{"id":"a0575f5f-f9e0-4fa5-9557-cb3b8e29501a","entityType":"agent","slug":"clawhub-juan-xin-cai-google-deep-research","name":"deep-research","canonicalUrl":"https://www.xpersona.co/agent/clawhub-juan-xin-cai-google-deep-research","canonicalPath":"/agent/clawhub-juan-xin-cai-google-deep-research","generatedAt":"2026-10-10T13:32:38.886Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T10:52:12.556Z","emptyReason":null},"description":"使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。 Skill: deep-research Owner: juan-xin-cai Summary: 使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-03-09T08:39:30.819Z | user - Clarifies dependency handling: now requires explicit use of the @google/genai NPM package and/or GOOGLE_GENAI_SDK_PATH; stops scanning multiple local c","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.5K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s176vmsw277cbmxftj2h1emcr183hbx1:google-deep-research","sourceUrl":"https://clawhub.ai/juan-xin-cai/google-deep-research","homepage":"https://clawhub.ai/juan-xin-cai/skills/google-deep-research","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/juan-xin-cai/google-deep-research","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/juan-xin-cai/skills/google-deep-research","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":63,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。 Skill: deep-research"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T10:52:12.556Z","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":"2026-10-10T10:52:12.556Z","emptyReason":null},"stars":null,"forks":null,"downloads":1484,"packageName":null,"latestVersion":"1.0.2","tractionLabel":"1.5K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T10:52:12.556Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T10:52:12.556Z","lastCrawledAt":"2026-10-10T10:52:12.556Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T10:52:12.556Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.2","createdAt":"2026-03-09T08:39:30.819Z","changelog":"- Clarifies dependency handling: now requires explicit use of the @google/genai NPM package and/or GOOGLE_GENAI_SDK_PATH; stops scanning multiple local config paths. - Sets GEMINI_API_KEY as the explicit and only way to provide API credentials; local file/config scan is no longer supported. - Adds OpenClaw metadata (primaryEnv, homepage) to the manifest. - Updates process instructions to ensure SDK path and API key are provided in a clear, auditable, and controlled way. - Improves clarity on security and avoids use of personal/dev machine paths or bundled SDKs.","fileCount":4,"zipByteSize":6304},{"version":"1.0.1","createdAt":"2026-03-09T07:21:52.408Z","changelog":"- 增强了 API Key 加载逻辑，优先使用环境变量，无需硬编码路径，同时兼容本地 OpenClaw 配置。 - 优化 Google GenAI SDK 的加载机制，支持多种路径自动发现，提高节点兼容性。 - 移除了开发者绝对路径说明，改为相对 skill 目录下脚本，便于跨环境部署。 - 更新错误处理，覆盖 SDK 路径和环境问题。 - 文档细化 API Key 获取步骤及运行环境兼容性说明。","fileCount":3,"zipByteSize":5612},{"version":"1.0.0","createdAt":"2026-03-09T06:05:38.127Z","changelog":"feat: publish deep research skill","fileCount":3,"zipByteSize":4575}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s176vmsw277cbmxftj2h1emcr183hbx1:google-deep-research","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-juan-xin-cai-google-deep-research/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-juan-xin-cai-google-deep-research/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-juan-xin-cai-google-deep-research/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-juan-xin-cai-google-deep-research/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-juan-xin-cai-google-deep-research/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-juan-xin-cai-google-deep-research/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T13:32:38.885Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-juan-xin-cai-google-deep-research/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-juan-xin-cai-google-deep-research/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-juan-xin-cai-google-deep-research/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-juan-xin-cai-google-deep-research/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":"2026-10-10T10:52:12.556Z","emptyReason":null},"readme":"Skill: deep-research\n\nOwner: juan-xin-cai\n\nSummary: 使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。\n\nTags: latest:1.0.2\n\nVersion history:\n\nv1.0.2 | 2026-03-09T08:39:30.819Z | user\n\n- Clarifies dependency handling: now requires explicit use of the @google/genai NPM package and/or GOOGLE_GENAI_SDK_PATH; stops scanning multiple local config paths.\n- Sets GEMINI_API_KEY as the explicit and only way to provide API credentials; local file/config scan is no longer supported.\n- Adds OpenClaw metadata (primaryEnv, homepage) to the manifest.\n- Updates process instructions to ensure SDK path and API key are provided in a clear, auditable, and controlled way.\n- Improves clarity on security and avoids use of personal/dev machine paths or bundled SDKs.\n\nv1.0.1 | 2026-03-09T07:21:52.408Z | user\n\n- 增强了 API Key 加载逻辑，优先使用环境变量，无需硬编码路径，同时兼容本地 OpenClaw 配置。\n- 优化 Google GenAI SDK 的加载机制，支持多种路径自动发现，提高节点兼容性。\n- 移除了开发者绝对路径说明，改为相对 skill 目录下脚本，便于跨环境部署。\n- 更新错误处理，覆盖 SDK 路径和环境问题。\n- 文档细化 API Key 获取步骤及运行环境兼容性说明。\n\nv1.0.0 | 2026-03-09T06:05:38.127Z | user\n\nfeat: publish deep research skill\n\nArchive index:\n\nArchive v1.0.2: 4 files, 6304 bytes\n\nFiles: deep-research.mjs (9107b), skill-card.md (1944b), SKILL.md (3430b), _meta.json (139b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: deep-research\ndescription: \"使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。\"\nmetadata:\n  openclaw:\n    primaryEnv: GEMINI_API_KEY\n    homepage: https://www.npmjs.com/package/@google/genai\n---\n\n# Deep Research Agent\n\n使用 Gemini Deep Research Pro 执行自主多步搜索-阅读-分析的深度研究，通常需要 5-20 分钟完成。\n\n## 依赖来源\n\n- 首选 SDK 来源：npm 包 `@google/genai`\n- 可选兼容模式：通过 `GOOGLE_GENAI_SDK_PATH` 显式指定一个本地 SDK 路径\n\n不要依赖某台开发机上的隐式 bundled SDK 路径，也不要在技能里写死个人机器目录。\n\n## 工作流程\n\n### 1. 确认研究主题\n\n- 与用户确认研究主题和范围\n- 如果话题模糊，帮助用户明确研究方向和关注点\n- 将用户需求转化为清晰的英文或中文研究查询\n\n### 2. 准备 API Key\n\n必须显式提供：\n\n```bash\nexport GEMINI_API_KEY=\"<api_key>\"\n```\n\n不要自动读取本地 `openclaw.json` 或扫描多个默认配置位置。发布型技能应让密钥来源保持明确、可审查、可控。\n\n### 3. 执行研究\n\n**提醒用户**：深度研究通常需要 5-20 分钟，请耐心等待。\n\n脚本与 `SKILL.md` 位于同一目录。执行时先把脚本路径解析为当前技能目录下的 `deep-research.mjs`，不要写死开发机绝对路径。\n\n运行脚本：\n\n```bash\nGEMINI_API_KEY=\"<api_key>\" node <skill-dir>/deep-research.mjs \"<研究主题>\"\n```\n\n可选参数：\n\n- `--timeout <seconds>` — 超时时间，默认 3600 秒（1 小时）\n- `--no-stream` — 使用轮询模式（如果流式出错可尝试）\n\n可选 SDK 路径覆盖：\n\n```bash\nGOOGLE_GENAI_SDK_PATH=\"/path/to/@google/genai/dist/node/index.mjs\" \\\nGEMINI_API_KEY=\"<api_key>\" \\\nnode <skill-dir>/deep-research.mjs \"<研究主题>\"\n```\n\n**重要**：由于研究耗时较长，使用 exec 工具时设置足够的超时时间（至少 1200 秒）。\n\n### 4. 后续追问\n\n研究完成后，脚本会输出 Interaction ID。如果用户需要追问或深入某个方面：\n\n```bash\nGEMINI_API_KEY=\"<api_key>\" node <skill-dir>/deep-research.mjs --follow-up <interaction_id> \"<追加问题>\"\n```\n\n### 5. 呈现结果\n\n- stdout 输出为 Markdown 格式的研究报告\n- 保持原始 Markdown 格式呈现给用户\n- 报告包含引用来源链接\n- 如果用户需要，可以将报告保存为文件\n\n## 输出说明\n\n- **stdout** — 最终研究报告（Markdown 格式）\n- **stderr** — 进度信息：\n  - 🔬 研究开始\n  - 📊 状态更新\n  - 💭 思考摘要（Agent 的中间思考过程）\n  - ✅ 研究完成 + 耗时\n  - 📎 Interaction ID（用于后续追问）\n\n## 错误处理\n\n| 退出码 | 含义 | 处理方式 |\n|--------|------|----------|\n| 0 | 成功 | 正常呈现报告 |\n| 1 | 参数错误 | 检查研究主题是否提供 |\n| 2 | 环境或 API 错误 | 检查 `GEMINI_API_KEY`、`@google/genai` 安装和配额 |\n| 3 | 超时 | 建议缩小研究范围或增加超时 |\n\n## 安全\n\n- 不要将 API Key 直接展示给用户\n- 使用环境变量传递 API Key，不要把真实密钥写进技能文件\n- 不要在未获用户确认前读取本地配置中的潜在密钥\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn7c2bjkpmjpv66zts0py6tt65814y9c\",\n  \"slug\": \"google-deep-research\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1773045570819\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nUses Gemini Deep Research Agent to run autonomous multi-step research and produce detailed Markdown reports with citations.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[juan-xin-cai](https://clawhub.ai/user/juan-xin-cai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent users use this skill to turn a research topic into a long-running Gemini Deep Research session, then present the resulting cited Markdown report and support follow-up questions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill requires a Gemini API key and sends research prompts to Gemini.\n\nMitigation: Use an approved Gemini API key and avoid submitting secrets or sensitive data unless that use is authorized.\n\nRisk: The optional GOOGLE_GENAI_SDK_PATH override can execute local JavaScript with the same environment as the skill, including access to the Gemini API key.\n\nMitigation: Prefer the default @google/genai package, or set GOOGLE_GENAI_SDK_PATH only to a fully trusted SDK file.\n\n## Reference(s):\n\n- [@google/genai NPM package](https://www.npmjs.com/package/@google/genai)\n- [ClawHub skill page](https://clawhub.ai/juan-xin-cai/skills/google-deep-research)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown report on stdout, with progress status and follow-up interaction ID on stderr]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Reports may include citation links; runs can be streamed or polled and may take 5-20 minutes.]\n\n## Skill Version(s):\n\n1.0.2 (source: 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 v1.0.1: 3 files, 5612 bytes\n\nFiles: deep-research.mjs (10660b), SKILL.md (3353b), _meta.json (139b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: deep-research\ndescription: \"使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。\"\n---\n\n# Deep Research Agent\n\n使用 Gemini Deep Research Pro 执行自主多步搜索-阅读-分析的深度研究，通常需要 5-20 分钟完成。\n\n## 工作流程\n\n### 1. 确认研究主题\n\n- 与用户确认研究主题和范围\n- 如果话题模糊，帮助用户明确研究方向和关注点\n- 将用户需求转化为清晰的英文或中文研究查询\n\n### 2. 准备 API Key\n\n优先使用环境变量：\n\n```bash\nexport GEMINI_API_KEY=\"<api_key>\"\n```\n\n如果当前环境没有显式设置 `GEMINI_API_KEY`，脚本会自动尝试从常见 OpenClaw 配置路径读取：\n\n- `OPENCLAW_CONFIG_PATH`\n- `${OPENCLAW_HOME:-~/.openclaw}/openclaw.json`\n\n当前脚本会优先查找：\n\n- `skills.entries.nano-banana-pro.apiKey`\n- `agents.defaults.memorySearch.remote.apiKey`\n\n### 3. 执行研究\n\n**提醒用户**：深度研究通常需要 5-20 分钟，请耐心等待。\n\n脚本与 `SKILL.md` 位于同一目录。执行时先把脚本路径解析为当前技能目录下的 `deep-research.mjs`，不要写死开发机绝对路径。\n\n运行脚本：\n\n```bash\nGEMINI_API_KEY=\"<api_key>\" node <skill-dir>/deep-research.mjs \"<研究主题>\"\n```\n\n可选参数：\n\n- `--timeout <seconds>` — 超时时间，默认 3600 秒（1 小时）\n- `--no-stream` — 使用轮询模式（如果流式出错可尝试）\n\n**重要**：由于研究耗时较长，使用 exec 工具时设置足够的超时时间（至少 1200 秒）。\n\n### 4. 后续追问\n\n研究完成后，脚本会输出 Interaction ID。如果用户需要追问或深入某个方面：\n\n```bash\nGEMINI_API_KEY=\"<api_key>\" node <skill-dir>/deep-research.mjs --follow-up <interaction_id> \"<追加问题>\"\n```\n\n### 5. 呈现结果\n\n- stdout 输出为 Markdown 格式的研究报告\n- 保持原始 Markdown 格式呈现给用户\n- 报告包含引用来源链接\n- 如果用户需要，可以将报告保存为文件\n\n## 运行时兼容性\n\n脚本会按以下顺序尝试加载 Google GenAI SDK：\n\n1. `GOOGLE_GENAI_SDK_PATH`\n2. 直接导入 `@google/genai`\n3. `${OPENCLAW_HOME:-~/.openclaw}/extensions/mqtt/node_modules/@google/genai/dist/node/index.mjs`\n\n这让技能既能在通用 Node.js 环境中运行，也能在典型 OpenClaw 安装里运行，而不依赖某个开发者机器上的绝对路径。\n\n## 输出说明\n\n- **stdout** — 最终研究报告（Markdown 格式）\n- **stderr** — 进度信息：\n  - 🔬 研究开始\n  - 📊 状态更新\n  - 💭 思考摘要（Agent 的中间思考过程）\n  - ✅ 研究完成 + 耗时\n  - 📎 Interaction ID（用于后续追问）\n\n## 错误处理\n\n| 退出码 | 含义 | 处理方式 |\n|--------|------|----------|\n| 0 | 成功 | 正常呈现报告 |\n| 1 | 参数错误 | 检查研究主题是否提供 |\n| 2 | 环境或 API 错误 | 检查 API Key、SDK 路径和配额 |\n| 3 | 超时 | 建议缩小研究范围或增加超时 |\n\n## 安全\n\n- 不要将 API Key 直接展示给用户\n- 使用环境变量或本地配置读取 API Key，不要把真实密钥写进技能文件\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn7c2bjkpmjpv66zts0py6tt65814y9c\",\n  \"slug\": \"google-deep-research\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1773040912408\n}\n\nArchive v1.0.0: 3 files, 4575 bytes\n\nFiles: deep-research.mjs (8019b), SKILL.md (2928b), _meta.json (139b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: deep-research\ndescription: \"使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。\"\n---\n\n# Deep Research Agent\n\n使用 Gemini Deep Research Pro 执行自主多步搜索-阅读-分析的深度研究，通常需要 5-20 分钟完成。\n\n## 工作流程\n\n### 1. 确认研究主题\n\n- 与用户确认研究主题和范围\n- 如果话题模糊，帮助用户明确研究方向和关注点\n- 将用户需求转化为清晰的英文或中文研究查询\n\n### 2. 获取 API Key\n\n从 `openclaw.json` 配置中读取 Gemini API Key：\n\n```bash\n# 路径：skills.entries.nano-banana-pro.apiKey\n# 或：agents.defaults.memorySearch.remote.apiKey\n```\n\n使用 `exec` 工具从配置文件提取：\n```bash\nnode -e \"const c=JSON.parse(require('fs').readFileSync('/Users/feifei/.openclaw/openclaw.json','utf8')); console.log(c.skills?.entries?.['nano-banana-pro']?.apiKey || c.agents?.defaults?.memorySearch?.remote?.apiKey || '')\"\n```\n\n### 3. 执行研究\n\n**提醒用户**：深度研究通常需要 5-20 分钟，请耐心等待。\n\n运行脚本：\n```bash\nGEMINI_API_KEY=\"<api_key>\" node /Users/feifei/.openclaw/workspace/skills/deep-research/deep-research.mjs \"<研究主题>\"\n```\n\n可选参数：\n- `--timeout <seconds>` — 超时时间，默认 3600 秒（1 小时）\n- `--no-stream` — 使用轮询模式（如果流式出错可尝试）\n\n**重要**：由于研究耗时较长，使用 exec 工具时设置足够的超时时间（至少 1200 秒）。\n\n### 4. 后续追问\n\n研究完成后，脚本会输出 Interaction ID。如果用户需要追问或深入某个方面：\n\n```bash\nGEMINI_API_KEY=\"<api_key>\" node /Users/feifei/.openclaw/workspace/skills/deep-research/deep-research.mjs --follow-up <interaction_id> \"<追加问题>\"\n```\n\n### 5. 呈现结果\n\n- stdout 输出为 Markdown 格式的研究报告\n- 保持原始 Markdown 格式呈现给用户\n- 报告包含引用来源链接\n- 如果用户需要，可以将报告保存为文件\n\n## 输出说明\n\n- **stdout** — 最终研究报告（Markdown 格式）\n- **stderr** — 进度信息：\n  - 🔬 研究开始\n  - 📊 状态更新\n  - 💭 思考摘要（Agent 的中间思考过程）\n  - ✅ 研究完成 + 耗时\n  - 📎 Interaction ID（用于后续追问）\n\n## 错误处理\n\n| 退出码 | 含义 | 处理方式 |\n|--------|------|----------|\n| 0 | 成功 | 正常呈现报告 |\n| 1 | 参数错误 | 检查研究主题是否提供 |\n| 2 | API 错误 | 检查 API Key 是否有效，提示用户检查配额 |\n| 3 | 超时 | 建议缩小研究范围或增加超时 |\n\n## 安全\n\n- 不要将 API Key 直接展示给用户\n- 使用环境变量传递 API Key，不要硬编码在命令中显示\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn7c2bjkpmjpv66zts0py6tt65814y9c\",\n  \"slug\": \"google-deep-research\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1773036338127\n}","readmeExcerpt":"Skill: deep-research Owner: juan-xin-cai Summary: 使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-03-09T08:39:30.819Z | user - Clarifies dependency handling: now requires explicit use of the @google/genai NPM package and/or GOOGLE_GENAI_SDK_PATH; stops scanning multiple local c","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"export GEMINI_API_KEY=\"<api_key>\""},{"language":"bash","snippet":"GEMINI_API_KEY=\"<api_key>\" node <skill-dir>/deep-research.mjs \"<研究主题>\""},{"language":"bash","snippet":"GOOGLE_GENAI_SDK_PATH=\"/path/to/@google/genai/dist/node/index.mjs\" \\\nGEMINI_API_KEY=\"<api_key>\" \\\nnode <skill-dir>/deep-research.mjs \"<研究主题>\""},{"language":"bash","snippet":"GEMINI_API_KEY=\"<api_key>\" node <skill-dir>/deep-research.mjs --follow-up <interaction_id> \"<追加问题>\""},{"language":"bash","snippet":"export GEMINI_API_KEY=\"<api_key>\""},{"language":"bash","snippet":"GEMINI_API_KEY=\"<api_key>\" node <skill-dir>/deep-research.mjs \"<研究主题>\""}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: deep-research\ndescription: \"使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。\"\nmetadata:\n  openclaw:\n    primaryEnv: GEMINI_API_KEY\n    homepage: https://www.npmjs.com/package/@google/genai\n---\n\n# Deep Research Agent\n\n使用 Gemini Deep Research Pro 执行自主多步搜索-阅读-分析的深度研究，通常需要 5-20 分钟完成。\n\n## 依赖来源\n\n- 首选 SDK 来源：npm 包 `@google/genai`\n- 可选兼容模式：通过 `GOOGLE_GENAI_SDK_PATH` 显式指定一个本地 SDK 路径\n\n不要依赖某台开发机上的隐式 bundled SDK 路径，也不要在技能里写死个人机器目录。\n\n## 工作流程\n\n### 1. 确认研究主题\n\n- 与用户确认研究主题和范围\n- 如果话题模糊，帮助用户明确研究方向和关注点\n- 将用户需求转化为清晰的英文或中文研究查询\n\n### 2. 准备 API Key\n\n必须显式提供：\n\n```bash\nexport GEMINI_API_KEY=\"<api_key>\"\n```\n\n不要自动读取本地 `openclaw.json` 或扫描多个默认配置位置。发布型技能应让密钥来源保持明确、可审查、可控。\n\n### 3. 执行研究\n\n**提醒用户**：深度研究通常需要 5-20 分钟，请耐心等待。\n\n脚本与 `SKILL.md` 位于同一目录。执行时先把脚本路径解析为当前技能目录下的 `deep-research.mjs`，不要写死开发机绝对路径。\n\n运行脚本：\n\n```bash\nGEMINI_API_KEY=\"<api_key>\" node <skill-dir>/deep-research.mjs \"<研究主题>\"\n```\n\n可选参数：\n\n- `--timeout <seconds>` — 超时时间，默认 3600 秒（1 小时）\n- `--no-stream` — 使用轮询模式（如果流式出错可尝试）\n\n可选 SDK 路径覆盖：\n\n```bash\nGOOGLE_GENAI_SDK_PATH=\"/path/to/@google/genai/dist/node/index.mjs\" \\\nGEMINI_API_KEY=\"<api_key>\" \\\nnode <skill-dir>/deep-research.mjs \"<研究主题>\"\n```\n\n**重要**：由于研究耗时较长，使用 exec 工具时设置足够的超时时间（至少 1200 秒）。\n\n### 4. 后续追问\n\n研究完成后，脚本会输出 Interaction ID。如果用户需要追问或深入某个方面：\n\n```bash\nGEMINI_API_KEY=\"<api_key>\" node <skill-dir>/deep-research.mjs --follow-up <interaction_id> \"<追加问题>\"\n```\n\n### 5. 呈现结果\n\n- stdout 输出为 Markdown 格式的研究报告\n- 保持原始 Markdown 格式呈现给用户\n- 报告包含引用来源链接\n- 如果用户需要，可以将报告保存为文件\n\n## 输出说明\n\n- **stdout** — 最终研究报告（Markdown 格式）\n- **stderr** — 进度信息：\n  - 🔬 研究开始\n  - 📊 状态更新\n  - 💭 思考摘要（Agent 的中间思考过程）\n  - ✅ 研究完成 + 耗时\n  - 📎 Interaction ID（用于后续追问）\n\n## 错误处理\n\n| 退出码 | 含义 | 处理方式 |\n|--------|------|----------|\n| 0 | 成功 | 正常呈现报告 |\n| 1 | 参数错误 | 检查研究主题是否提供 |\n| 2 | 环境或 API 错误 | 检查 `GEMINI_API_KEY`、`@google/genai` 安装和配额 |\n| 3 | 超时 | 建议缩小研究范围或增加超时 |\n\n## 安全\n\n- 不要将 API Key 直接展示给用户\n- 使用环境变量传递 API Key，不要把真实密钥写进技能文件\n- 不要在未获用户确认前读取本地配置中的潜在密钥"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7c2bjkpmjpv66zts0py6tt65814y9c\",\n  \"slug\": \"google-deep-research\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1773045570819\n}"},{"path":"skill-card.md","content":"## Description:\n\nUses Gemini Deep Research Agent to run autonomous multi-step research and produce detailed Markdown reports with citations.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[juan-xin-cai](https://clawhub.ai/user/juan-xin-cai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and agent users use this skill to turn a research topic into a long-running Gemini Deep Research session, then present the resulting cited Markdown report and support follow-up questions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill requires a Gemini API key and sends research prompts to Gemini.\n\nMitigation: Use an approved Gemini API key and avoid submitting secrets or sensitive data unless that use is authorized.\n\nRisk: The optional GOOGLE_GENAI_SDK_PATH override can execute local JavaScript with the same environment as the skill, including access to the Gemini API key.\n\nMitigation: Prefer the default @google/genai package, or set GOOGLE_GENAI_SDK_PATH only to a fully trusted SDK file.\n\n## Reference(s):\n\n- [@google/genai NPM package](https://www.npmjs.com/package/@google/genai)\n- [ClawHub skill page](https://clawhub.ai/juan-xin-cai/skills/google-deep-research)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown report on stdout, with progress status and follow-up interaction ID on stderr]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Reports may include citation links; runs can be streamed or polled and may take 5-20 minutes.]\n\n## Skill Version(s):\n\n1.0.2 (source: 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":"使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。 Skill: deep-research Owner: juan-xin-cai Summary: 使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。 Tags: latest:1.0.2 Version history: v1.0.2 | 2026-03-09T08:39:30.819Z | user - Clarifies dependency handling: now requires explicit use of the @google/genai NPM package and/or GOOGLE_GENAI_SDK_PATH; stops scanning multiple local c","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":811,"uniquenessScore":56,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T10:52:12.556Z","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":"2026-10-10T10:52:12.556Z","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":"2026-10-10T13:32:38.886Z","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"}]}}}