{"id":"1544a1ef-7ccf-4410-a46c-cedb2b76078d","entityType":"agent","slug":"clawhub-dlazyai-dlazy-logo-branding-system","name":"Logo 品牌设计系统 Logo Branding System","canonicalUrl":"https://www.xpersona.co/agent/clawhub-dlazyai-dlazy-logo-branding-system","canonicalPath":"/agent/clawhub-dlazyai-dlazy-logo-branding-system","generatedAt":"2026-10-10T10:45:23.585Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T06:07:01.278Z","emptyReason":null},"description":"A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.6K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-logo-branding-system","sourceUrl":"https://clawhub.ai/dlazyai/dlazy-logo-branding-system","homepage":"https://clawhub.ai/dlazyai/skills/dlazy-logo-branding-system","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/dlazyai/dlazy-logo-branding-system","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/dlazyai/skills/dlazy-logo-branding-system","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":64,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Logo 品牌设计系统 Logo Branding System technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T06:07:01.278Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T06:07:01.278Z","emptyReason":null},"stars":null,"forks":null,"downloads":1630,"packageName":null,"latestVersion":"1.2.23","tractionLabel":"1.6K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T06:07:01.244Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T06:07:01.278Z","lastCrawledAt":"2026-10-10T06:07:01.244Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T06:07:01.245Z","lastVerifiedAt":null,"highlights":[{"version":"1.2.23","createdAt":"2026-10-10T01:19:30.587Z","changelog":"例行版本更新 2026-10-10","fileCount":4,"zipByteSize":11199},{"version":"1.2.22","createdAt":"2026-10-08T01:19:26.891Z","changelog":"例行版本更新 2026-10-08","fileCount":4,"zipByteSize":11085},{"version":"1.2.21","createdAt":"2026-10-04T01:18:22.390Z","changelog":"例行版本更新 2026-10-04","fileCount":4,"zipByteSize":11090},{"version":"1.2.20","createdAt":"2026-10-02T04:59:41.428Z","changelog":"例行版本更新 2026-10-02","fileCount":4,"zipByteSize":11093},{"version":"1.2.19","createdAt":"2026-09-30T01:16:51.359Z","changelog":"例行版本更新 2026-09-30","fileCount":4,"zipByteSize":11159},{"version":"1.2.18","createdAt":"2026-09-28T02:15:15.897Z","changelog":"例行版本更新 2026-09-28","fileCount":4,"zipByteSize":11101},{"version":"1.2.17","createdAt":"2026-09-28T01:17:44.593Z","changelog":"例行版本更新 2026-09-28","fileCount":4,"zipByteSize":11074},{"version":"1.2.16","createdAt":"2026-09-24T01:55:56.265Z","changelog":"例行版本更新 2026-09-24","fileCount":4,"zipByteSize":11100}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-logo-branding-system","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s170j1ymymrxasgd00dsk7tckx84cf45:dlazy-logo-branding-system` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/dlazyai/dlazy-logo-branding-system before using production credentials."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-logo-branding-system/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-logo-branding-system/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-logo-branding-system/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-logo-branding-system/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-logo-branding-system/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-logo-branding-system/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T10:45:23.581Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-logo-branding-system/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-logo-branding-system/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-logo-branding-system/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dlazyai-dlazy-logo-branding-system/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T06:07:01.278Z","emptyReason":null},"readme":"Skill: Logo 品牌设计系统 Logo Branding System\n\nOwner: dlazyai\n\nSummary: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\nTags: latest:1.2.23\n\nVersion history:\n\nv1.2.23 | 2026-10-10T01:19:30.587Z | user\n\n例行版本更新 2026-10-10\n\nv1.2.22 | 2026-10-08T01:19:26.891Z | user\n\n例行版本更新 2026-10-08\n\nv1.2.21 | 2026-10-04T01:18:22.390Z | user\n\n例行版本更新 2026-10-04\n\nv1.2.20 | 2026-10-02T04:59:41.428Z | user\n\n例行版本更新 2026-10-02\n\nv1.2.19 | 2026-09-30T01:16:51.359Z | user\n\n例行版本更新 2026-09-30\n\nv1.2.18 | 2026-09-28T02:15:15.897Z | user\n\n例行版本更新 2026-09-28\n\nv1.2.17 | 2026-09-28T01:17:44.593Z | user\n\n例行版本更新 2026-09-28\n\nv1.2.16 | 2026-09-24T01:55:56.265Z | user\n\n例行版本更新 2026-09-24\n\nv1.2.15 | 2026-09-20T01:20:21.506Z | user\n\n例行版本更新 2026-09-20\n\nv1.2.14 | 2026-09-14T01:17:14.428Z | user\n\n例行版本更新 2026-09-14\n\nv1.2.13 | 2026-09-10T01:14:32.557Z | user\n\n例行版本更新 2026-09-10\n\nv1.2.12 | 2026-09-08T01:15:53.278Z | user\n\n例行版本更新 2026-09-08\n\nv1.2.11 | 2026-09-07T01:21:55.727Z | user\n\n例行版本更新 2026-09-07\n\nv1.2.10 | 2026-09-04T01:21:00.266Z | user\n\n例行版本更新 2026-09-04\n\nv1.2.9 | 2026-09-02T01:15:37.939Z | user\n\n例行版本更新 2026-09-02\n\nv1.2.8 | 2026-08-31T02:55:58.464Z | user\n\n源码仓库迁移至 github.com/dlazy-ai/cli\n\nv1.2.7 | 2026-08-24T09:27:03.548Z | user\n\nRestore Chinese display name\n\nv1.2.6 | 2026-08-17T09:10:12.783Z | user\n\nRestore Chinese display name\n\nv1.2.5 | 2026-08-10T05:51:26.635Z | user\n\nRestore Chinese display name\n\nv1.2.4 | 2026-08-10T04:07:36.537Z | user\n\nRestore Chinese display name\n\nv1.2.3 | 2026-07-21T02:24:25.516Z | auto\n\n- Updated CLI version in install instructions and metadata from 1.2.2 to 1.2.3.\n- Fixed all related install and usage references to use @dlazy/cli@1.2.3.\n- Removed the file skill-card.md from the project.\n\nv1.0.0 | 2026-07-20T05:53:47.192Z | user\n\n规范 dlazy- 前缀命名，补充中文显示名\n\nArchive index:\n\nArchive v1.2.23: 4 files, 11199 bytes\n\nFiles: skill-card.md (2373b), SKILL-cn.md (8886b), SKILL.md (8886b), _meta.json (146b)\n\nFile v1.2.23:SKILL.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.2.23:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-logo-branding-system\",\n  \"version\": \"1.2.23\",\n  \"publishedAt\": 1791595170587\n}\n\nFile v1.2.23:skill-card.md\n\n## Description:\n\nGuides agents through a staged logo and brand-identity design process, from core marks to consistent visual applications and deliverables.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDesigners, marketers, and other external users can use this skill to plan and refine a logo, explore brand directions, and develop coordinated variants and visual applications with approval at each stage.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Installing a third-party CLI and storing a dLazy API key locally may expose credentials if the environment is not trusted.\n\nMitigation: Install only in a trusted environment; prefer the one-time npx invocation if a persistent global installation is unnecessary, and protect or rotate the API key.\n\nRisk: Prompts and referenced media files are sent to dLazy cloud endpoints for generation.\n\nMitigation: Check the content and obtain permission before sending sensitive prompts or media to dLazy.\n\nRisk: Installation metadata pins CLI version 1.2.3, while the prose also mentions an older 1.0.9 version.\n\nMitigation: Confirm the intended @dlazy/cli version before installing or running it.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-logo-branding-system)\n- [dLazy CLI repository (linked in skill metadata; not verified skill provenance)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy website](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Guidance, Shell commands, Image links]\n\n**Output Format:** [Markdown with design rationales, stepwise plans, commands, and links to generated images]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Delivers logo concepts and brand-system applications incrementally, with user confirmation between stages.]\n\n## Skill Version(s):\n\n1.2.23 (source: ClawHub release metadata; embedded skill frontmatter says 1.2.3)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.23:SKILL-cn.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.2.22: 4 files, 11085 bytes\n\nFiles: skill-card.md (2136b), SKILL-cn.md (8886b), SKILL.md (8886b), _meta.json (146b)\n\nFile v1.2.22:SKILL.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.2.22:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-logo-branding-system\",\n  \"version\": \"1.2.22\",\n  \"publishedAt\": 1791422366891\n}\n\nFile v1.2.22:skill-card.md\n\n## Description:\n\nGuides a stepwise logo and brand identity workflow from initial concepts through consistent visual assets and applications.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDesigners and brand teams use this skill to explore logo concepts, confirm a core mark, and develop consistent variants, social assets, and brand identity guidance.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and selected media files are sent to dLazy cloud services.\n\nMitigation: Review what you submit and avoid sharing sensitive brand materials without authorization.\n\nRisk: Installing and authenticating the external CLI creates package and credential exposure.\n\nMitigation: Review the CLI package before installation, prefer an environment-scoped install or npx when appropriate, and rotate or revoke unused API keys.\n\nRisk: Conflicting version notes and unclear language behavior can cause incorrect expectations.\n\nMitigation: Confirm the installed CLI version and expected output language before relying on the workflow.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-logo-branding-system)\n- [dLazy CLI repository (linked in skill metadata)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Design guidance, Shell commands, Image URLs]\n\n**Output Format:** [Markdown with design rationales, commands, and links to generated images]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Concepts and derivatives are presented in stages for user confirmation.]\n\n## Skill Version(s):\n\n1.2.22 (source: ClawHub release metadata; skill frontmatter says 1.2.3)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.22:SKILL-cn.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.2.21: 4 files, 11090 bytes\n\nFiles: skill-card.md (2082b), SKILL-cn.md (8886b), SKILL.md (8886b), _meta.json (146b)\n\nFile v1.2.21:SKILL.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.2.21:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-logo-branding-system\",\n  \"version\": \"1.2.21\",\n  \"publishedAt\": 1791076702390\n}\n\nFile v1.2.21:skill-card.md\n\n## Description:\n\nGuides a phased logo and brand identity workflow from initial concepts through consistent visual applications and deliverables.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDesigners and brand teams use this skill to plan, generate, review, and refine logo concepts and coordinated brand assets with phased approvals.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and selected media files are sent to dLazy's hosted services.\n\nMitigation: Confirm the content is suitable to share before submitting prompts or reference assets.\n\nRisk: The CLI can store a dLazy API key locally.\n\nMitigation: Use the DLAZY_API_KEY environment variable if persistent key storage is unwanted, and rotate or revoke keys when needed.\n\nRisk: The published skill version differs from the CLI version documented for installation; the CLI implementation is not included in the skill artifacts.\n\nMitigation: Review the @dlazy/cli@1.2.3 package before running it and verify the intended CLI version.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-logo-branding-system)\n- [dLazy CLI project (metadata link)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Guidance, Shell commands, Image URLs]\n\n**Output Format:** [Markdown with design rationales, phase plans, and links to generated images]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Image generation proceeds one approved step at a time.]\n\n## Skill Version(s):\n\n1.2.21 (source: ClawHub release evidence; embedded skill frontmatter says 1.2.3)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.21:SKILL-cn.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.2.20: 4 files, 11093 bytes\n\nFiles: skill-card.md (2157b), SKILL-cn.md (8886b), SKILL.md (8886b), _meta.json (146b)\n\nFile v1.2.20:SKILL.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.2.20:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-logo-branding-system\",\n  \"version\": \"1.2.20\",\n  \"publishedAt\": 1790917181428\n}\n\nFile v1.2.20:skill-card.md\n\n## Description:\n\nGuides logo creation and the development of a consistent brand visual system, from initial concepts through application assets.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDesigners, marketers, and other brand creators use this skill to plan and review logo concepts, generate approved visual assets, and extend a chosen mark into a coherent brand identity.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and referenced media are sent to dLazy's hosted services when generating assets.\n\nMitigation: Confirm cloud processing is appropriate before submitting confidential prompts or media.\n\nRisk: Authentication can store a dLazy API key in the local CLI configuration.\n\nMitigation: Protect the local key and rotate or revoke it if exposed.\n\nRisk: The workflow installs or runs an external CLI, and its text inconsistently refers to version 1.0.9 versus 1.2.3.\n\nMitigation: Review the package before execution and confirm the intended CLI version with the publisher.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-logo-branding-system)\n- [dLazy CLI source (listed in skill metadata; skill import provenance unavailable)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown, Shell commands, Images]\n\n**Output Format:** [Markdown design plans and concept rationales, with generation commands and links to image assets when executed]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Stepwise review and user confirmation before generating further assets]\n\n## Skill Version(s):\n\n1.2.20 (source: ClawHub release; artifact frontmatter states 1.2.3)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.20:SKILL-cn.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.2.19: 4 files, 11159 bytes\n\nFiles: skill-card.md (2320b), SKILL-cn.md (8886b), SKILL.md (8886b), _meta.json (146b)\n\nFile v1.2.19:SKILL.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.2.19:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-logo-branding-system\",\n  \"version\": \"1.2.19\",\n  \"publishedAt\": 1790731011359\n}\n\nFile v1.2.19:skill-card.md\n\n## Description:\n\nGuides agents through staged logo design and development of a consistent brand visual system, from core mark to applications.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDesigners, brand teams, and other agents use this skill to plan logo concepts, obtain approval, and develop consistent variants and brand applications with dLazy image generation.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and selected local media are sent to dLazy's cloud service for generation.\n\nMitigation: Use the service only when this data transfer is acceptable; do not upload sensitive media unless intended.\n\nRisk: Installing the third-party CLI introduces a software supply-chain dependency.\n\nMitigation: Review the @dlazy/cli package source when assurance matters and confirm the installed version is 1.2.3.\n\nRisk: A version typo in the skill documentation could cause installation confusion.\n\nMitigation: Check the installation command and confirm the intended CLI version before running it.\n\nRisk: The dLazy API key grants access to the user's dLazy organization.\n\nMitigation: Keep the key private and rotate or revoke it in the dLazy dashboard if needed.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/dlazyai/skills/dlazy-logo-branding-system)\n- [dLazy CLI repository (linked in skill metadata; not verified release provenance)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Guidance, Shell commands]\n\n**Output Format:** [Markdown with design concepts, brand-system guidance, and CLI commands; generated image URLs when used]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Staged deliverables and confirmation between design phases]\n\n## Skill Version(s):\n\n1.2.19 (source: ClawHub release metadata; bundled skill frontmatter says 1.2.3)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.19:SKILL-cn.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.2.18: 4 files, 11101 bytes\n\nFiles: skill-card.md (2213b), SKILL-cn.md (8886b), SKILL.md (8886b), _meta.json (146b)\n\nFile v1.2.18:SKILL.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.2.18:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-logo-branding-system\",\n  \"version\": \"1.2.18\",\n  \"publishedAt\": 1790561715897\n}\n\nFile v1.2.18:skill-card.md\n\n## Description:\n\nGuides a phased logo-design process from core mark concepts through consistent brand variants and visual applications.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDesigners, brand teams, and other users can plan and develop a logo, review concepts, and extend a confirmed mark into a consistent brand identity and applications.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and selected media files are sent to dLazy cloud endpoints during generation.\n\nMitigation: Use the service only when those inputs are suitable for third-party processing; check selected files before sending.\n\nRisk: Using the service requires an API key, which may be saved locally by the CLI.\n\nMitigation: Use an environment variable if persistent key storage is unsuitable, and protect or rotate the key as needed.\n\nRisk: Installing or running the third-party CLI executes a separate package.\n\nMitigation: Verify the intended @dlazy/cli version and use the on-demand npx option if a persistent global installation is unwanted.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-logo-branding-system)\n- [dLazy CLI package (skill metadata)](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy CLI project (skill metadata)](https://github.com/dlazy-ai/cli)\n- [dLazy service](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Guidance, Shell commands]\n\n**Output Format:** [Markdown with design rationales, image links, and optional shell commands]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Phased deliverables and confirmation requests; generated logo and brand asset links when used with the dLazy service.]\n\n## Skill Version(s):\n\n1.2.18 (source: ClawHub release metadata; bundled skill frontmatter says 1.2.3)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.18:SKILL-cn.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.2.17: 4 files, 11074 bytes\n\nFiles: skill-card.md (2097b), SKILL-cn.md (8886b), SKILL.md (8886b), _meta.json (146b)\n\nFile v1.2.17:SKILL.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.2.17:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-logo-branding-system\",\n  \"version\": \"1.2.17\",\n  \"publishedAt\": 1790558264593\n}\n\nFile v1.2.17:skill-card.md\n\n## Description:\n\nGuides a phased logo and brand identity design process from initial concepts through consistent variants and applications.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDesigners, brand teams, and other users develop a core logo, review alternative concepts, and extend the approved mark into a consistent brand identity and application assets.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Installing and running the third-party dLazy CLI introduces a software dependency.\n\nMitigation: Review the CLI package before installation; use the documented npx option if a persistent global installation is unnecessary.\n\nRisk: Prompts and referenced local media may be sent to dLazy services.\n\nMitigation: Confirm what content may be shared with the service before submitting prompts or local assets.\n\nRisk: A saved dLazy API key can grant access to the user's organization.\n\nMitigation: Protect the credential and rotate or revoke it through dLazy if it may be exposed.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-logo-branding-system)\n- [dLazy CLI package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy CLI repository (CLI dependency, not verified skill provenance)](https://github.com/dlazy-ai/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Shell commands, Guidance]\n\n**Output Format:** [Markdown with design rationales, optional shell commands, and generated image links]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Phased delivery with user confirmation before image generation and downstream applications.]\n\n## Skill Version(s):\n\n1.2.17 (source: ClawHub release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.17:SKILL-cn.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.2.16: 4 files, 11100 bytes\n\nFiles: skill-card.md (2183b), SKILL-cn.md (8886b), SKILL.md (8886b), _meta.json (146b)\n\nFile v1.2.16:SKILL.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.2.16:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-logo-branding-system\",\n  \"version\": \"1.2.16\",\n  \"publishedAt\": 1790214956265\n}\n\nFile v1.2.16:skill-card.md\n\n## Description:\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers, designers, and external users use this skill to plan logo concepts, generate brand-system derivatives, and organize identity-system deliverables through a stepwise dLazy workflow.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and selected local media can be uploaded to the dLazy service, and a dLazy API key may be stored in local CLI configuration.\n\nMitigation: Confirm the user trusts the @dlazy/cli package and dLazy service before installing or running commands, and use the documented npx path when avoiding a global CLI install.\n\nRisk: The artifact contains a stale 1.0.9 package-version reference while the install metadata uses 1.2.3 and the server release metadata is 1.2.16.\n\nMitigation: Verify the intended @dlazy/cli package version before installation or execution.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dlazyai/skills/dlazy-logo-branding-system)\n- [dLazy CLI repository](https://github.com/dlazy-ai/cli)\n- [@dlazy/cli npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy service](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [guidance, markdown, shell commands, configuration]\n\n**Output Format:** [Markdown guidance with inline shell commands and generated image result URLs]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires dLazy authentication; the workflow generates one image command at a time and waits for user confirmation between phases.]\n\n## Skill Version(s):\n\n1.2.16 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.16:SKILL-cn.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nArchive v1.2.15: 4 files, 11186 bytes\n\nFiles: skill-card.md (2325b), SKILL-cn.md (8886b), SKILL.md (8886b), _meta.json (146b)\n\nFile v1.2.15:SKILL.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, not to reinterpret.\n3. User assets first\n   - Reference images, logos, and assets provided by the user have the highest priority.\n   - Strictly separate visual style from textual content; the brand name uses what the user specifies.\n\n## Execution Framework\n\n### Step 0: Task Planning (Mandatory)\n\nBefore any design output, call the `write_todos` tool to set up a task plan that includes at least:\n\n- Gather requirements and boundaries\n- Design the core logo concept\n- Generate derivatives and the brand system\n- Phase confirmation and iterative correction\n\nExecution rules:\n\n- Keep only one task `in_progress`; the rest are `pending`.\n- Update `write_todos` status as soon as each phase finishes.\n- If the user asks for rework or new assets, add or re-order tasks and re-enter the corresponding phase.\n\n### Step A: Gather Requirements\n\nYou must confirm:\n\n- Brand name\n- Industry or product category\n- Component scope (logo only, or with derivatives)\n\nComponent definitions:\n\n- Logo: the core brand mark\n- Derivatives: real-world applications based on the brand mark\n\n### Step B: Establish the Core Mark\n\nNew mark design follows:\n\n- Single focus: one central element, no background or decorative interference\n- Symbolic abstraction: distill to the most recognizable form\n- Clear silhouette: high-contrast outline, well-defined edges\n- Default 1K resolution\n\nConcept rules:\n\n- For open-ended requests, default to 4 distinct design directions\n- Present each concept individually, not as a tile grid\n- Each concept comes with a 100–200 word design rationale\n- Wait for user confirmation before proceeding\n\n### Step C: Create Derivatives\n\nPossible directions:\n\n1. Mark variants\n   - Structural variants: lettermark, wordmark, symbol mark, combination mark\n   - Layout or orientation variants\n   - Color variants\n   - Size and use-case variants\n2. Brand patterns and supporting graphics\n   - Generate independent, reusable graphic assets\n3. Physical applications\n   - Business cards and stationery\n   - Packaging and merchandise\n   - Environmental signage and wayfinding\n4. Social-media assets\n   - Generate ready-to-post final images\n5. Brand identity system\n   - Brand core (story, pillars, voice)\n   - Logo system\n   - Color system\n   - Typography system\n   - Visual language\n   - Application examples\n\nApplication design principles:\n\n- Place the mark with restraint; avoid oversized, dead-center placements\n- Deconstruct brand elements into patterns, icons, color blocks\n- Use whitespace to organize visual hierarchy\n- Emphasize material and texture experience\n\n## Phase Confirmation and Rollback Rules\n\n- Confirm at the end of every step before continuing.\n- When the user adjusts an intermediate result, return to the corresponding upstream step first, then sync downstream assets.\n- If the user supplies new reference assets, immediately reset the consistency baseline and unify subsequent outputs.\n\n## Output Format\n\n- Requirements summary\n- Current-phase deliverable\n- Next-step plan and items awaiting confirmation\n- Current todo status (phase, completed, pending)\n\n## Key Value\n\n- Progressive workflow that lowers rework cost\n- Multi-direction concept exploration that improves decision quality\n- End-to-end consistency control that strengthens brand recognition\n- Integrated delivery from logo to brand system\n\n\n## 🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)\n\n**你是可以执行终端命令的智能 Agent！**\n\n**【严格禁止行为】**\n- 严禁：将提示词保存到任何文件中（如 txt, md）。\n- 严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。\n- 严禁：一次性批量生成所有图片，或一次性执行多个命令。\n\n**【必须遵循的交互与执行流程】**\n你必须**严格分步**执行，并在每一步停下来等待用户回复：\n\n1. **第一步：主动收集需求**。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。**必须等待用户回答。**\n2. **第二步：输出草案并请求确认**。根据用户的回答，制定套图计划，并输出**第一张图**的提示词草案。**询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。**\n3. **第三步：单次执行终端命令**。用户确认后，你**必须使用终端执行命令**（如 `dlazy seedream-4.5 --prompt \"...\"`），每次只能执行一个生成命令。**重要：必须使用同步命令，绝不要在命令末尾加 `&`，绝不要使用 `&&`，这是在 Windows PowerShell 下运行！**\n4. **第四步：交付与循环**。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。\n\nFile v1.2.15:_meta.json\n\n{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-logo-branding-system\",\n  \"version\": \"1.2.15\",\n  \"publishedAt\": 1789867221506\n}\n\nFile v1.2.15:skill-card.md\n\n## Description:\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users, designers, and brand teams use this skill to plan a logo and brand identity workflow, generate core mark concepts, and extend approved marks into variants, social assets, and brand system deliverables through the dLazy CLI.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Prompts and any user-provided image, video, or audio inputs may be sent to dLazy-hosted services.\n\nMitigation: Use the skill only with data appropriate for third-party processing, and avoid sending confidential brand assets unless that use is approved.\n\nRisk: Using dLazy login or auth setup can store an API key in the local dLazy configuration file.\n\nMitigation: Use DLAZY_API_KEY per session when persistent local storage is not desired, and rotate or revoke keys from the dLazy dashboard when needed.\n\nRisk: The evidence notes documentation version inconsistencies around the dLazy CLI and skill release.\n\nMitigation: Confirm the intended skill and CLI versions before publishing, installing globally, or relying on the documented commands.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/dlazyai/skills/dlazy-logo-branding-system)\n- [dLazy CLI source](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown, Shell commands]\n\n**Output Format:** [Markdown with structured requirements summaries, prompt drafts, status updates, and inline shell commands]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include generated image URLs returned by dLazy-hosted services.]\n\n## Skill Version(s):\n\n1.2.15 (source: ClawHub release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.2.15:SKILL-cn.md\n\n---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  \n\nArchive v1.2.14: 4 files, 11160 bytes\n\nFiles: skill-card.md (2304b), SKILL-cn.md (8886b), SKILL.md (8886b), _meta.json (146b)","readmeExcerpt":"Skill: Logo 品牌设计系统 Logo Branding System Owner: dlazyai Summary: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery. Tags: latest:1.2.23 Version history: v1.2.23 | 2026-10-10T01:19:30.587Z | user 例行版本更新 2026-10-10 v1.2.22 | 2026-10-08T01:19:26.891Z | user 例行版本更新 2026-10-08 v1.2.21 | 2026-10-04T01:1","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"dlazy login"},{"language":"bash","snippet":"dlazy auth set YOUR_API_KEY"},{"language":"bash","snippet":"npx @dlazy/cli@1.2.3 <command>"},{"language":"bash","snippet":"dlazy login"},{"language":"bash","snippet":"dlazy auth set YOUR_API_KEY"},{"language":"bash","snippet":"npx @dlazy/cli@1.2.3 <command>"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, n"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7c5wgeajfcfvdfb5ceemvdb984cjpd\",\n  \"slug\": \"dlazy-logo-branding-system\",\n  \"version\": \"1.2.23\",\n  \"publishedAt\": 1791595170587\n}"},{"path":"skill-card.md","content":"## Description:\n\nGuides agents through a staged logo and brand-identity design process, from core marks to consistent visual applications and deliverables.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dlazyai](https://clawhub.ai/user/dlazyai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDesigners, marketers, and other external users can use this skill to plan and refine a logo, explore brand directions, and develop coordinated variants and visual applications with approval at each stage.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Installing a third-party CLI and storing a dLazy API key locally may expose credentials if the environment is not trusted.\n\nMitigation: Install only in a trusted environment; prefer the one-time npx invocation if a persistent global installation is unnecessary, and protect or rotate the API key.\n\nRisk: Prompts and referenced media files are sent to dLazy cloud endpoints for generation.\n\nMitigation: Check the content and obtain permission before sending sensitive prompts or media to dLazy.\n\nRisk: Installation metadata pins CLI version 1.2.3, while the prose also mentions an older 1.0.9 version.\n\nMitigation: Confirm the intended @dlazy/cli version before installing or running it.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/dlazyai/skills/dlazy-logo-branding-system)\n- [dLazy CLI repository (linked in skill metadata; not verified skill provenance)](https://github.com/dlazy-ai/cli)\n- [dLazy CLI npm package](https://www.npmjs.com/package/@dlazy/cli)\n- [dLazy website](https://dlazy.com)\n\n## Skill Output:\n\n**Output Type(s):** [Markdown, Guidance, Shell commands, Image links]\n\n**Output Format:** [Markdown with design rationales, stepwise plans, commands, and links to generated images]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Delivers logo concepts and brand-system applications incrementally, with user confirmation between stages.]\n\n## Skill Version(s):\n\n1.2.23 (source: ClawHub release metadata; embedded skill frontmatter says 1.2.3)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."},{"path":"SKILL-cn.md","content":"---\nname: dlazy-logo-branding-system\nversion: 1.2.3\ndescription: A professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\ntriggers:\n  - Logo & Branding Professional Design System\nmetadata: {\"clawdbot\":{\"emoji\":\"🤖\",\"requires\":{\"bins\":[\"npm\",\"npx\"]},\"install\":\"npm install -g @dlazy/cli@1.2.3\",\"installAlternative\":\"npx @dlazy/cli@1.2.3\",\"homepage\":\"https://github.com/dlazy-ai/cli\",\"source\":\"https://github.com/dlazy-ai/cli\",\"author\":\"dlazyai\",\"license\":\"see-repo\",\"npm\":\"https://www.npmjs.com/package/@dlazy/cli\",\"configLocation\":\"~/.dlazy/config.json\",\"apiEndpoints\":[\"api.dlazy.com\",\"files.dlazy.com\"]},\"openclaw\":{\"systemPrompt\":\"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 `&` 或 `&&` 进行命令串联或后台运行，请单独且同步地执行命令。\"}}\n---\n\n## 身份验证 (Authentication)\n\n所有请求都需要 dLazy API key。**推荐使用** `dlazy login` 完成登录：\n\n```bash\ndlazy login\n```\n\n该命令使用设备码流程（远程终端也可用），登录成功后 **自动把 API key 写入本地 CLI 配置**，无需手动复制粘贴。\n\n### 备选：手动设置 API Key\n\n如果你已有 API key，也可以直接保存：\n\n```bash\ndlazy auth set YOUR_API_KEY\n```\n\nCLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 `~/.dlazy/config.json`，Windows 上为 `%USERPROFILE%\\.dlazy\\config.json`），文件权限仅限当前操作系统用户访问。你也可以用 `DLAZY_API_KEY` 环境变量按次传入。\n\n### 手动获取 API Key\n\n1. 登录或在 [dlazy.com](https://dlazy.com) 创建账号\n2. 访问 [dlazy.com/dashboard/organization/api-key](https://dlazy.com/dashboard/organization/api-key)\n3. 复制 API Key 区域显示的密钥\n\n每个 key 都属于你自己的 dLazy 组织，可在同一控制面板**随时轮换或吊销**。\n\n## 关于与来源 (Provenance)\n\n- **CLI 源代码**: [github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli)\n- **维护者**: dlazyai\n- **npm 包名**: `@dlazy/cli`（本技能 install 字段固定到 `1.0.9` 版本）\n- **官网**: [dlazy.com](https://dlazy.com)\n\n如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：\n\n```bash\nnpx @dlazy/cli@1.2.3 <command>\n```\n\n如选择全局安装，技能的 `metadata.clawdbot.install` 字段已固定到 `npm install -g @dlazy/cli@1.2.3`。安装前建议先到 GitHub 仓库审阅源码。\n\n## 工作原理 (How It Works)\n\n此技能是 dLazy 托管 API 的轻量封装。调用时：\n\n- 你提供的提示词与参数会发送到 dLazy API（`api.dlazy.com`）进行推理。\n- 传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（`files.dlazy.com`），以便模型读取 —— 与任何云端生成 API 的流程一致。\n- API 返回的生成结果 URL 由 `files.dlazy.com` 托管。\n\n这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。\n\n# Logo 品牌设计系统 Logo Branding System\n\n[English](./SKILL.md) · [中文](./SKILL-cn.md)\n\nA professional pipeline for building everything from a core mark to a complete brand visual system, ensuring creative quality, execution consistency, and shippable delivery.\n\n## Core Principles\n\n1. Stepwise execution\n   - Use a progressive flow; never dump large outputs in one shot.\n   - When a single plan exceeds 2 images, submit the execution plan and wait for confirmation before generating.\n   - Upstream assets must be confirmed before downstream applications proceed.\n2. Object consistency\n   - The same brand element stays strictly consistent across all applications.\n   - When deriving variants from an existing image, the goal is to replicate consistency, n"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1297,"uniquenessScore":40,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T06:07:01.278Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-10T06:07:01.278Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T10:45:23.585Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}