{"id":"f7c321ab-c2cf-4012-9380-0f2a7a4a9636","entityType":"agent","slug":"clawhub-flyelepai-flyelep-ai-image-matting","name":"AI-Image-Matting","canonicalUrl":"https://www.xpersona.co/agent/clawhub-flyelepai-flyelep-ai-image-matting","canonicalPath":"/agent/clawhub-flyelepai-flyelep-ai-image-matting","generatedAt":"2026-10-11T03:56:36.502Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T01:02:52.969Z","emptyReason":null},"description":"通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。 Skill: AI-Image-Matting Owner: flyelepai Summary: 通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。 Tags: latest:1.0.4 Version history: v1.0.4 | 2026-08-28T03:14:20.887Z | user - Expanded documentation to include a \"本地文件上传\" section for handling local images by uploading them to obtain public URLs before processing. - Clarified authentication and file format requirements for both image background","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s175rfkzzv81fcfhp65sjggxa984fmry:flyelep-ai-image-matting","sourceUrl":"https://clawhub.ai/flyelepai/flyelep-ai-image-matting","homepage":"https://clawhub.ai/flyelepai/skills/flyelep-ai-image-matting","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/flyelepai/flyelep-ai-image-matting","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/flyelepai/skills/flyelep-ai-image-matting","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":62,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。 Skill: AI-Image-Matting Owner: flyelepai Summary: 通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。 "},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T01:02:52.969Z","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":"2026-10-11T01:02:52.969Z","emptyReason":null},"stars":null,"forks":null,"downloads":1211,"packageName":null,"latestVersion":"1.0.4","tractionLabel":"1.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T01:02:52.892Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T01:02:52.969Z","lastCrawledAt":"2026-10-11T01:02:52.892Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T01:02:52.892Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.4","createdAt":"2026-08-28T03:14:20.887Z","changelog":"- Expanded documentation to include a \"本地文件上传\" section for handling local images by uploading them to obtain public URLs before processing. - Clarified authentication and file format requirements for both image background removal and file upload. - Improved and consolidated cross-platform (Windows, macOS/Linux) API call examples for better usability. - Added step-by-step execution flow, emphasizing explicit user input for API keys and image paths. - Removed redundant or duplicate content and updated security notices. - Removed the redundant skill-card.md file.","fileCount":3,"zipByteSize":5433},{"version":"1.0.3","createdAt":"2026-08-07T06:17:32.317Z","changelog":"- Added detailed multi-platform (Windows/PowerShell, macOS/Linux) API call instructions, including encoding/temporary file handling for robust compatibility. - Updated required parameter collection: agents must now prompt users for all required fields before execution and get explicit input/confirmation. - Strengthened API usage notes, enforcing correct Content-Type and platform-specific invocation guides. - Removed the skill-card.md file.","fileCount":3,"zipByteSize":4663},{"version":"1.0.2","createdAt":"2026-04-27T03:54:18.078Z","changelog":"- No user-facing or functionality changes in this version. - All files remain unchanged.","fileCount":3,"zipByteSize":3654},{"version":"1.0.1","createdAt":"2026-04-27T01:13:51.399Z","changelog":"- 更新认证方式说明，新增了 Flyelep 控制台申请 API 密钥的网址链接（https://www.flyelep.cn/controlboard） - 其余接口文档、用法说明和功能保持不变","fileCount":2,"zipByteSize":2429},{"version":"1.0.0","createdAt":"2026-04-20T07:30:50.456Z","changelog":"- Initial release of the ai-image-matting skill. - Enables automatic image background removal using the Flyelep AI API. - Supports both single and batch processing of image URLs. - Returns transparent-background image links after processing. - Requires users to provide a valid secretKey in request headers.","fileCount":2,"zipByteSize":2414}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s175rfkzzv81fcfhp65sjggxa984fmry:flyelep-ai-image-matting","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"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-flyelepai-flyelep-ai-image-matting/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-flyelepai-flyelep-ai-image-matting/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-flyelepai-flyelep-ai-image-matting/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-flyelepai-flyelep-ai-image-matting/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-flyelepai-flyelep-ai-image-matting/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-flyelepai-flyelep-ai-image-matting/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T03:56:36.501Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-flyelepai-flyelep-ai-image-matting/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-flyelepai-flyelep-ai-image-matting/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-flyelepai-flyelep-ai-image-matting/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-flyelepai-flyelep-ai-image-matting/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":"high","updatedAt":"2026-10-11T01:02:52.969Z","emptyReason":null},"readme":"Skill: AI-Image-Matting\n\nOwner: flyelepai\n\nSummary: 通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。\n\nTags: latest:1.0.4\n\nVersion history:\n\nv1.0.4 | 2026-08-28T03:14:20.887Z | user\n\n- Expanded documentation to include a \"本地文件上传\" section for handling local images by uploading them to obtain public URLs before processing.\n- Clarified authentication and file format requirements for both image background removal and file upload.\n- Improved and consolidated cross-platform (Windows, macOS/Linux) API call examples for better usability.\n- Added step-by-step execution flow, emphasizing explicit user input for API keys and image paths.\n- Removed redundant or duplicate content and updated security notices.\n- Removed the redundant skill-card.md file.\n\nv1.0.3 | 2026-08-07T06:17:32.317Z | user\n\n- Added detailed multi-platform (Windows/PowerShell, macOS/Linux) API call instructions, including encoding/temporary file handling for robust compatibility.\n- Updated required parameter collection: agents must now prompt users for all required fields before execution and get explicit input/confirmation.\n- Strengthened API usage notes, enforcing correct Content-Type and platform-specific invocation guides.\n- Removed the skill-card.md file.\n\nv1.0.2 | 2026-04-27T03:54:18.078Z | user\n\n- No user-facing or functionality changes in this version.\n- All files remain unchanged.\n\nv1.0.1 | 2026-04-27T01:13:51.399Z | user\n\n- 更新认证方式说明，新增了 Flyelep 控制台申请 API 密钥的网址链接（https://www.flyelep.cn/controlboard）\n- 其余接口文档、用法说明和功能保持不变\n\nv1.0.0 | 2026-04-20T07:30:50.456Z | user\n\n- Initial release of the ai-image-matting skill.\n- Enables automatic image background removal using the Flyelep AI API.\n- Supports both single and batch processing of image URLs.\n- Returns transparent-background image links after processing.\n- Requires users to provide a valid secretKey in request headers.\n\nArchive index:\n\nArchive v1.0.4: 3 files, 5433 bytes\n\nFiles: skill-card.md (2469b), SKILL.md (9570b), _meta.json (143b)\n\nFile v1.0.4:SKILL.md\n\n---\nname: ai-image-matting\ndescription: >-\n 通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。\n 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。\n---\n# Flyelep AI抠图\n\n通过 Flyelep AI Tool API 自动去除图片背景，并返回抠图后的新图片 URL。\n\n**重要：这是一个 HTTP API 调用技能。必须通过 HTTP POST 请求调用 API 接口，禁止通过浏览器访问 Flyelep 网站。**\n\n## API 接口信息\n\n- **URL**: `POST https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting`\n- **Content-Type**: `application/json`\n- **认证方式**: 在请求头中传入 `secretKey`（密钥需由用户在 Flyelep 开放平台申请：https://www.flyelep.cn/controlboard）\n- **超时时间**: 建议 120-300 秒\n\n请求头示例：\n\n```http\nContent-Type: application/json\nsecretKey: 用户提供的API密钥\n```\n\n> **安全说明**：不要将真实密钥写入技能文件、示例代码仓库或持久化配置中，应在运行时由用户动态提供。\n\n## 请求 Body\n\n```json\n{\n \"imgUrls\": \"https://example.com/img1.jpg,https://example.com/img2.jpg\"\n}\n```\n\n## 响应格式\n\n```json\n{\n \"code\": 200,\n \"msg\": \"操作成功\",\n \"data\": \"https://example.com/matted1.png,https://example.com/matted2.png\"\n}\n```\n\n- `code=200` 表示调用成功\n- `msg` 为接口返回说明\n- `data` 为抠图后图片地址，多张时以英文逗号 `,` 分隔\n- 返回结果应按逗号拆分后逐个展示给用户，不要回读图片内容\n\n## 参数说明\n\n### 必传参数\n\n> **重要**：以下必传参数必须通过询问用户获取，agent 不可自行填写。调用本技能时，应先向用户列出必传参数与可选参数表格，由用户确认或提供后再执行。\n\n| 字段 | 默认值 | 说明 |\n|------|--------|------|\n| imgUrls | - | 图片链接字符串，多张时使用英文逗号分隔 |\n\n### 参数映射规则\n\n**imgUrls**：\n- 接口要求传字符串，不是数组\n- 单张图片直接传 URL 字符串；多张图片用英文逗号 `,` 拼接\n- 也可以改用 `imageUrl` 字段传单张图片，两者二选一；同时传时以 `imgUrls` 为准\n- 每个链接都应为公网可访问的图片直链\n- 如果用户提供本地文件路径，先按「本地文件上传」章节换取公网直链，再填入此参数\n\n**结果格式**：\n- 抠图结果通常为透明背景的 `.png` 图片\n- 若接口实际返回其他格式，按接口返回值原样展示即可\n\n## 本地文件上传\n\n用户提供的是本地文件路径而不是公网直链时，先把文件上传换取直链，再调用本接口。已安装 `file-upload` 技能时以该技能为准；未安装时按下面的说明直接调用上传接口。\n\n- **URL**: `POST https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload`\n- **请求方式**: `multipart/form-data`，文件字段名固定为 `file`，单次只能上传一个文件，多个文件并发调用多次\n- **认证方式**: 请求头传 `secretKey`，与本技能使用同一个密钥\n- **超时时间**: 图片建议 60-120 秒\n- **不要手动设置 `Content-Type` 请求头**，让 HTTP 客户端自动生成带 boundary 的值，手写会导致服务端解析失败\n- 图片仅支持 `bmp`、`gif`、`jpg`、`jpeg`、`png`，`webp` 需先转成 `png` 或 `jpg`；文件名必须带正确后缀，服务端靠它判断格式\n- 原文件名不会出现在 URL 里，中文名、空格、特殊字符都能直接上传，不需要提前改名\n- 上传不消耗算力，但服务端不做去重：同一个文件在一次任务里只上传一次，记下 `fullPath` 复用\n\n成功响应取 `data.fullPath` 作为公网直链，永久有效、不带签名：\n\n```json\n{\n \"code\": 200,\n \"msg\": null,\n \"data\": {\n \"relativePath\": \"cos_ai_agent/2026-08-11/3f2a9c1b7d84e6f5a012.png\",\n \"fullPath\": \"https://agent-1404002717.cos.ap-guangzhou.myqcloud.com/cos_ai_agent/2026-08-11/3f2a9c1b7d84e6f5a012.png\",\n \"serviceProvider\": null\n }\n}\n```\n\n判断成功只看 `code`，业务失败时 HTTP 状态码仍是 200，`code` 为 500 或 9999，原因在 `msg` 里。\n\n```bash\n# Windows/PowerShell（用 curl.exe，PowerShell 里的 curl 是 Invoke-WebRequest 的别名）\ncurl.exe -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload\" -H \"secretKey: 你的密钥\" --max-time 120 -F \"file=@C:/path/to/product.png\"\n\n# macOS/Linux\ncurl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload\" -H \"secretKey: 你的密钥\" --max-time 120 -F \"file=@./product.png\"\n```\n\n图片入桶前会先过内容审核，审核不通过整个请求失败，需换图重试。拿到 `code=9999`、`msg` 为 `服务繁忙，请稍后再试` 时，先自查三项：是否漏了 `secretKey` 请求头、表单字段名是否为 `file`、文件是否超出服务端体积上限。密钥、格式、审核、体积类错误重试无效，只有网络超时、5xx 和存储类异常值得重试。\n\n## 调用示例\n\n> **跨平台调用说明**：\n> - 请求头必须包含 `Content-Type: application/json; charset=utf-8` 和 `secretKey`\n> - **Windows/PowerShell**：因 GBK 编码问题，必须先将 JSON 写入临时文件 `payload_temp.json`（UTF-8 无 BOM），再用 `curl.exe --% --data-binary @payload_temp.json` 发送请求。使用 Write 工具创建文件，或用 .NET API `[System.IO.File]::WriteAllText(\"payload_temp.json\", $json, [System.Text.UTF8Encoding]::new($false))`。调用后用 `rm payload_temp.json` 清理。\n> - **macOS/Linux**：bash/zsh 默认 UTF-8，可直接内联 JSON：`curl -X POST URL -H \"Content-Type: application/json; charset=utf-8\" -H \"secretKey: 你的密钥\" --data-binary 'JSON单行内容'`\n\n### 示例 1：单张图片抠图\n\n**前置步骤**：向用户索取图片路径或 URL。如用户提供本地文件，先按「本地文件上传」章节换取公网直链。\n\n**Windows/PowerShell**：\n\n步骤 1：创建 `payload_temp.json`（两种方式任选其一）：\n\n方式 A（使用 Write 工具）：\n```json\n{\n \"imgUrls\": \"https://example.com/img1.jpg\"\n}\n```\n\n方式 B（无 Write 工具，PowerShell 执行）：\n```powershell\n[System.IO.File]::WriteAllText(\"payload_temp.json\", '{\"imgUrls\":\"https://example.com/img1.jpg\"}', [System.Text.UTF8Encoding]::new($false))\n```\n\n步骤 2：执行请求：\n```bash\ncurl.exe --% -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" -H \"Content-Type: application/json; charset=utf-8\" -H \"secretKey: 你的密钥\" --max-time 300 --data-binary @payload_temp.json\n```\n\n步骤 3：清理临时文件：\n```bash\nrm payload_temp.json\n```\n\n**macOS/Linux**：\n```bash\ncurl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" -H \"Content-Type: application/json; charset=utf-8\" -H \"secretKey: 你的密钥\" --max-time 300 --data-binary '{\"imgUrls\":\"https://example.com/img1.jpg\"}'\n```\n\n### 示例 2：批量图片抠图\n\n**前置步骤**：向用户索取图片路径或 URL。如用户提供本地文件，先按「本地文件上传」章节换取公网直链。\n\n**Windows/PowerShell**：\n\n步骤 1：创建 `payload_temp.json`（两种方式任选其一）：\n\n方式 A（使用 Write 工具）：\n```json\n{\n \"imgUrls\": \"https://example.com/img1.jpg,https://example.com/img2.jpg\"\n}\n```\n\n方式 B（无 Write 工具，PowerShell 执行）：\n```powershell\n[System.IO.File]::WriteAllText(\"payload_temp.json\", '{\"imgUrls\":\"https://example.com/img1.jpg,https://example.com/img2.jpg\"}', [System.Text.UTF8Encoding]::new($false))\n```\n\n步骤 2：执行请求：\n```bash\ncurl.exe --% -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" -H \"Content-Type: application/json; charset=utf-8\" -H \"secretKey: 你的密钥\" --max-time 300 --data-binary @payload_temp.json\n```\n\n步骤 3：清理临时文件：\n```bash\nrm payload_temp.json\n```\n\n**macOS/Linux**：\n```bash\ncurl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" -H \"Content-Type: application/json; charset=utf-8\" -H \"secretKey: 你的密钥\" --max-time 300 --data-binary '{\"imgUrls\":\"https://example.com/img1.jpg,https://example.com/img2.jpg\"}'\n```\n\n## 常见错误及解决方案\n\n| 错误 | 原因与解决 |\n|------|-----------|\n| HTTP 401 / `code` 非 200 | `secretKey` 无效、缺失或已过期，确认请求头是否正确传入 |\n| HTTP 405 Not Allowed | 请求方法错误，必须使用 `POST` |\n| `imgUrls` 格式错误 | 该字段必须是字符串，多张图用英文逗号分隔，不是 JSON 数组 |\n| 图片 URL 无法访问 | 传入的链接不是公网直链、已过期，或源站限制访问 |\n| 抠图边缘效果不理想 | 原图主体与背景对比不足、边缘过于复杂，可换更清晰或背景更干净的源图 |\n| 请求超时 | 批量图片较多或源图较大时，可适当增大超时时间 |\n\n## 执行流程\n\n1. **向用户询问 `secretKey`**（API 密钥必须由用户提供，agent 不可自行填写）\n2. 收集一张或多张图片 URL（如用户提供本地文件，先按「本地文件上传」章节换取公网直链）\n3. 将多张 URL 用英文逗号拼接为 `imgUrls`\n4. 在请求头中传入 `secretKey`，调用接口\n5. 将返回的结果按逗号拆分后逐个展示\n\n> 当用户明确要求\"透明底\"\"抠出主体\"\"去掉背景\"时，优先使用此技能；如果用户真正想要的是\"换背景\"而不是\"去背景\"，则更适合使用场景替换或局部重绘类技能。\n\nFile v1.0.4:_meta.json\n\n{\n \"ownerId\": \"kn7fp1zsg4nwdq826y0awapkks84fkq1\",\n \"slug\": \"flyelep-ai-image-matting\",\n \"version\": \"1.0.4\",\n \"publishedAt\": 1787886860887\n}\n\nFile v1.0.4:skill-card.md\n\n## Description:\n\nUses the Flyelep AI Tool API to remove image backgrounds for one or more public image URLs and return the resulting matted image URLs.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[flyelepai](https://clawhub.ai/user/flyelepai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to remove image backgrounds, extract product subjects, or generate transparent-background image assets through Flyelep's hosted API.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Local images may be uploaded to a third-party service and converted into permanent unsigned public URLs.\n\nMitigation: Use only images that are appropriate to send to Flyelep and expose through a public URL, or confirm deletion and access-control guarantees before processing sensitive material.\n\nRisk: API keys could be exposed if written into prompts, files, examples, or logs.\n\nMitigation: Provide the Flyelep secretKey only at runtime and avoid persisting it in skill files, temporary payloads, prompts, or logs.\n\nRisk: The security evidence flags the release as suspicious due to third-party upload behavior without a documented informed-consent step.\n\nMitigation: Review the upload behavior before installation and obtain user confirmation before processing private photos, identity documents, credentials, medical images, or confidential business material.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/flyelepai/skills/flyelep-ai-image-matting)\n- [Flyelep controlboard](https://www.flyelep.cn/controlboard)\n- [Flyelep image matting API endpoint](https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting)\n- [Flyelep file upload API endpoint](https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with JSON and shell command examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Returns one or more hosted matted image URLs from the Flyelep API.]\n\n## Skill Version(s):\n\n1.0.4 (source: server 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\nArchive v1.0.3: 3 files, 4663 bytes\n\nFiles: skill-card.md (2107b), SKILL.md (7940b), _meta.json (143b)\n\nFile v1.0.3:SKILL.md\n\n---\r\nname: ai-image-matting\r\ndescription: >-\r\n 通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。\r\n 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。\r\n---\r\n# Flyelep AI抠图\r\n通过 Flyelep AI Tool API 自动去除图片背景，并返回抠图后的新图片 URL。\r\n\r\n**重要：这是一个 HTTP API 调用技能。必须通过 HTTP POST 请求调用 API 接口，禁止通过浏览器访问 Flyelep 网站。**\r\n\r\n## API 接口信息\r\n- **URL**: `POST https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting`\r\n- **Content-Type**: `application/json`\r\n- **认证方式**: 在请求头中传入 `secretKey`\r\n- **超时时间**: 建议 120-300 秒\r\n\r\n## 认证方式\r\n所有 AI 工具接口均需在请求头中传入 `secretKey`。该密钥需由用户在 Flyelep 开放平台申请获得：https://www.flyelep.cn/controlboard 。\r\n\r\n请求头示例：\r\n\r\n```http\r\nContent-Type: application/json\r\nsecretKey: 用户提供的API密钥\r\n```\r\n\r\n> **安全说明**：`secretKey` 必须放在请求头中，这是 AI 工具接口的统一鉴权要求。不要将真实密钥写入技能文件、示例代码仓库或持久化配置中，应在运行时由用户动态提供。\r\n\r\n## 请求 Body\r\n```json\r\n{\r\n \"imgUrls\": \"https://example.com/img1.jpg,https://example.com/img2.jpg\"\r\n}\r\n```\r\n\r\n## 响应格式\r\n统一响应结构：\r\n\r\n```json\r\n{\r\n \"code\": 200,\r\n \"msg\": \"操作成功\",\r\n \"data\": \"https://example.com/matted1.png,https://example.com/matted2.png\"\r\n}\r\n```\r\n\r\n- `code=200` 表示调用成功\r\n- `msg` 为接口返回说明\r\n- `data` 为抠图后图片地址\r\n- 多张图片时，`data` 中多个 URL 以英文逗号 `,` 分隔\r\n\r\n返回结果应按逗号拆分后逐个展示给用户，不要回读图片内容。\r\n\r\n## 参数说明\r\n### 必传参数\r\n\r\n> **重要**：以下必传参数必须通过询问用户获取，agent 不可自行填写。调用本技能时，应先向用户列出必传参数与可选参数表格，由用户确认或提供后再执行。\r\n\r\n| 字段 | 默认值 | 说明 |\r\n|------|--------|------|\r\n| imgUrls | - | 图片链接字符串，多张时使用英文逗号分隔 |\r\n\r\n## 参数映射规则\r\n### imgUrls\r\n- 接口要求传字符串，不是数组\r\n- 单张图片时直接传一个 URL 字符串\r\n- 多张图片时，用英文逗号 `,` 按顺序拼接\r\n- 每个链接都应为公网可访问的图片直链，不要传网页地址\r\n\r\n### 结果格式\r\n- 抠图结果通常更适合返回透明背景图片\r\n- 文档示例中返回的是 `.png`，因此应优先预期结果为支持透明底的图片格式\r\n- 若接口实际返回其他格式，按接口返回值原样展示即可\r\n\r\n## 调用示例\r\n- **重要**：调用 API 时，必须设置 `Content-Type: application/json; charset=utf-8` 请求头。以下分平台说明：\r\n- **Windows/PowerShell 环境**：\r\n - 必须采用以下流程：**先将请求体 JSON 写入当前工作目录下的临时文件 `payload_temp.json`，再通过 Shell 工具调用 `curl.exe --data-binary @payload_temp.json` 发送请求**。这是因为 PowerShell 使用 GBK 编码，而服务端使用 UTF-8 解析，直接在命令行中嵌入中文 JSON 会导致乱码。\r\n - 使用 `curl.exe`（而非 `curl`，后者在 PowerShell 中是 `Invoke-WebRequest` 的别名）。必须在 `curl.exe` 后加 `--%` 停止 PowerShell 解析，否则 `@` 会被误判为 splatting 操作符导致报错。\r\n - **文件创建方式**：根据可用工具选择其一（均需确保 UTF-8 **无 BOM** 编码，否则服务端 JSON 解析会在 position 0 报错）：\r\n - **方式 A（有 Write 工具）**：使用 Write 工具创建 `payload_temp.json`\r\n - **方式 B（无 Write 工具）**：使用 Shell 的 .NET API 创建文件（`Set-Content -Encoding UTF8` 会带 BOM，不可用）\r\n- **macOS/Linux 环境**：\r\n - bash/zsh 默认使用 UTF-8 编码，可直接内联中文 JSON，无需临时文件。命令中使用 `curl`（无需 `.exe`，无需 `--%`）。\r\n - 推荐内联写法：`curl -X POST URL -H \"Content-Type: application/json; charset=utf-8\" -H \"secretKey: 你的密钥\" --data-binary 'JSON单行内容'`，一步完成\r\n - 也可使用临时文件方式：`curl --data-binary @payload_temp.json`\r\n- **清理**：API 返回结果后，务必删除 `payload_temp.json` 临时文件（如使用了临时文件）。\r\n\r\n**示例 1：单张图片抠图**\r\n\r\n步骤 1：创建 `payload_temp.json`，内容如下：\r\n```json\r\n{\r\n \"imgUrls\": \"https://example.com/img1.jpg\"\r\n}\r\n```\r\n> 方式 B（无 Write 工具）：\r\n> ```powershell\r\n> $json = '{\"imgUrls\":\"https://example.com/img1.jpg\"}'\r\n> [System.IO.File]::WriteAllText(\"payload_temp.json\", $json, [System.Text.UTF8Encoding]::new($false))\r\n> ```\r\n\r\n步骤 2：使用 Shell 工具执行：\r\n```bash\r\ncurl.exe --% -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" -H \"Content-Type: application/json; charset=utf-8\" -H \"secretKey: 你的密钥\" --max-time 300 --data-binary @payload_temp.json\r\n```\r\n\r\n> **macOS/Linux 内联写法**（无需临时文件）：\r\n> ```bash\r\n> curl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" -H \"Content-Type: application/json; charset=utf-8\" -H \"secretKey: 你的密钥\" --max-time 300 --data-binary '{\"imgUrls\":\"https://example.com/img1.jpg\"}'\r\n> ```\r\n\r\n步骤 3：清理临时文件：\r\n```bash\r\nrm payload_temp.json\r\n```\r\n\r\n**示例 2：批量图片抠图**\r\n\r\n步骤 1：创建 `payload_temp.json`，内容如下：\r\n```json\r\n{\r\n \"imgUrls\": \"https://example.com/img1.jpg,https://example.com/img2.jpg\"\r\n}\r\n```\r\n> 方式 B（无 Write 工具）：\r\n> ```powershell\r\n> $json = '{\"imgUrls\":\"https://example.com/img1.jpg,https://example.com/img2.jpg\"}'\r\n> [System.IO.File]::WriteAllText(\"payload_temp.json\", $json, [System.Text.UTF8Encoding]::new($false))\r\n> ```\r\n\r\n步骤 2：使用 Shell 工具执行：\r\n```bash\r\ncurl.exe --% -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" -H \"Content-Type: application/json; charset=utf-8\" -H \"secretKey: 你的密钥\" --max-time 300 --data-binary @payload_temp.json\r\n```\r\n\r\n> **macOS/Linux 内联写法**（无需临时文件）：\r\n> ```bash\r\n> curl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" -H \"Content-Type: application/json; charset=utf-8\" -H \"secretKey: 你的密钥\" --max-time 300 --data-binary '{\"imgUrls\":\"https://example.com/img1.jpg,https://example.com/img2.jpg\"}'\r\n> ```\r\n\r\n步骤 3：清理临时文件：\r\n```bash\r\nrm payload_temp.json\r\n```\r\n\r\n## 常见错误及解决方案\r\n| 错误 | 原因与解决 |\r\n|------|-----------|\r\n| HTTP 401 / `code` 非 200 | `secretKey` 无效、缺失或已过期，确认请求头是否正确传入 |\r\n| HTTP 405 Not Allowed | 请求方法错误，必须使用 `POST` |\r\n| `imgUrls` 格式错误 | 该字段必须是字符串，多张图用英文逗号分隔，不是 JSON 数组 |\r\n| 图片 URL 无法访问 | 传入的链接不是公网直链、已过期，或源站限制访问 |\r\n| 抠图边缘效果不理想 | 原图主体与背景对比不足、边缘过于复杂，可换更清晰或背景更干净的源图 |\r\n| 请求超时 | 批量图片较多或源图较大时，可适当增大超时时间 |\r\n\r\n## 提示词处理\r\n该接口不接收自然语言提示词，不需要构造额外文案。\r\n\r\n执行时只需要：\r\n\r\n1. 收集一张或多张图片 URL\r\n2. 将多张 URL 用英文逗号拼接为 `imgUrls`\r\n3. 在请求头中传入 `secretKey`\r\n4. 调用接口并将返回的结果按逗号拆分后逐个展示\r\n\r\n当用户明确要求“透明底”“抠出主体”“去掉背景”时，优先使用此技能；如果用户真正想要的是“换背景”而不是“去背景”，则更适合使用场景替换或局部重绘类技能。\n\nFile v1.0.3:_meta.json\n\n{\n \"ownerId\": \"kn7fp1zsg4nwdq826y0awapkks84fkq1\",\n \"slug\": \"flyelep-ai-image-matting\",\n \"version\": \"1.0.3\",\n \"publishedAt\": 1786083452317\n}\n\nFile v1.0.3:skill-card.md\n\n## Description:\n\nUses the Flyelep AI Tool API to remove image backgrounds for one or more public image URLs and return matted image URLs.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[flyelepai](https://clawhub.ai/user/flyelepai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and agents use this skill to remove backgrounds from product, subject, or other user-provided images by collecting public image URLs and a Flyelep API key, then presenting the returned transparent-background image URLs.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Image URLs and the Flyelep API key are sent to Flyelep during execution.\n\nMitigation: Use non-sensitive public image URLs, provide the API key only at runtime, and avoid saving the key in files or chat history.\n\nRisk: Temporary payload files may contain submitted image URLs when the Windows/PowerShell flow is used.\n\nMitigation: Create temporary payload files only when needed and delete them after the API response is received.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/flyelepai/skills/flyelep-ai-image-matting)\n- [Flyelep AI image matting API endpoint](https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting)\n- [Flyelep controlboard](https://www.flyelep.cn/controlboard)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Shell commands, API Calls, Guidance]\n\n**Output Format:** [Markdown guidance with JSON payloads, shell command examples, and returned image URLs.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires user-provided image URLs and a Flyelep secretKey; Windows/PowerShell usage may create a temporary JSON payload file that should be deleted after the API call.]\n\n## Skill Version(s):\n\n1.0.3 (source: server 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\nArchive v1.0.2: 3 files, 3654 bytes\n\nFiles: skill-card.md (2290b), SKILL.md (4316b), _meta.json (143b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: ai-image-matting\ndescription: >-\n 通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。\n 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。\n---\n# Flyelep AI抠图\n通过 Flyelep AI Tool API 自动去除图片背景，并返回抠图后的新图片 URL。\n\n**重要：这是一个 HTTP API 调用技能。必须通过 HTTP POST 请求调用 API 接口，禁止通过浏览器访问 Flyelep 网站。**\n\n## API 接口信息\n- **URL**: `POST https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting`\n- **Content-Type**: `application/json`\n- **认证方式**: 在请求头中传入 `secretKey`\n- **超时时间**: 建议 120-300 秒\n\n## 认证方式\n所有 AI 工具接口均需在请求头中传入 `secretKey`。该密钥需由用户在 Flyelep 开放平台申请获得：https://www.flyelep.cn/controlboard 。\n\n请求头示例：\n\n```http\nContent-Type: application/json\nsecretKey: 用户提供的API密钥\n```\n\n> **安全说明**：`secretKey` 必须放在请求头中，这是 AI 工具接口的统一鉴权要求。不要将真实密钥写入技能文件、示例代码仓库或持久化配置中，应在运行时由用户动态提供。\n\n## 请求 Body\n```json\n{\n \"imgUrls\": \"https://example.com/img1.jpg,https://example.com/img2.jpg\"\n}\n```\n\n## 响应格式\n统一响应结构：\n\n```json\n{\n \"code\": 200,\n \"msg\": \"操作成功\",\n \"data\": \"https://example.com/matted1.png,https://example.com/matted2.png\"\n}\n```\n\n- `code=200` 表示调用成功\n- `msg` 为接口返回说明\n- `data` 为抠图后图片地址\n- 多张图片时，`data` 中多个 URL 以英文逗号 `,` 分隔\n\n返回结果应按逗号拆分后逐个展示给用户，不要回读图片内容。\n\n## 参数说明\n### 必传参数\n| 字段 | 默认值 | 说明 |\n|------|--------|------|\n| imgUrls | - | 图片链接字符串，多张时使用英文逗号分隔 |\n\n## 参数映射规则\n### imgUrls\n- 接口要求传字符串，不是数组\n- 单张图片时直接传一个 URL 字符串\n- 多张图片时，用英文逗号 `,` 按顺序拼接\n- 每个链接都应为公网可访问的图片直链，不要传网页地址\n\n### 结果格式\n- 抠图结果通常更适合返回透明背景图片\n- 文档示例中返回的是 `.png`，因此应优先预期结果为支持透明底的图片格式\n- 若接口实际返回其他格式，按接口返回值原样展示即可\n\n## 调用示例\n**单张图片抠图：**\n\n```bash\ncurl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" \\\n -H \"Content-Type: application/json\" \\\n -H \"secretKey: 你的密钥\" \\\n --max-time 300 \\\n -d '{\n \"imgUrls\": \"https://example.com/img1.jpg\"\n }'\n```\n\n**批量图片抠图：**\n\n```bash\ncurl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" \\\n -H \"Content-Type: application/json\" \\\n -H \"secretKey: 你的密钥\" \\\n --max-time 300 \\\n -d '{\n \"imgUrls\": \"https://example.com/img1.jpg,https://example.com/img2.jpg\"\n }'\n```\n\n## 常见错误及解决方案\n| 错误 | 原因与解决 |\n|------|-----------|\n| HTTP 401 / `code` 非 200 | `secretKey` 无效、缺失或已过期，确认请求头是否正确传入 |\n| HTTP 405 Not Allowed | 请求方法错误，必须使用 `POST` |\n| `imgUrls` 格式错误 | 该字段必须是字符串，多张图用英文逗号分隔，不是 JSON 数组 |\n| 图片 URL 无法访问 | 传入的链接不是公网直链、已过期，或源站限制访问 |\n| 抠图边缘效果不理想 | 原图主体与背景对比不足、边缘过于复杂，可换更清晰或背景更干净的源图 |\n| 请求超时 | 批量图片较多或源图较大时，可适当增大超时时间 |\n\n## 提示词处理\n该接口不接收自然语言提示词，不需要构造额外文案。\n\n执行时只需要：\n\n1. 收集一张或多张图片 URL\n2. 将多张 URL 用英文逗号拼接为 `imgUrls`\n3. 在请求头中传入 `secretKey`\n4. 调用接口并将返回的结果按逗号拆分后逐个展示\n\n当用户明确要求“透明底”“抠出主体”“去掉背景”时，优先使用此技能；如果用户真正想要的是“换背景”而不是“去背景”，则更适合使用场景替换或局部重绘类技能。\n\nFile v1.0.2:_meta.json\n\n{\n \"ownerId\": \"kn7fp1zsg4nwdq826y0awapkks84fkq1\",\n \"slug\": \"flyelep-ai-image-matting\",\n \"version\": \"1.0.2\",\n \"publishedAt\": 1777262058078\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:
\nUses the Flyelep AI Tool API to remove image backgrounds from one or more public image URLs and return processed image URLs.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[flyelepai](https://clawhub.ai/user/flyelepai)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nAgents use this skill when a user asks to cut out a subject, remove an image background, extract a product subject, or create transparent-background assets. It is suitable for single-image or batch workflows where the input images are available as direct public URLs.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The skill sends user-provided image URLs to Flyelep's API with a user-supplied secretKey.
\nMitigation: Install only if you trust Flyelep with the submitted image URLs, provide the secretKey at runtime, and avoid storing the key in files or persistent configuration.
\nRisk: Private, expired, or non-direct image links may fail or expose content through an unintended public URL workflow.
\nMitigation: Use only intended public direct image URLs and test with non-sensitive images before submitting sensitive or production assets.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/flyelepai/flyelep-ai-image-matting)
\n- [Flyelep open platform](https://www.flyelep.cn/controlboard)
\n- [Flyelep AI image matting API endpoint](https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, shell commands, guidance]
\n**Output Format:** [Markdown with JSON and shell command examples; runtime results are image URLs returned by the API.]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Returns one or more processed image URLs, comma-separated by the API for batch requests.]
\n\n## Skill Version(s):
\n1.0.2 (source: server release metadata)
\n\n## Ethical Considerations:
\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\nArchive v1.0.1: 2 files, 2429 bytes\n\nFiles: SKILL.md (4315b), _meta.json (143b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: ai-image-matting\ndescription: >-\n 通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。\n 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。\n---\n# Flyelep AI抠图\n通过 Flyelep AI Tool API 自动去除图片背景，并返回抠图后的新图片 URL。\n\n**重要：这是一个 HTTP API 调用技能。必须通过 HTTP POST 请求调用 API 接口，禁止通过浏览器访问 Flyelep 网站。**\n\n## API 接口信息\n- **URL**: `POST https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting`\n- **Content-Type**: `application/json`\n- **认证方式**: 在请求头中传入 `secretKey`\n- **超时时间**: 建议 120-300 秒\n\n## 认证方式\n所有 AI 工具接口均需在请求头中传入 `secretKey`。该密钥需由用户在 Flyelep 开放平台申请获得：https://www.flyelep.cn/controlboard。\n\n请求头示例：\n\n```http\nContent-Type: application/json\nsecretKey: 用户提供的API密钥\n```\n\n> **安全说明**：`secretKey` 必须放在请求头中，这是 AI 工具接口的统一鉴权要求。不要将真实密钥写入技能文件、示例代码仓库或持久化配置中，应在运行时由用户动态提供。\n\n## 请求 Body\n```json\n{\n \"imgUrls\": \"https://example.com/img1.jpg,https://example.com/img2.jpg\"\n}\n```\n\n## 响应格式\n统一响应结构：\n\n```json\n{\n \"code\": 200,\n \"msg\": \"操作成功\",\n \"data\": \"https://example.com/matted1.png,https://example.com/matted2.png\"\n}\n```\n\n- `code=200` 表示调用成功\n- `msg` 为接口返回说明\n- `data` 为抠图后图片地址\n- 多张图片时，`data` 中多个 URL 以英文逗号 `,` 分隔\n\n返回结果应按逗号拆分后逐个展示给用户，不要回读图片内容。\n\n## 参数说明\n### 必传参数\n| 字段 | 默认值 | 说明 |\n|------|--------|------|\n| imgUrls | - | 图片链接字符串，多张时使用英文逗号分隔 |\n\n## 参数映射规则\n### imgUrls\n- 接口要求传字符串，不是数组\n- 单张图片时直接传一个 URL 字符串\n- 多张图片时，用英文逗号 `,` 按顺序拼接\n- 每个链接都应为公网可访问的图片直链，不要传网页地址\n\n### 结果格式\n- 抠图结果通常更适合返回透明背景图片\n- 文档示例中返回的是 `.png`，因此应优先预期结果为支持透明底的图片格式\n- 若接口实际返回其他格式，按接口返回值原样展示即可\n\n## 调用示例\n**单张图片抠图：**\n\n```bash\ncurl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" \\\n -H \"Content-Type: application/json\" \\\n -H \"secretKey: 你的密钥\" \\\n --max-time 300 \\\n -d '{\n \"imgUrls\": \"https://example.com/img1.jpg\"\n }'\n```\n\n**批量图片抠图：**\n\n```bash\ncurl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" \\\n -H \"Content-Type: application/json\" \\\n -H \"secretKey: 你的密钥\" \\\n --max-time 300 \\\n -d '{\n \"imgUrls\": \"https://example.com/img1.jpg,https://example.com/img2.jpg\"\n }'\n```\n\n## 常见错误及解决方案\n| 错误 | 原因与解决 |\n|------|-----------|\n| HTTP 401 / `code` 非 200 | `secretKey` 无效、缺失或已过期，确认请求头是否正确传入 |\n| HTTP 405 Not Allowed | 请求方法错误，必须使用 `POST` |\n| `imgUrls` 格式错误 | 该字段必须是字符串，多张图用英文逗号分隔，不是 JSON 数组 |\n| 图片 URL 无法访问 | 传入的链接不是公网直链、已过期，或源站限制访问 |\n| 抠图边缘效果不理想 | 原图主体与背景对比不足、边缘过于复杂，可换更清晰或背景更干净的源图 |\n| 请求超时 | 批量图片较多或源图较大时，可适当增大超时时间 |\n\n## 提示词处理\n该接口不接收自然语言提示词，不需要构造额外文案。\n\n执行时只需要：\n\n1. 收集一张或多张图片 URL\n2. 将多张 URL 用英文逗号拼接为 `imgUrls`\n3. 在请求头中传入 `secretKey`\n4. 调用接口并将返回的结果按逗号拆分后逐个展示\n\n当用户明确要求“透明底”“抠出主体”“去掉背景”时，优先使用此技能；如果用户真正想要的是“换背景”而不是“去背景”，则更适合使用场景替换或局部重绘类技能。\n\nFile v1.0.1:_meta.json\n\n{\n \"ownerId\": \"kn7fp1zsg4nwdq826y0awapkks84fkq1\",\n \"slug\": \"flyelep-ai-image-matting\",\n \"version\": \"1.0.1\",\n \"publishedAt\": 1777252431399\n}\n\nArchive v1.0.0: 2 files, 2414 bytes\n\nFiles: SKILL.md (4277b), _meta.json (143b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: ai-image-matting\ndescription: >-\n 通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。\n 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。\n---\n# Flyelep AI抠图\n通过 Flyelep AI Tool API 自动去除图片背景，并返回抠图后的新图片 URL。\n\n**重要：这是一个 HTTP API 调用技能。必须通过 HTTP POST 请求调用 API 接口，禁止通过浏览器访问 Flyelep 网站。**\n\n## API 接口信息\n- **URL**: `POST https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting`\n- **Content-Type**: `application/json`\n- **认证方式**: 在请求头中传入 `secretKey`\n- **超时时间**: 建议 120-300 秒\n\n## 认证方式\n所有 AI 工具接口均需在请求头中传入 `secretKey`。该密钥需由用户在 Flyelep 开放平台申请获得。\n\n请求头示例：\n\n```http\nContent-Type: application/json\nsecretKey: 用户提供的API密钥\n```\n\n> **安全说明**：`secretKey` 必须放在请求头中，这是 AI 工具接口的统一鉴权要求。不要将真实密钥写入技能文件、示例代码仓库或持久化配置中，应在运行时由用户动态提供。\n\n## 请求 Body\n```json\n{\n \"imgUrls\": \"https://example.com/img1.jpg,https://example.com/img2.jpg\"\n}\n```\n\n## 响应格式\n统一响应结构：\n\n```json\n{\n \"code\": 200,\n \"msg\": \"操作成功\",\n \"data\": \"https://example.com/matted1.png,https://example.com/matted2.png\"\n}\n```\n\n- `code=200` 表示调用成功\n- `msg` 为接口返回说明\n- `data` 为抠图后图片地址\n- 多张图片时，`data` 中多个 URL 以英文逗号 `,` 分隔\n\n返回结果应按逗号拆分后逐个展示给用户，不要回读图片内容。\n\n## 参数说明\n### 必传参数\n| 字段 | 默认值 | 说明 |\n|------|--------|------|\n| imgUrls | - | 图片链接字符串，多张时使用英文逗号分隔 |\n\n## 参数映射规则\n### imgUrls\n- 接口要求传字符串，不是数组\n- 单张图片时直接传一个 URL 字符串\n- 多张图片时，用英文逗号 `,` 按顺序拼接\n- 每个链接都应为公网可访问的图片直链，不要传网页地址\n\n### 结果格式\n- 抠图结果通常更适合返回透明背景图片\n- 文档示例中返回的是 `.png`，因此应优先预期结果为支持透明底的图片格式\n- 若接口实际返回其他格式，按接口返回值原样展示即可\n\n## 调用示例\n**单张图片抠图：**\n\n```bash\ncurl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" \\\n -H \"Content-Type: application/json\" \\\n -H \"secretKey: 你的密钥\" \\\n --max-time 300 \\\n -d '{\n \"imgUrls\": \"https://example.com/img1.jpg\"\n }'\n```\n\n**批量图片抠图：**\n\n```bash\ncurl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting\" \\\n -H \"Content-Type: application/json\" \\\n -H \"secretKey: 你的密钥\" \\\n --max-time 300 \\\n -d '{\n \"imgUrls\": \"https://example.com/img1.jpg,https://example.com/img2.jpg\"\n }'\n```\n\n## 常见错误及解决方案\n| 错误 | 原因与解决 |\n|------|-----------|\n| HTTP 401 / `code` 非 200 | `secretKey` 无效、缺失或已过期，确认请求头是否正确传入 |\n| HTTP 405 Not Allowed | 请求方法错误，必须使用 `POST` |\n| `imgUrls` 格式错误 | 该字段必须是字符串，多张图用英文逗号分隔，不是 JSON 数组 |\n| 图片 URL 无法访问 | 传入的链接不是公网直链、已过期，或源站限制访问 |\n| 抠图边缘效果不理想 | 原图主体与背景对比不足、边缘过于复杂，可换更清晰或背景更干净的源图 |\n| 请求超时 | 批量图片较多或源图较大时，可适当增大超时时间 |\n\n## 提示词处理\n该接口不接收自然语言提示词，不需要构造额外文案。\n\n执行时只需要：\n\n1. 收集一张或多张图片 URL\n2. 将多张 URL 用英文逗号拼接为 `imgUrls`\n3. 在请求头中传入 `secretKey`\n4. 调用接口并将返回的结果按逗号拆分后逐个展示\n\n当用户明确要求“透明底”“抠出主体”“去掉背景”时，优先使用此技能；如果用户真正想要的是“换背景”而不是“去背景”，则更适合使用场景替换或局部重绘类技能。\n\nFile v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn7fp1zsg4nwdq826y0awapkks84fkq1\",\n \"slug\": \"flyelep-ai-image-matting\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1776670250456\n}","readmeExcerpt":"Skill: AI-Image-Matting Owner: flyelepai Summary: 通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。 Tags: latest:1.0.4 Version history: v1.0.4 | 2026-08-28T03:14:20.887Z | user - Expanded documentation to include a \"本地文件上传\" section for handling local images by uploading them to obtain public URLs before processing. - Clarified authentication and file format requirements for both image background","codeSnippets":[],"executableExamples":[{"language":"http","snippet":"Content-Type: application/json\nsecretKey: 用户提供的API密钥"},{"language":"json","snippet":"{\n \"imgUrls\": \"https://example.com/img1.jpg,https://example.com/img2.jpg\"\n}"},{"language":"json","snippet":"{\n \"code\": 200,\n \"msg\": \"操作成功\",\n \"data\": \"https://example.com/matted1.png,https://example.com/matted2.png\"\n}"},{"language":"json","snippet":"{\n \"code\": 200,\n \"msg\": null,\n \"data\": {\n \"relativePath\": \"cos_ai_agent/2026-08-11/3f2a9c1b7d84e6f5a012.png\",\n \"fullPath\": \"https://agent-1404002717.cos.ap-guangzhou.myqcloud.com/cos_ai_agent/2026-08-11/3f2a9c1b7d84e6f5a012.png\",\n \"serviceProvider\": null\n }\n}"},{"language":"bash","snippet":"curl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload\" -H \"secretKey: 你的密钥\" --max-time 120 -F \"file=@./product.png\""},{"language":"bash","snippet":"# Windows/PowerShell（用 curl.exe，PowerShell 里的 curl 是 Invoke-WebRequest 的别名）\ncurl.exe -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload\" -H \"secretKey: 你的密钥\" --max-time 120 -F \"file=@C:/path/to/product.png\"\n\n# macOS/Linux\ncurl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload\" -H \"secretKey: 你的密钥\" --max-time 120 -F \"file=@./product.png\""}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: ai-image-matting\ndescription: >-\n 通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。\n 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。\n---\n# Flyelep AI抠图\n\n通过 Flyelep AI Tool API 自动去除图片背景，并返回抠图后的新图片 URL。\n\n**重要：这是一个 HTTP API 调用技能。必须通过 HTTP POST 请求调用 API 接口，禁止通过浏览器访问 Flyelep 网站。**\n\n## API 接口信息\n\n- **URL**: `POST https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting`\n- **Content-Type**: `application/json`\n- **认证方式**: 在请求头中传入 `secretKey`（密钥需由用户在 Flyelep 开放平台申请：https://www.flyelep.cn/controlboard）\n- **超时时间**: 建议 120-300 秒\n\n请求头示例：\n\n```http\nContent-Type: application/json\nsecretKey: 用户提供的API密钥\n```\n\n> **安全说明**：不要将真实密钥写入技能文件、示例代码仓库或持久化配置中，应在运行时由用户动态提供。\n\n## 请求 Body\n\n```json\n{\n \"imgUrls\": \"https://example.com/img1.jpg,https://example.com/img2.jpg\"\n}\n```\n\n## 响应格式\n\n```json\n{\n \"code\": 200,\n \"msg\": \"操作成功\",\n \"data\": \"https://example.com/matted1.png,https://example.com/matted2.png\"\n}\n```\n\n- `code=200` 表示调用成功\n- `msg` 为接口返回说明\n- `data` 为抠图后图片地址，多张时以英文逗号 `,` 分隔\n- 返回结果应按逗号拆分后逐个展示给用户，不要回读图片内容\n\n## 参数说明\n\n### 必传参数\n\n> **重要**：以下必传参数必须通过询问用户获取，agent 不可自行填写。调用本技能时，应先向用户列出必传参数与可选参数表格，由用户确认或提供后再执行。\n\n| 字段 | 默认值 | 说明 |\n|------|--------|------|\n| imgUrls | - | 图片链接字符串，多张时使用英文逗号分隔 |\n\n### 参数映射规则\n\n**imgUrls**：\n- 接口要求传字符串，不是数组\n- 单张图片直接传 URL 字符串；多张图片用英文逗号 `,` 拼接\n- 也可以改用 `imageUrl` 字段传单张图片，两者二选一；同时传时以 `imgUrls` 为准\n- 每个链接都应为公网可访问的图片直链\n- 如果用户提供本地文件路径，先按「本地文件上传」章节换取公网直链，再填入此参数\n\n**结果格式**：\n- 抠图结果通常为透明背景的 `.png` 图片\n- 若接口实际返回其他格式，按接口返回值原样展示即可\n\n## 本地文件上传\n\n用户提供的是本地文件路径而不是公网直链时，先把文件上传换取直链，再调用本接口。已安装 `file-upload` 技能时以该技能为准；未安装时按下面的说明直接调用上传接口。\n\n- **URL**: `POST https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload`\n- **请求方式**: `multipart/form-data`，文件字段名固定为 `file`，单次只能上传一个文件，多个文件并发调用多次\n- **认证方式**: 请求头传 `secretKey`，与本技能使用同一个密钥\n- **超时时间**: 图片建议 60-120 秒\n- **不要手动设置 `Content-Type` 请求头**，让 HTTP 客户端自动生成带 boundary 的值，手写会导致服务端解析失败\n- 图片仅支持 `bmp`、`gif`、`jpg`、`jpeg`、`png`，`webp` 需先转成 `png` 或 `jpg`；文件名必须带正确后缀，服务端靠它判断格式\n- 原文件名不会出现在 URL 里，中文名、空格、特殊字符都能直接上传，不需要提前改名\n- 上传不消耗算力，但服务端不做去重：同一个文件在一次任务里只上传一次，记下 `fullPath` 复用\n\n成功响应取 `data.fullPath` 作为公网直链，永久有效、不带签名：\n\n```json\n{\n \"code\": 200,\n \"msg\": null,\n \"data\": {\n \"relativePath\": \"cos_ai_agent/2026-08-11/3f2a9c1b7d84e6f5a012.png\",\n \"fullPath\": \"https://agent-1404002717.cos.ap-guangzhou.myqcloud.com/cos_ai_agent/2026-08-11/3f2a9c1b7d84e6f5a012.png\",\n \"serviceProvider\": null\n }\n}\n```\n\n判断成功只看 `code`，业务失败时 HTTP 状态码仍是 200，`code` 为 500 或 9999，原因在 `msg` 里。\n\n```bash\n# Windows/PowerShell（用 curl.exe，PowerShell 里的 curl 是 Invoke-WebRequest 的别名）\ncurl.exe -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload\" -H \"secretKey: 你的密钥\" --max-time 120 -F \"file=@C:/path/to/product.png\"\n\n# macOS/Linux\ncurl -X POST \"https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload\" -H \"secretKey: 你的密钥\" --max-time 120 -F \"file=@./product.png\"\n```\n\n图片入桶前会先过内容审核，审核不通过整个请求失败，需换图重试。拿到 `code=9999`、`msg` 为 `服务繁忙，请稍后再试` 时，先自查三项：是否漏了 `secretKey` 请求头、表单字段名是否为 `file`、文件是否超出服务端体积上限。密钥、格式、审核、体积类错误重试无效，只有网络超时、5xx 和存储类异常值得重试。\n\n## 调用示例\n\n> **跨平台调用说明**：\n>"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn7fp1zsg4nwdq826y0awapkks84fkq1\",\n \"slug\": \"flyelep-ai-image-matting\",\n \"version\": \"1.0.4\",\n \"publishedAt\": 1787886860887\n}"},{"path":"skill-card.md","content":"## Description:\n\nUses the Flyelep AI Tool API to remove image backgrounds for one or more public image URLs and return the resulting matted image URLs.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[flyelepai](https://clawhub.ai/user/flyelepai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to remove image backgrounds, extract product subjects, or generate transparent-background image assets through Flyelep's hosted API.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Local images may be uploaded to a third-party service and converted into permanent unsigned public URLs.\n\nMitigation: Use only images that are appropriate to send to Flyelep and expose through a public URL, or confirm deletion and access-control guarantees before processing sensitive material.\n\nRisk: API keys could be exposed if written into prompts, files, examples, or logs.\n\nMitigation: Provide the Flyelep secretKey only at runtime and avoid persisting it in skill files, temporary payloads, prompts, or logs.\n\nRisk: The security evidence flags the release as suspicious due to third-party upload behavior without a documented informed-consent step.\n\nMitigation: Review the upload behavior before installation and obtain user confirmation before processing private photos, identity documents, credentials, medical images, or confidential business material.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/flyelepai/skills/flyelep-ai-image-matting)\n- [Flyelep controlboard](https://www.flyelep.cn/controlboard)\n- [Flyelep image matting API endpoint](https://www.flyelep.cn/prod-api/poster-design/api/v1/poster/aiTool/aiImageMatting)\n- [Flyelep file upload API endpoint](https://www.flyelep.cn/prod-api/poster-design/api/v1/file/upload)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with JSON and shell command examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Returns one or more hosted matted image URLs from the Flyelep API.]\n\n## Skill Version(s):\n\n1.0.4 (source: server 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."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。 Skill: AI-Image-Matting Owner: flyelepai Summary: 通过 Flyelep AI 工具接口自动去除图片背景，支持单张或批量处理。 当用户要求抠图、去背景、提取商品主体、生成透明底素材时使用此技能。 Tags: latest:1.0.4 Version history: v1.0.4 | 2026-08-28T03:14:20.887Z | user - Expanded documentation to include a \"本地文件上传\" section for handling local images by uploading them to obtain public URLs before processing. - Clarified authentication and file format requirements for both image background","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":981,"uniquenessScore":54,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T01:02:52.969Z","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":"2026-10-11T01:02:52.969Z","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":"2026-10-11T03:56:36.502Z","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"}]}}}