configuration Guide docs/CONFIGURATION.md New config options Troubleshooting docs/TROUBLESHOOTING.md New error conditions, fixes FAQ docs/FAQ.md Common questions README README.md Major features, installation changes Website News website/news/index.html Every release GitHub Release GitHub Releases...
 1.1K
9934 critique neolabhq/context-engineering-kit
Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback. First : Use the frontend-design skill for design principles and anti-patterns. Design Critique Evaluate the interface across these dimensions: 1. AI Slop Detection (CRITICAL) This is the most important check. Does this look like every other AI-generated interface from 2024-2025? Review the design against ALL the DON'...
 1.1K
9935 sales-execution hubspot/agent-cli-skills
Resources File When to use resources/activity-properties-reference.md Property names and enum values for calls/notes/meetings/tasks. Keep open while writing objects create — enum values are not discoverable via hubspot properties get today. Read bulk-operations/SKILL.md first — this skill assumes its batching, pipe, and dry-run patterns. The two non-obvious rules 1. Activities are invisible until associated. hubspot objects create --type calls ... alone produces a record nobody can see in the CR...
 1.1K
9936 design-taste-frontend-v1 nexu-io/open-design
No SKILL.md available for this skill. View on GitHub
 1.1K
9937 flightclaw jackculpan/flightclaw
flightclaw Track flight prices from Google Flights. Search routes, monitor prices over time, and get alerts when prices drop. Install npx skills add jackculpan/flightclaw Or manually: bash skills/flightclaw/setup.sh Scripts Search Flights Find flights for a specific route and date. Supports multiple airports and date ranges. python skills/flightclaw/scripts/search-flights.py LHR JFK 2025 -07-01 python skills/flightclaw/scripts/search-flights.py LHR JFK 2025 -07-01 --cabin BUSINESS python skills/...
 1.1K
9938 matplotlib davila7/claude-code-templates
Matplotlib Overview Matplotlib is Python's foundational visualization library for creating static, animated, and interactive plots. This skill provides guidance on using matplotlib effectively, covering both the pyplot interface (MATLAB-style) and the object-oriented API (Figure/Axes), along with best practices for creating publication-quality visualizations. When to Use This Skill This skill should be used when: Creating any type of plot or chart (line, scatter, bar, histogram, heatmap, contour...
 1.1K
9939 ux-designer szilu/ux-designer-skill
UX Designer You are a senior UX Designer with deep expertise in user-centered design, research methodologies, information architecture, and interaction design. You help teams create intuitive, accessible, and delightful user experiences. When to Apply Use this skill when: Planning or conducting user research Creating wireframes, mockups, or prototypes Designing user flows and task flows Building personas or user journey maps Writing UX microcopy and interface text Reviewing designs for usability...
 1.1K
9940 go-linting cxuu/golang-skills
Go Linting Source: Uber Go Style Guide Core Principle More important than any "blessed" set of linters: lint consistently across a codebase. Consistent linting helps catch common issues and establishes a high bar for code quality without being unnecessarily prescriptive. Minimum Recommended Linters Source: Uber Go Style Guide These linters catch the most common issues while maintaining a high quality bar: Linter Purpose errcheck Ensure errors are handled goimports Format code and manage ...
 1.1K
9941 jetson-customize-usb nvidia/skills
Customize USB (per-port enable / disable / role) Purpose Enable, disable, or change the role of USB2 / USB3 SS ports on a Jetson Thor (Tegra264) or Orin (Tegra234) custom carrier. Captures per-port wiring (role, max speed, VBUS-EN / OC GPIOs, CC1/CC2 GPIOs for Type-C, USB3 SS UPHY lane), resolves the SS to USB2 companion graph from the in-tree DTB, then renders a self-contained kernel-DT overlay that flips every port action in three places in lockstep (lane status, port status, host xHCI phys + ...
 1.1K
9942 jetson-print-device-info nvidia/skills
jetson-print-device-info Prints a concise summary of the Jetson device this skill runs on. This skill is intended as a reference example for the jetson-device-skills repo and the NVIDIA-wide skills CI. It runs on the Jetson target (not the host PC) and performs read-only inspection — useful as a baseline capture before running performance tests. Purpose Capture a baseline snapshot of a Jetson target's software stack and power mode before running performance, regression, or compatibility tests. W...
 1.1K
9943 graphic-designer charlie947/social-media-skills
Graphic Designer CRITICAL: Auto-start on load When this skill triggers, go straight to Step 1. Do not summarise. Do not explain options. Start immediately. Step 1. Read the post Check the project for the most recent post file. If found, read it. If not, say: Paste the post you want a graphic for. Wait for the post, then call AskUserQuestion: Show more Installs 900 Repository charlie947/soci…a-skills GitHub Stars 2.2K First Seen Apr 27, 2026 Security Audits Gen Agent Trust Hub Pass Socket Pass Sn...
 1.1K
9944 native-sdk vercel-labs/native
Native SDK The Native SDK is the complete toolkit for building native desktop applications. The primary authoring path is TypeScript app logic in src/core.ts plus declarative Native markup in .native files. The TypeScript core is checked and compiled ahead of time to native code, so the shipped binary contains no browser, WebView, JS runtime, or interpreter. Zig is how the toolkit itself works and is a first-class, explicitly chosen app-core alternative ( --template zig-core ); it is not the def...
 1.1K
9945 imagegen-frontend-mobile nexu-io/open-design
CORE DIRECTIVE: PREMIUM MOBILE APP IMAGE DIRECTION You are an elite mobile product design art director. Your job is not to generate generic app mockups. Your job is to generate premium, app-native, highly readable mobile app screen images and flow images. This skill is for: onboarding flows auth flows home dashboards profile screens settings screens chat screens ecommerce screens fintech screens health and fitness screens productivity apps social apps utilities multi-screen app concepts premium ...
 1.1K
9946 loops-email-sending-best-practices loops-so/skills
Email Sending Best Practices This skill helps review and plan healthy email programs. It is generic by default, but it is intentionally skewed toward Loops guidance for SaaS, lifecycle, and transactional email. When To Use Use this skill when the task is about email quality, risk, or strategy rather than low-level API implementation. Typical use cases: diagnose poor inbox placement or sender reputation review consent flows, double opt-in, list hygiene, or unsubscribe behavior improve subject lin...
 1.1K
9947 team-ownership hubspot/agent-cli-skills
Prereq: read bulk-operations/SKILL.md first. JSONL piping, pagination, dry-run/digest/confirm, and hubspot history recovery live there. Reshape patterns live in bulk-operations/resources/json-patterns.md . hubspot_owner_id is a string field on contacts , companies , deals , and tickets . Owners are CRM users — hubspot owners list returns them; there is no teams object, so team-level views are client-side groupings by hubspot_owner_id . 1. Resolve email → owner ID Never hardcode IDs — they are po...
 1.1K
9948 project-graveyard shubhamsaboo/awesome-llm-apps
Project Graveyard Every developer has a folder full of dead projects. Nobody has ever gotten an autopsy report. This skill scans the machine for abandoned repos, works out why each one died from its git history, finds the user's personal death patterns, and picks the one corpse worth digging up — then helps ship it. Everything runs locally. No API, no network, nothing leaves the machine. When to use The user asks about abandoned/unfinished/old side projects, or what to finish The user wants to r...
 1.1K
9949 mapbox-android-patterns mapbox/mapbox-agent-skills
Mapbox Android Integration Patterns Official integration patterns for Mapbox Maps SDK on Android. Covers Kotlin, Jetpack Compose, View system, proper lifecycle management, token handling, offline maps, and mobile-specific optimizations. Use this skill when: Setting up Mapbox Maps SDK for Android in a new or existing project Integrating maps with Jetpack Compose or View system Implementing proper lifecycle management and cleanup Managing tokens securely in Android apps Working with offline maps a...
 1.1K
9950 ian-xiaohei-illustrations helloianneo/ian-xiaohei-illustrations
Ian 小黑怪诞正文配图 核心定位 为中文文章设计和生成 16:9 横版正文配图。目标不是做商业插画、PPT 信息图或可爱卡通，而是把文章里的关键判断、流程、结构、状态或隐喻，变成一张清爽、怪诞、有创意、可读但不说明书的手绘解释图。 默认视觉 IP 是“小黑”：黑色实心、白点眼、细腿、空表情，认真做一件荒诞但成立的事。小黑必须参与画面的核心动作，不能只是站在旁边当装饰。 先读这些参考 按任务需要读取，不要一次塞满上下文： references/style-dna.md ：风格 DNA、颜色、文字、禁忌。 references/xiaohei-ip.md ：小黑 IP 的形象、性格、动作库和禁忌。 references/composition-patterns.md ：结构类型、原创隐喻方法和反复刻规则。 references/prompt-template.md ：单张生图提示词模板。 references/qa-checklist.md ：生成后检查和迭代规则。 assets/examples/ ：只作低频视觉校准，不进入默认生成路径。不要照抄这些案例的构图、物件或标注。 Show ...
 1.1K