{"id":"18f4144f-22f4-4a69-bd12-cc91df43c2ee","entityType":"agent","slug":"clawhub-dataify-server-dataify-tiktok-comment-by-url","name":"Dataify Tiktok Builder","canonicalUrl":"https://www.xpersona.co/agent/clawhub-dataify-server-dataify-tiktok-comment-by-url","canonicalPath":"/agent/clawhub-dataify-server-dataify-tiktok-comment-by-url","generatedAt":"2026-10-11T20:56:10.172Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:09:29.872Z","emptyReason":null},"description":"Collect Tiktok Builder data and return results","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17feed8b2qc486skqmjapxmjs86bd4f:dataify-tiktok-comment-by-url","sourceUrl":"https://clawhub.ai/dataify-server/dataify-tiktok-comment-by-url","homepage":"https://clawhub.ai/dataify-server/skills/dataify-tiktok-comment-by-url","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/dataify-server/dataify-tiktok-comment-by-url","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/dataify-server/skills/dataify-tiktok-comment-by-url","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Dataify Tiktok Builder technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:09:29.872Z","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":"2026-10-11T16:09:29.872Z","emptyReason":null},"stars":null,"forks":null,"downloads":1031,"packageName":null,"latestVersion":"1.3.1","tractionLabel":"1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:09:29.810Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T16:09:29.872Z","lastCrawledAt":"2026-10-11T16:09:29.810Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T16:09:29.810Z","lastVerifiedAt":null,"highlights":[{"version":"1.3.1","createdAt":"2026-09-08T06:18:54.122Z","changelog":"Fix natural-language usage failures: validate required targets and URLs, preserve catalog references, default Amazon region safely, normalize Google News links, and improve UTF-8 error output.","fileCount":14,"zipByteSize":30722},{"version":"1.3.0","createdAt":"2026-09-01T09:15:26.554Z","changelog":"默认返回最终采集结果，完善异步等待下载与安全恢复；修复空目标误执行、Quick Start、Token 配置和触发路由冲突，并补齐发布前自动化测试","fileCount":8,"zipByteSize":9709},{"version":"1.2.0","createdAt":"2026-07-16T08:38:48.137Z","changelog":"新增能力路由与异步任务闭环，修复失效引用、Token 泄漏和 Skill 元数据兼容性","fileCount":8,"zipByteSize":8053},{"version":"1.1.0","createdAt":"2026-06-08T02:07:37.615Z","changelog":"补全中文文档，更新目录结构","fileCount":6,"zipByteSize":7348},{"version":"1.0.0","createdAt":"2026-06-01T01:17:35.869Z","changelog":"Initial release of Dataify TikTok comment builder integration. - Guides users through preparing Dataify builder requests for TikTok scraper tools, supporting both Python and PowerShell scripts. - Lets users choose from a list of Chinese-labeled scraper tools and handles all parameter prompting, including select options with Chinese labels. - Generates the required curl POST command for scraperapi.dataify.com/builder, using the environment's DATAIFY_API_TOKEN. - Supports batch/multi-row parameter input, correctly zipping multi-value parameters. - Provides detailed instructions for environment variable setup for Windows and Unix systems. - Reads saved tool options from references/tool-params.json and ensures correct mapping to final request fields.","fileCount":6,"zipByteSize":7124}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17feed8b2qc486skqmjapxmjs86bd4f:dataify-tiktok-comment-by-url","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s17feed8b2qc486skqmjapxmjs86bd4f:dataify-tiktok-comment-by-url` 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/dataify-server/dataify-tiktok-comment-by-url 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-dataify-server-dataify-tiktok-comment-by-url/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dataify-server-dataify-tiktok-comment-by-url/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dataify-server-dataify-tiktok-comment-by-url/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dataify-server-dataify-tiktok-comment-by-url/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dataify-server-dataify-tiktok-comment-by-url/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-dataify-server-dataify-tiktok-comment-by-url/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T20:56:10.170Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dataify-server-dataify-tiktok-comment-by-url/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dataify-server-dataify-tiktok-comment-by-url/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dataify-server-dataify-tiktok-comment-by-url/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-dataify-server-dataify-tiktok-comment-by-url/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":"2026-10-11T16:09:29.872Z","emptyReason":null},"readme":"Skill: Dataify Tiktok Builder\n\nOwner: dataify-server\n\nSummary: Collect Tiktok Builder data and return results\n\nTags: latest:1.3.1\n\nVersion history:\n\nv1.3.1 | 2026-09-08T06:18:54.122Z | user\n\nFix natural-language usage failures: validate required targets and URLs, preserve catalog references, default Amazon region safely, normalize Google News links, and improve UTF-8 error output.\n\nv1.3.0 | 2026-09-01T09:15:26.554Z | user\n\n默认返回最终采集结果，完善异步等待下载与安全恢复；修复空目标误执行、Quick Start、Token 配置和触发路由冲突，并补齐发布前自动化测试\n\nv1.2.0 | 2026-07-16T08:38:48.137Z | user\n\n新增能力路由与异步任务闭环，修复失效引用、Token 泄漏和 Skill 元数据兼容性\n\nv1.1.0 | 2026-06-08T02:07:37.615Z | user\n\n补全中文文档，更新目录结构\n\nv1.0.0 | 2026-06-01T01:17:35.869Z | auto\n\nInitial release of Dataify TikTok comment builder integration.\n\n- Guides users through preparing Dataify builder requests for TikTok scraper tools, supporting both Python and PowerShell scripts.\n- Lets users choose from a list of Chinese-labeled scraper tools and handles all parameter prompting, including select options with Chinese labels.\n- Generates the required curl POST command for scraperapi.dataify.com/builder, using the environment's DATAIFY_API_TOKEN.\n- Supports batch/multi-row parameter input, correctly zipping multi-value parameters.\n- Provides detailed instructions for environment variable setup for Windows and Unix systems.\n- Reads saved tool options from references/tool-params.json and ensures correct mapping to final request fields.\n\nArchive index:\n\nArchive v1.3.1: 14 files, 30722 bytes\n\nFiles: agents/openai.yaml (370b), references/tool-params.json (1177b), scripts/build-dataify-request.ps1 (294b), scripts/build-dataify-request.py (730b), scripts/business_workflow.py (34775b), scripts/catalog_builder.py (7013b), scripts/dataify_client.py (6994b), scripts/task_runtime.py (2259b), scripts/token_setup.py (2585b), scripts/wait_for_task.py (8879b), skill-card.md (2537b), SKILL.md (8296b), SKILL.zh-CN.md (6463b), _meta.json (148b)\n\nFile v1.3.1:SKILL.md\n\n---\nname: \"dataify-tiktok-comment-by-url\"\ndescription: \"Collect TikTok comments from a known TikTok content URL. Do not use for video download, profile collection, or general TikTok discovery.\"\n---\n\n# Dataify Builder Skill\n\nUse this skill to prepare Dataify builder requests for the scraper family rooted at `tiktok_comment_by-url` on `tiktok.com`.\n\n## Workflow\n\n1. Check whether `DATAIFY_API_TOKEN` exists in the environment.\n2. If the token is missing, stop and tell the user: `Dataify requires an API token. New accounts get 50 free credits, enough for about 6,000 trial results, valid for 7 days, and only successful requests are billed. Once registration is complete, tell me and I'll continue the current task.`.\n3. Ask the user to choose exactly one tool from the following Chinese list:\n- 通过URL采集 (tiktok_comment_by-url)\n- 通过URL采集 (tiktok_shop_by-url)\n- 通过列表URL采集 (tiktok_posts_by-listurl)\n- 通过URL采集 (tiktok_profiles_by-url)\n- 通过搜索网址采集 (tiktok_profiles_by-listurl)\n4. Read `references/tool-params.json` and find the chosen tool by `tool_sign` or Chinese tool name.\n5. For each parameter in the chosen tool:\n - If `input_mode` is `user_input`, ask the user for the value.\n - If `input_mode` is `select`, present the saved options to the user.\n6. Use `scripts/build-dataify-request.py` as the default cross-platform helper.\n7. Use `scripts/build-dataify-request.ps1` as the Windows PowerShell helper when needed.\n8. When a selectable parameter has a human-readable Chinese label, keep that label in `spider_parameters`. Do not replace it with a code such as `HK` unless the user explicitly asks for the coded value.\n9. Build `spider_parameters` as a JSON array.\n10. If every parameter has only one final value, build one object such as `[{\"searchurl\":\"...\",\"country\":\"Hong Kong\"}]`.\n11. If one or more parameters have multiple aligned values, zip them by index and build one object per row. Example: `[{\"search_url\":\"url1\",\"page_turning\":\"1\",\"max_num\":\"15\"},{\"search_url\":\"url2\",\"page_turning\":\"1\",\"max_num\":\"15\"}]`.\n12. If a parameter has one value while another parameter has multiple values, reuse the single value across every generated row.\n13. Set `spider_name` to `tiktok.com`.\n14. Set `spider_id` to the selected tool's `tool_sign`.\n15. Always include `spider_errors=true` and `file_name={{TasksID}}`.\n16. Return a curl command for `https://scraperapi.dataify.com/builder`.\n\n## Set DATAIFY_API_TOKEN\n\nPrefer a permanent environment-variable setup instead of setting the token only for the current terminal session.\n\nWindows PowerShell, permanent for the current user:\n```powershell\n[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")\n```\n\nThen reopen PowerShell. If the current session also needs the token immediately, run:\n```powershell\n$env:DATAIFY_API_TOKEN = \"your_token_here\"\n```\n\nmacOS or Linux, permanent for bash:\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\nmacOS or Linux, permanent for zsh:\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.zshrc\nsource ~/.zshrc\n```\n\n## Script usage\n\nPython:\n```bash\npython scripts/build-dataify-request.py --tool-sign --values-file values.json\n```\n\nPowerShell:\n```powershell\n& \".\\scripts\\build-dataify-request.ps1\" -ToolSign \"\" -ValuesFile \".\\values.json\"\n```\n\nThe `values.json` file should contain either one object or an array of objects. Example:\n```json\n[{\"searchurl\":\"https://www.airbnb.com/s/Greece/homes?...\",\"country\":\"Hong Kong\"}]\n```\n\n## Required output shape\n\nGenerate a curl command in this form:\n\n```bash\ncurl -X POST 'https://scraperapi.dataify.com/builder' \\\n -H \"Authorization: Bearer $DATAIFY_API_TOKEN\" \\\n -H 'Content-Type: application/x-www-form-urlencoded' \\\n -d 'spider_name=tiktok.com' \\\n -d 'spider_id=' \\\n -d 'spider_parameters=[{\"param\":\"value\"}]' \\\n -d 'spider_errors=true' \\\n -d 'file_name={{TasksID}}'\n```\n\n## Reference usage\n\n- `references/tool-params.json` stores the full saved parameter catalog for every available tool in this scraper family.\n- `scripts/build-dataify-request.py` is the portable implementation and should be preferred.\n- `scripts/build-dataify-request.ps1` mirrors the same behavior for Windows users.\n- If a parameter has no options, the user must provide the value.\n- Do not assume `spider_parameters` always contains exactly one object. Multi-value tools may require multiple objects zipped by index.\n- Use the saved `url_example` only as a reference example. Do not assume the user wants the example values unless they explicitly confirm them.\n\n## Default completion behavior\n\nThe default deliverable is the collected result, not only a `task_id`.\n\n1. Submit the Builder task once and capture its `task_id`.\n2. Immediately continue with `$dataify-task-operations` and monitor the same task ID.\n - Use the default 600-second wait for ordinary collections.\n - Use `--timeout 1800` for media downloads or clearly high-volume, multi-page, or multi-input collections.\n3. When the task succeeds, download and return the final JSON result. Summarize large payloads while preserving access to the raw result.\n4. If monitoring times out or is interrupted, return the task ID and a resume command. Do not resubmit the paid task.\n5. Stop after submission only when the user explicitly asks for submission only, a task ID, or `--no-wait` behavior.\n\n## Quick Start\n\n```bash\npython3 scripts/build-dataify-request.py --help\n```\n\n## Parameter interaction policy\n\n- For a clear, low-risk, read-only, and low-cost request, apply safe defaults and execute immediately. A short execution summary is optional; do not pause for confirmation.\n- Ask only for a missing required input, a material ambiguity, a high-volume or multi-page scope, a media download, a choice that materially changes credit usage, an irreversible action, or an explicit user request to review parameters.\n- When confirmation is required, show only user-facing values that affect the target, scope, output, or cost. Prefer one concise sentence; use a compact table only when three or more consequential values are easier to compare.\n- Never show fixed fields, empty optional fields, unchanged defaults, credentials, or internal implementation parameters such as engine selectors, response-format flags, offsets, spider IDs, and file-name templates.\n- Keep advanced filters hidden unless the user asks for them or they are needed to resolve ambiguity. Never substitute documentation example values for missing required user input.\n- After returning results, offer relevant refinements instead of forcing all optional decisions before the first result.\n\n## Account CTA policy\n\n- Show a prominent Dataify account CTA only when the API token is missing, rejected/invalid, or the account has insufficient credits.\n- For a missing token, offer https://dashboard.dataify.com/login?utm_source=skill and state: New accounts get 50 free credits, enough for about 6,000 trial results, valid for 7 days, and only successful requests are billed. Never ask the user to paste the token into chat.\n- Detect the current operating system and shell. Show only the matching session-scoped setup command first (`export` for macOS/Linux shells, `$env:` for Windows PowerShell, or `set` for Windows Command Prompt). Show other platforms or persistent setup only when detection is ambiguous or the user asks.\n- After the user says the token is configured, verify only whether `DATAIFY_API_TOKEN` is present; never print its value. If verification succeeds, continue the original task without asking the user to repeat it.\n- Explain that persistent shell changes may require a new terminal or restarting the agent application. Do not recommend a project `.env` unless the execution path explicitly loads it, and ensure `.env` is ignored by version control.\n- For an invalid token, direct the user to API-key management without implying that a new registration is required. For insufficient credits, direct the user to balance or recharge management.\n- During normal submission, processing, and successful completion, do not promote registration or the Dashboard. Never expose the token or include it in CTA attribution parameters.\n\nFile v1.3.1:_meta.json\n\n{\n \"ownerId\": \"kn74z5hmmwk21kw8tpphd9w21x86bkdf\",\n \"slug\": \"dataify-tiktok-comment-by-url\",\n \"version\": \"1.3.1\",\n \"publishedAt\": 1788848334122\n}\n\nFile v1.3.1:references/tool-params.json\n\n[{\"tool_name_cn\":\"评论URL\",\"tool_sign\":\"tiktok_comment_by-url\",\"spider_name\":\"tiktok.com\",\"params\":[{\"param\":\"url\",\"required\":true,\"input_mode\":\"user_input\",\"format\":\"url\",\"url_example\":\"https://www.tiktok.com/@user/video/1234567890\"}]},{\"tool_name_cn\":\"店铺URL\",\"tool_sign\":\"tiktok_shop_by-url\",\"spider_name\":\"tiktok.com\",\"params\":[{\"param\":\"url\",\"required\":true,\"input_mode\":\"user_input\",\"format\":\"url\",\"url_example\":\"https://www.tiktok.com/@shop\"}]},{\"tool_name_cn\":\"帖子列表URL\",\"tool_sign\":\"tiktok_posts_by-listurl\",\"spider_name\":\"tiktok.com\",\"params\":[{\"param\":\"listurl\",\"required\":true,\"input_mode\":\"user_input\",\"format\":\"url\",\"url_example\":\"https://www.tiktok.com/@user\"}]},{\"tool_name_cn\":\"个人资料URL\",\"tool_sign\":\"tiktok_profiles_by-url\",\"spider_name\":\"tiktok.com\",\"params\":[{\"param\":\"url\",\"required\":true,\"input_mode\":\"user_input\",\"format\":\"url\",\"url_example\":\"https://www.tiktok.com/@user\"}]},{\"tool_name_cn\":\"个人资料列表URL\",\"tool_sign\":\"tiktok_profiles_by-listurl\",\"spider_name\":\"tiktok.com\",\"params\":[{\"param\":\"listurl\",\"required\":true,\"input_mode\":\"user_input\",\"format\":\"url\",\"url_example\":\"https://www.tiktok.com/search/user?q=creator\"}]}]\n\nFile v1.3.1:skill-card.md\n\n## Description:\n\nCollect TikTok comments from a known TikTok content URL. Do not use for video download, profile collection, or general TikTok discovery.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dataify-server](https://clawhub.ai/user/dataify-server)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to prepare and optionally submit Dataify scraper requests for TikTok comment collection from a known content URL, then monitor the asynchronous task and return JSON results.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The artifact catalog exposes broader TikTok profile, shop, and post collection beyond the declared comment-by-URL task.\n\nMitigation: Narrow the catalog to the declared comment-by-URL task or require explicit tool selection review before execution.\n\nRisk: Credential setup guidance and helper scripts involve DATAIFY_API_TOKEN handling.\n\nMitigation: Use environment or secret-management controls, never paste or commit tokens, and verify only token presence rather than printing token values.\n\nRisk: Submitting Dataify tasks may spend credits and may collect profile-level data when broader tools are selected.\n\nMitigation: Require explicit confirmation before submissions that may spend credits, use high-volume settings, or collect profile-level data.\n\nRisk: Generated curl commands and task IDs can expose sensitive task access details.\n\nMitigation: Treat generated commands, task IDs, and result files as sensitive and avoid sharing them in public logs or tickets.\n\n## Reference(s):\n\n- [Tool parameter catalog](references/tool-params.json)\n- [ClawHub skill page](https://clawhub.ai/dataify-server/skills/dataify-tiktok-comment-by-url)\n- [Dataify Builder endpoint](https://scraperapi.dataify.com/builder)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, JSON, Code, Configuration instructions, Guidance]\n\n**Output Format:** [Markdown with inline shell commands and JSON results]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires DATAIFY_API_TOKEN; generated curl commands, task IDs, and returned data should be treated as sensitive.]\n\n## Skill Version(s):\n\n1.3.1 (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\nFile v1.3.1:SKILL.zh-CN.md\n\n---\nname: \"dataify-tiktok-comment-by-url\"\ndescription: \"为 tiktok.com 上以 tiktok_comment_by-url 为根的 scraper 系列准备 Dataify builder 请求。当需要处理成功的 Dataify scraper detail 条目 tiktok_comment_by-url、让用户选择可用工具、读取已保存的 getToolParams 选项，并使用 DATAIFY_API_TOKEN 生成 scraperapi.dataify.com/builder curl 请求时，使用此 skill。\"\n---\n\n# Dataify Builder Skill 中文版\n\n这个 skill 用于为 `tiktok.com` 下、以 `tiktok_comment_by-url` 为入口的 Dataify scraper 工具族生成 builder 请求。\n\n## 工作流程\n\n1. 先检查环境变量中是否存在 `DATAIFY_API_TOKEN`。\n2. 如果 token 缺失，告诉用户：`Dataify 需要 API Token。新账号注册即得 50 免费积分，约可获得 6000 条试用结果，7 天有效，仅成功请求计费。注册完成后告诉我，我会继续当前任务。`。\n3. 先让用户从下面的中文工具列表中明确选择一个工具：\n- 通过URL采集 (tiktok_comment_by-url)\n- 通过URL采集 (tiktok_shop_by-url)\n- 通过列表URL采集 (tiktok_posts_by-listurl)\n- 通过URL采集 (tiktok_profiles_by-url)\n- 通过搜索网址采集 (tiktok_profiles_by-listurl)\n4. 再读取 `references/tool-params.json`，根据 `tool_sign` 或中文工具名找到对应工具。\n5. 对所选工具的每个参数分别处理：\n - 如果 `input_mode` 是 `user_input`，让用户提供值。\n - 如果 `input_mode` 是 `select`，把已保存的可选项展示给用户，让用户选择。\n6. 默认优先使用 `scripts/build-dataify-request.py`，因为它是跨平台版本。\n7. Windows 下也可以使用 `scripts/build-dataify-request.ps1`。\n8. `spider_parameters` 必须是一个 JSON 数组。\n9. `spider_name` 固定取 `tiktok.com`。\n10. `spider_id` 固定取用户所选工具的 `tool_sign`。\n11. 始终包含 `spider_errors=true` 和 `file_name={{TasksID}}`。\n\n## 设置 DATAIFY_API_TOKEN\n\n推荐使用永久环境变量，而不是只在当前终端临时设置。\n\nWindows PowerShell，当前用户永久设置：\n\n```powershell\n[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")\n```\n\n然后重新打开 PowerShell。如果当前会话也要立即生效，再执行：\n\n```powershell\n$env:DATAIFY_API_TOKEN = \"your_token_here\"\n```\n\nmacOS 或 Linux，bash 永久设置：\n\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\nmacOS 或 Linux，zsh 永久设置：\n\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.zshrc\nsource ~/.zshrc\n```\n\n## 脚本用法\n\nPython：\n\n```bash\npython scripts/build-dataify-request.py --tool-sign --values-file values.json\n```\n\nPowerShell：\n\n```powershell\n& \".\\scripts\\build-dataify-request.ps1\" -ToolSign \"\" -ValuesFile \".\\values.json\"\n```\n\n`values.json` 可以是单个对象，也可以是对象数组。\n\n## 输出格式\n\n最终 `curl` 命令应为：\n\n```bash\ncurl -X POST 'https://scraperapi.dataify.com/builder' \\\n -H \"Authorization: Bearer $DATAIFY_API_TOKEN\" \\\n -H 'Content-Type: application/x-www-form-urlencoded' \\\n -d 'spider_name=tiktok.com' \\\n -d 'spider_id=' \\\n -d 'spider_parameters=[{\"param\":\"value\"}]' \\\n -d 'spider_errors=true' \\\n -d 'file_name={{TasksID}}'\n```\n\n## 参考文件\n\n- `references/tool-params.json` 保存了这个 skill 下所有工具及参数选项。\n- `scripts/build-dataify-request.py` 是首选的跨平台实现。\n- `scripts/build-dataify-request.ps1` 是 Windows PowerShell 版本。\n- 如果参数没有预设选项，必须向用户要值。\n- 不要假设 `spider_parameters` 永远只有一个对象；多值工具可能需要按索引生成多个对象。\n- `url_example` 仅作为参考，不要默认用户就要用示例值，除非用户明确确认。\n\n## 参数交互策略\n\n- 当请求意图明确、只读、低风险且成本较低时，使用安全默认值直接执行。可以用一句话说明执行内容，但不要暂停等待确认。\n- 只在缺少必填输入、存在会明显改变结果的歧义、大批量或多页采集、媒体下载、会明显增加积分消耗、不可逆操作，或用户明确要求查看参数时询问。\n- 必须确认时，只展示会影响目标、范围、输出或成本的用户参数。优先使用一句简短说明；只有三个及以上关键值确实需要比较时才使用精简表格。\n- 不要展示固定字段、空的可选字段、未修改的默认值、凭据或内部实现参数，例如引擎选择、响应格式开关、偏移量、spider ID 和文件名模板。\n- 默认隐藏高级筛选项，除非用户主动询问或需要它们消除歧义。不得用文档示例值代替用户缺失的必填输入。\n- 先返回首个结果，再提供相关的细化选项，不要在首次执行前强迫用户决定所有可选项。\n\n## Account CTA policy\n\n- Show a prominent Dataify account CTA only when the API token is missing, rejected/invalid, or the account has insufficient credits.\n- For a missing token, offer https://dashboard.dataify.com/login?utm_source=skill and state: New accounts get 50 free credits, enough for about 6,000 trial results, valid for 7 days, and only successful requests are billed. Never ask the user to paste the token into chat.\n- Detect the current operating system and shell. Show only the matching session-scoped setup command first (`export` for macOS/Linux shells, `$env:` for Windows PowerShell, or `set` for Windows Command Prompt). Show other platforms or persistent setup only when detection is ambiguous or the user asks.\n- After the user says the token is configured, verify only whether `DATAIFY_API_TOKEN` is present; never print its value. If verification succeeds, continue the original task without asking the user to repeat it.\n- Explain that persistent shell changes may require a new terminal or restarting the agent application. Do not recommend a project `.env` unless the execution path explicitly loads it, and ensure `.env` is ignored by version control.\n- For an invalid token, direct the user to API-key management without implying that a new registration is required. For insufficient credits, direct the user to balance or recharge management.\n- During normal submission, processing, and successful completion, do not promote registration or the Dashboard. Never expose the token or include it in CTA attribution parameters.\n\nFile v1.3.1:agents/openai.yaml\n\ninterface:\n display_name: \"Dataify Tiktok Builder\"\n short_description: \"Collect Tiktok Builder data and return results\"\n default_prompt: \"Use $dataify-tiktok-comment-by-url to complete the requested Dataify collection, wait for the asynchronous task, and return the final collected result. Stop at task submission only when I explicitly request no-wait behavior.\"\n\nArchive v1.3.0: 8 files, 9709 bytes\n\nFiles: agents/openai.yaml (370b), references/tool-params.json (551b), scripts/build-dataify-request.ps1 (294b), scripts/build-dataify-request.py (408b), skill-card.md (2193b), SKILL.md (8058b), SKILL.zh-CN.md (6268b), _meta.json (148b)\n\nFile v1.3.0:SKILL.md\n\n---\nname: \"dataify-tiktok-comment-by-url\"\ndescription: \"Collect TikTok comments from a known TikTok content URL. Do not use for video download, profile collection, or general TikTok discovery.\"\n---\n\n# Dataify Builder Skill\n\nUse this skill to prepare Dataify builder requests for the scraper family rooted at `tiktok_comment_by-url` on `tiktok.com`.\n\n## Workflow\n\n1. Check whether `DATAIFY_API_TOKEN` exists in the environment.\n2. If the token is missing, stop and tell the user to sign in at [Dataify Dashboard](https://dashboard.dataify.com?utm_source=skill) to obtain it.\n3. Ask the user to choose exactly one tool from the following Chinese list:\n- 通过URL采集 (tiktok_comment_by-url)\n- 通过URL采集 (tiktok_shop_by-url)\n- 通过列表URL采集 (tiktok_posts_by-listurl)\n- 通过URL采集 (tiktok_profiles_by-url)\n- 通过搜索网址采集 (tiktok_profiles_by-listurl)\n4. Read `references/tool-params.json` and find the chosen tool by `tool_sign` or Chinese tool name.\n5. For each parameter in the chosen tool:\n - If `input_mode` is `user_input`, ask the user for the value.\n - If `input_mode` is `select`, present the saved options to the user.\n6. Use `scripts/build-dataify-request.py` as the default cross-platform helper.\n7. Use `scripts/build-dataify-request.ps1` as the Windows PowerShell helper when needed.\n8. When a selectable parameter has a human-readable Chinese label, keep that label in `spider_parameters`. Do not replace it with a code such as `HK` unless the user explicitly asks for the coded value.\n9. Build `spider_parameters` as a JSON array.\n10. If every parameter has only one final value, build one object such as `[{\"searchurl\":\"...\",\"country\":\"Hong Kong\"}]`.\n11. If one or more parameters have multiple aligned values, zip them by index and build one object per row. Example: `[{\"search_url\":\"url1\",\"page_turning\":\"1\",\"max_num\":\"15\"},{\"search_url\":\"url2\",\"page_turning\":\"1\",\"max_num\":\"15\"}]`.\n12. If a parameter has one value while another parameter has multiple values, reuse the single value across every generated row.\n13. Set `spider_name` to `tiktok.com`.\n14. Set `spider_id` to the selected tool's `tool_sign`.\n15. Always include `spider_errors=true` and `file_name={{TasksID}}`.\n16. Return a curl command for `https://scraperapi.dataify.com/builder`.\n\n## Set DATAIFY_API_TOKEN\n\nPrefer a permanent environment-variable setup instead of setting the token only for the current terminal session.\n\nWindows PowerShell, permanent for the current user:\n```powershell\n[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")\n```\n\nThen reopen PowerShell. If the current session also needs the token immediately, run:\n```powershell\n$env:DATAIFY_API_TOKEN = \"your_token_here\"\n```\n\nmacOS or Linux, permanent for bash:\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\nmacOS or Linux, permanent for zsh:\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.zshrc\nsource ~/.zshrc\n```\n\n## Script usage\n\nPython:\n```bash\npython scripts/build-dataify-request.py --tool-sign --values-file values.json\n```\n\nPowerShell:\n```powershell\n& \".\\scripts\\build-dataify-request.ps1\" -ToolSign \"\" -ValuesFile \".\\values.json\"\n```\n\nThe `values.json` file should contain either one object or an array of objects. Example:\n```json\n[{\"searchurl\":\"https://www.airbnb.com/s/Greece/homes?...\",\"country\":\"Hong Kong\"}]\n```\n\n## Required output shape\n\nGenerate a curl command in this form:\n\n```bash\ncurl -X POST 'https://scraperapi.dataify.com/builder' \\\n -H \"Authorization: Bearer $DATAIFY_API_TOKEN\" \\\n -H 'Content-Type: application/x-www-form-urlencoded' \\\n -d 'spider_name=tiktok.com' \\\n -d 'spider_id=' \\\n -d 'spider_parameters=[{\"param\":\"value\"}]' \\\n -d 'spider_errors=true' \\\n -d 'file_name={{TasksID}}'\n```\n\n## Reference usage\n\n- `references/tool-params.json` stores the full saved parameter catalog for every available tool in this scraper family.\n- `scripts/build-dataify-request.py` is the portable implementation and should be preferred.\n- `scripts/build-dataify-request.ps1` mirrors the same behavior for Windows users.\n- If a parameter has no options, the user must provide the value.\n- Do not assume `spider_parameters` always contains exactly one object. Multi-value tools may require multiple objects zipped by index.\n- Use the saved `url_example` only as a reference example. Do not assume the user wants the example values unless they explicitly confirm them.\n\n## Default completion behavior\n\nThe default deliverable is the collected result, not only a `task_id`.\n\n1. Submit the Builder task once and capture its `task_id`.\n2. Immediately continue with `$dataify-task-operations` and monitor the same task ID.\n - Use the default 600-second wait for ordinary collections.\n - Use `--timeout 1800` for media downloads or clearly high-volume, multi-page, or multi-input collections.\n3. When the task succeeds, download and return the final JSON result. Summarize large payloads while preserving access to the raw result.\n4. If monitoring times out or is interrupted, return the task ID and a resume command. Do not resubmit the paid task.\n5. Stop after submission only when the user explicitly asks for submission only, a task ID, or `--no-wait` behavior.\n\n## Quick Start\n\n```bash\npython3 scripts/build-dataify-request.py --help\n```\n\n## Parameter interaction policy\n\n- For a clear, low-risk, read-only, and low-cost request, apply safe defaults and execute immediately. A short execution summary is optional; do not pause for confirmation.\n- Ask only for a missing required input, a material ambiguity, a high-volume or multi-page scope, a media download, a choice that materially changes credit usage, an irreversible action, or an explicit user request to review parameters.\n- When confirmation is required, show only user-facing values that affect the target, scope, output, or cost. Prefer one concise sentence; use a compact table only when three or more consequential values are easier to compare.\n- Never show fixed fields, empty optional fields, unchanged defaults, credentials, or internal implementation parameters such as engine selectors, response-format flags, offsets, spider IDs, and file-name templates.\n- Keep advanced filters hidden unless the user asks for them or they are needed to resolve ambiguity. Never substitute documentation example values for missing required user input.\n- After returning results, offer relevant refinements instead of forcing all optional decisions before the first result.\n\n## Account CTA policy\n\n- Show a prominent Dataify account CTA only when the API token is missing, rejected/invalid, or the account has insufficient credits.\n- For a missing token, offer https://dashboard.dataify.com/login?utm_source=skill and state: New accounts receive 50 free credits. Never ask the user to paste the token into chat.\n- Detect the current operating system and shell. Show only the matching session-scoped setup command first (`export` for macOS/Linux shells, `$env:` for Windows PowerShell, or `set` for Windows Command Prompt). Show other platforms or persistent setup only when detection is ambiguous or the user asks.\n- After the user says the token is configured, verify only whether `DATAIFY_API_TOKEN` is present; never print its value. If verification succeeds, continue the original task without asking the user to repeat it.\n- Explain that persistent shell changes may require a new terminal or restarting the agent application. Do not recommend a project `.env` unless the execution path explicitly loads it, and ensure `.env` is ignored by version control.\n- For an invalid token, direct the user to API-key management without implying that a new registration is required. For insufficient credits, direct the user to balance or recharge management.\n- During normal submission, processing, and successful completion, do not promote registration or the Dashboard. Never expose the token or include it in CTA attribution parameters.\n\nFile v1.3.0:_meta.json\n\n{\n \"ownerId\": \"kn74z5hmmwk21kw8tpphd9w21x86bkdf\",\n \"slug\": \"dataify-tiktok-comment-by-url\",\n \"version\": \"1.3.0\",\n \"publishedAt\": 1788254126554\n}\n\nFile v1.3.0:references/tool-params.json\n\n[{\"tool_name_cn\":\"评论URL\",\"tool_sign\":\"tiktok_comment_by-url\",\"spider_name\":\"tiktok.com\",\"params\":[]},{\"tool_name_cn\":\"店铺URL\",\"tool_sign\":\"tiktok_shop_by-url\",\"spider_name\":\"tiktok.com\",\"params\":[]},{\"tool_name_cn\":\"帖子列表URL\",\"tool_sign\":\"tiktok_posts_by-listurl\",\"spider_name\":\"tiktok.com\",\"params\":[]},{\"tool_name_cn\":\"个人资料URL\",\"tool_sign\":\"tiktok_profiles_by-url\",\"spider_name\":\"tiktok.com\",\"params\":[]},{\"tool_name_cn\":\"个人资料列表URL\",\"tool_sign\":\"tiktok_profiles_by-listurl\",\"spider_name\":\"tiktok.com\",\"params\":[]}]\n\nFile v1.3.0:skill-card.md\n\n## Description:\n\nPrepares Dataify builder requests for TikTok comment-by-URL collection and related TikTok Dataify tools, then returns submission commands and collected results.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dataify-server](https://clawhub.ai/user/dataify-server)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to configure and submit Dataify TikTok collection tasks from known URLs, monitor asynchronous task completion, and retrieve JSON results.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The release is broader than its TikTok-comments-only label because it can prepare and submit Dataify tasks for shops, post lists, and profiles.\n\nMitigation: Install only when broader TikTok Dataify builder authority is intended, or narrow the tool catalog and instructions to allow only tiktok_comment_by-url.\n\nRisk: The skill uses DATAIFY_API_TOKEN for authenticated external Dataify API calls that may consume credits.\n\nMitigation: Keep the token in the environment, never expose it in chat or logs, and review target scope before high-volume or multi-page submissions.\n\n## Reference(s):\n\n- [Tool parameter catalog](references/tool-params.json)\n- [ClawHub skill page](https://clawhub.ai/dataify-server/skills/dataify-tiktok-comment-by-url)\n- [Dataify builder endpoint](https://scraperapi.dataify.com/builder)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, Configuration, API Calls, JSON, Guidance]\n\n**Output Format:** [Markdown with inline shell commands and JSON result summaries]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Uses DATAIFY_API_TOKEN for authenticated Dataify requests; successful collections return final JSON results, with large payloads summarized while preserving raw result access.]\n\n## Skill Version(s):\n\n1.3.0 (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 v1.3.0:SKILL.zh-CN.md\n\n---\nname: \"dataify-tiktok-comment-by-url\"\ndescription: \"为 tiktok.com 上以 tiktok_comment_by-url 为根的 scraper 系列准备 Dataify builder 请求。当需要处理成功的 Dataify scraper detail 条目 tiktok_comment_by-url、让用户选择可用工具、读取已保存的 getToolParams 选项，并使用 DATAIFY_API_TOKEN 生成 scraperapi.dataify.com/builder curl 请求时，使用此 skill。\"\n---\n\n# Dataify Builder Skill 中文版\n\n这个 skill 用于为 `tiktok.com` 下、以 `tiktok_comment_by-url` 为入口的 Dataify scraper 工具族生成 builder 请求。\n\n## 工作流程\n\n1. 先检查环境变量中是否存在 `DATAIFY_API_TOKEN`。\n2. 如果 token 缺失，提示用户前往 dataify官网 获取。\n3. 先让用户从下面的中文工具列表中明确选择一个工具：\n- 通过URL采集 (tiktok_comment_by-url)\n- 通过URL采集 (tiktok_shop_by-url)\n- 通过列表URL采集 (tiktok_posts_by-listurl)\n- 通过URL采集 (tiktok_profiles_by-url)\n- 通过搜索网址采集 (tiktok_profiles_by-listurl)\n4. 再读取 `references/tool-params.json`，根据 `tool_sign` 或中文工具名找到对应工具。\n5. 对所选工具的每个参数分别处理：\n - 如果 `input_mode` 是 `user_input`，让用户提供值。\n - 如果 `input_mode` 是 `select`，把已保存的可选项展示给用户，让用户选择。\n6. 默认优先使用 `scripts/build-dataify-request.py`，因为它是跨平台版本。\n7. Windows 下也可以使用 `scripts/build-dataify-request.ps1`。\n8. `spider_parameters` 必须是一个 JSON 数组。\n9. `spider_name` 固定取 `tiktok.com`。\n10. `spider_id` 固定取用户所选工具的 `tool_sign`。\n11. 始终包含 `spider_errors=true` 和 `file_name={{TasksID}}`。\n\n## 设置 DATAIFY_API_TOKEN\n\n推荐使用永久环境变量，而不是只在当前终端临时设置。\n\nWindows PowerShell，当前用户永久设置：\n\n```powershell\n[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")\n```\n\n然后重新打开 PowerShell。如果当前会话也要立即生效，再执行：\n\n```powershell\n$env:DATAIFY_API_TOKEN = \"your_token_here\"\n```\n\nmacOS 或 Linux，bash 永久设置：\n\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\nmacOS 或 Linux，zsh 永久设置：\n\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.zshrc\nsource ~/.zshrc\n```\n\n## 脚本用法\n\nPython：\n\n```bash\npython scripts/build-dataify-request.py --tool-sign --values-file values.json\n```\n\nPowerShell：\n\n```powershell\n& \".\\scripts\\build-dataify-request.ps1\" -ToolSign \"\" -ValuesFile \".\\values.json\"\n```\n\n`values.json` 可以是单个对象，也可以是对象数组。\n\n## 输出格式\n\n最终 `curl` 命令应为：\n\n```bash\ncurl -X POST 'https://scraperapi.dataify.com/builder' \\\n -H \"Authorization: Bearer $DATAIFY_API_TOKEN\" \\\n -H 'Content-Type: application/x-www-form-urlencoded' \\\n -d 'spider_name=tiktok.com' \\\n -d 'spider_id=' \\\n -d 'spider_parameters=[{\"param\":\"value\"}]' \\\n -d 'spider_errors=true' \\\n -d 'file_name={{TasksID}}'\n```\n\n## 参考文件\n\n- `references/tool-params.json` 保存了这个 skill 下所有工具及参数选项。\n- `scripts/build-dataify-request.py` 是首选的跨平台实现。\n- `scripts/build-dataify-request.ps1` 是 Windows PowerShell 版本。\n- 如果参数没有预设选项，必须向用户要值。\n- 不要假设 `spider_parameters` 永远只有一个对象；多值工具可能需要按索引生成多个对象。\n- `url_example` 仅作为参考，不要默认用户就要用示例值，除非用户明确确认。\n\n## 参数交互策略\n\n- 当请求意图明确、只读、低风险且成本较低时，使用安全默认值直接执行。可以用一句话说明执行内容，但不要暂停等待确认。\n- 只在缺少必填输入、存在会明显改变结果的歧义、大批量或多页采集、媒体下载、会明显增加积分消耗、不可逆操作，或用户明确要求查看参数时询问。\n- 必须确认时，只展示会影响目标、范围、输出或成本的用户参数。优先使用一句简短说明；只有三个及以上关键值确实需要比较时才使用精简表格。\n- 不要展示固定字段、空的可选字段、未修改的默认值、凭据或内部实现参数，例如引擎选择、响应格式开关、偏移量、spider ID 和文件名模板。\n- 默认隐藏高级筛选项，除非用户主动询问或需要它们消除歧义。不得用文档示例值代替用户缺失的必填输入。\n- 先返回首个结果，再提供相关的细化选项，不要在首次执行前强迫用户决定所有可选项。\n\n## Account CTA policy\n\n- Show a prominent Dataify account CTA only when the API token is missing, rejected/invalid, or the account has insufficient credits.\n- For a missing token, offer https://dashboard.dataify.com/login?utm_source=skill and state: New accounts receive 50 free credits. Never ask the user to paste the token into chat.\n- Detect the current operating system and shell. Show only the matching session-scoped setup command first (`export` for macOS/Linux shells, `$env:` for Windows PowerShell, or `set` for Windows Command Prompt). Show other platforms or persistent setup only when detection is ambiguous or the user asks.\n- After the user says the token is configured, verify only whether `DATAIFY_API_TOKEN` is present; never print its value. If verification succeeds, continue the original task without asking the user to repeat it.\n- Explain that persistent shell changes may require a new terminal or restarting the agent application. Do not recommend a project `.env` unless the execution path explicitly loads it, and ensure `.env` is ignored by version control.\n- For an invalid token, direct the user to API-key management without implying that a new registration is required. For insufficient credits, direct the user to balance or recharge management.\n- During normal submission, processing, and successful completion, do not promote registration or the Dashboard. Never expose the token or include it in CTA attribution parameters.\n\nFile v1.3.0:agents/openai.yaml\n\ninterface:\n display_name: \"Dataify Tiktok Builder\"\n short_description: \"Collect Tiktok Builder data and return results\"\n default_prompt: \"Use $dataify-tiktok-comment-by-url to complete the requested Dataify collection, wait for the asynchronous task, and return the final collected result. Stop at task submission only when I explicitly request no-wait behavior.\"\n\nArchive v1.2.0: 8 files, 8053 bytes\n\nFiles: agents/openai.yaml (221b), references/tool-params.json (551b), scripts/build-dataify-request.ps1 (294b), scripts/build-dataify-request.py (3728b), skill-card.md (2216b), SKILL.md (4866b), SKILL.zh-CN.md (3839b), _meta.json (148b)\n\nFile v1.2.0:SKILL.md\n\n---\nname: \"dataify-tiktok-comment-by-url\"\ndescription: \"Prepare Dataify builder requests for the tiktok.com scraper family rooted at tiktok_comment_by-url. Use when needs to work with the successful Dataify scraper detail entry for tiktok_comment_by-url, let the user choose one of its available tools, read saved getToolParams options, and generate a scraperapi.dataify.com/builder curl request with DATAIFY_API_TOKEN.\"\n---\n\n# Dataify Builder Skill\n\nUse this skill to prepare Dataify builder requests for the scraper family rooted at `tiktok_comment_by-url` on `tiktok.com`.\n\n## Workflow\n\n1. Check whether `DATAIFY_API_TOKEN` exists in the environment.\n2. If the token is missing, stop and tell the user to sign in at [Dataify Dashboard](https://dashboard.dataify.com?utm_source=skill) to obtain it.\n3. Ask the user to choose exactly one tool from the following Chinese list:\n- 通过URL采集 (tiktok_comment_by-url)\n- 通过URL采集 (tiktok_shop_by-url)\n- 通过列表URL采集 (tiktok_posts_by-listurl)\n- 通过URL采集 (tiktok_profiles_by-url)\n- 通过搜索网址采集 (tiktok_profiles_by-listurl)\n4. Read `references/tool-params.json` and find the chosen tool by `tool_sign` or Chinese tool name.\n5. For each parameter in the chosen tool:\n - If `input_mode` is `user_input`, ask the user for the value.\n - If `input_mode` is `select`, present the saved options to the user.\n6. Use `scripts/build-dataify-request.py` as the default cross-platform helper.\n7. Use `scripts/build-dataify-request.ps1` as the Windows PowerShell helper when needed.\n8. When a selectable parameter has a human-readable Chinese label, keep that label in `spider_parameters`. Do not replace it with a code such as `HK` unless the user explicitly asks for the coded value.\n9. Build `spider_parameters` as a JSON array.\n10. If every parameter has only one final value, build one object such as `[{\"searchurl\":\"...\",\"country\":\"Hong Kong\"}]`.\n11. If one or more parameters have multiple aligned values, zip them by index and build one object per row. Example: `[{\"search_url\":\"url1\",\"page_turning\":\"1\",\"max_num\":\"15\"},{\"search_url\":\"url2\",\"page_turning\":\"1\",\"max_num\":\"15\"}]`.\n12. If a parameter has one value while another parameter has multiple values, reuse the single value across every generated row.\n13. Set `spider_name` to `tiktok.com`.\n14. Set `spider_id` to the selected tool's `tool_sign`.\n15. Always include `spider_errors=true` and `file_name={{TasksID}}`.\n16. Return a curl command for `https://scraperapi.dataify.com/builder`.\n\n## Set DATAIFY_API_TOKEN\n\nPrefer a permanent environment-variable setup instead of setting the token only for the current terminal session.\n\nWindows PowerShell, permanent for the current user:\n```powershell\n[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")\n```\n\nThen reopen PowerShell. If the current session also needs the token immediately, run:\n```powershell\n$env:DATAIFY_API_TOKEN = \"your_token_here\"\n```\n\nmacOS or Linux, permanent for bash:\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\nmacOS or Linux, permanent for zsh:\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.zshrc\nsource ~/.zshrc\n```\n\n## Script usage\n\nPython:\n```bash\npython scripts/build-dataify-request.py --tool-sign --values-file values.json\n```\n\nPowerShell:\n```powershell\n& \".\\scripts\\build-dataify-request.ps1\" -ToolSign \"\" -ValuesFile \".\\values.json\"\n```\n\nThe `values.json` file should contain either one object or an array of objects. Example:\n```json\n[{\"searchurl\":\"https://www.airbnb.com/s/Greece/homes?...\",\"country\":\"Hong Kong\"}]\n```\n\n## Required output shape\n\nGenerate a curl command in this form:\n\n```bash\ncurl -X POST 'https://scraperapi.dataify.com/builder' \\\n -H \"Authorization: Bearer $DATAIFY_API_TOKEN\" \\\n -H 'Content-Type: application/x-www-form-urlencoded' \\\n -d 'spider_name=tiktok.com' \\\n -d 'spider_id=' \\\n -d 'spider_parameters=[{\"param\":\"value\"}]' \\\n -d 'spider_errors=true' \\\n -d 'file_name={{TasksID}}'\n```\n\n## Reference usage\n\n- `references/tool-params.json` stores the full saved parameter catalog for every available tool in this scraper family.\n- `scripts/build-dataify-request.py` is the portable implementation and should be preferred.\n- `scripts/build-dataify-request.ps1` mirrors the same behavior for Windows users.\n- If a parameter has no options, the user must provide the value.\n- If a parameter has options, present those options back to the user before building the final request.\n- Do not assume `spider_parameters` always contains exactly one object. Multi-value tools may require multiple objects zipped by index.\n- Use the saved `url_example` only as a reference example. Do not assume the user wants the example values unless they explicitly confirm them.\n\nFile v1.2.0:_meta.json\n\n{\n \"ownerId\": \"kn74z5hmmwk21kw8tpphd9w21x86bkdf\",\n \"slug\": \"dataify-tiktok-comment-by-url\",\n \"version\": \"1.2.0\",\n \"publishedAt\": 1784191128137\n}\n\nFile v1.2.0:references/tool-params.json\n\n[{\"tool_name_cn\":\"评论URL\",\"tool_sign\":\"tiktok_comment_by-url\",\"spider_name\":\"tiktok.com\",\"params\":[]},{\"tool_name_cn\":\"店铺URL\",\"tool_sign\":\"tiktok_shop_by-url\",\"spider_name\":\"tiktok.com\",\"params\":[]},{\"tool_name_cn\":\"帖子列表URL\",\"tool_sign\":\"tiktok_posts_by-listurl\",\"spider_name\":\"tiktok.com\",\"params\":[]},{\"tool_name_cn\":\"个人资料URL\",\"tool_sign\":\"tiktok_profiles_by-url\",\"spider_name\":\"tiktok.com\",\"params\":[]},{\"tool_name_cn\":\"个人资料列表URL\",\"tool_sign\":\"tiktok_profiles_by-listurl\",\"spider_name\":\"tiktok.com\",\"params\":[]}]\n\nFile v1.2.0:skill-card.md\n\n## Description:
\nPrepare Dataify builder requests for TikTok scraper tools by helping users select a Dataify tool, collect parameter values, and generate a curl request using DATAIFY_API_TOKEN.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[dataify-server](https://clawhub.ai/user/dataify-server)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and external users who use Dataify can generate builder requests for TikTok comment, shop, post-list, and profile scraping tools after choosing a tool and supplying parameter values.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The generated curl request sends selected URLs and parameters to Dataify.
\nMitigation: Review the generated command before execution and use it only for the intended Dataify TikTok scraping workflow.
\nRisk: DATAIFY_API_TOKEN exposure could grant access to the Dataify account.
\nMitigation: Treat DATAIFY_API_TOKEN like a password; prefer a session-scoped environment variable or secret manager and avoid storing it in shared shell profile files.
\n\n\n## Reference(s):
\n- [Tool parameter catalog](artifact/references/tool-params.json)
\n- [Dataify Dashboard](https://dashboard.dataify.com?utm_source=skill)
\n- [Dataify builder endpoint](https://scraperapi.dataify.com/builder)
\n- [ClawHub skill page](https://clawhub.ai/dataify-server/skills/dataify-tiktok-comment-by-url)
\n\n\n## Skill Output:
\n**Output Type(s):** [Text, Markdown, Shell commands, Configuration]
\n**Output Format:** [Markdown with bash or PowerShell command blocks and JSON snippets]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Returns a Dataify builder curl command and may provide DATAIFY_API_TOKEN setup guidance.]
\n\n## Skill Version(s):
\n1.2.0 (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\nFile v1.2.0:SKILL.zh-CN.md\n\n---\nname: \"dataify-tiktok-comment-by-url\"\ndescription: \"为 tiktok.com 上以 tiktok_comment_by-url 为根的 scraper 系列准备 Dataify builder 请求。当需要处理成功的 Dataify scraper detail 条目 tiktok_comment_by-url、让用户选择可用工具、读取已保存的 getToolParams 选项，并使用 DATAIFY_API_TOKEN 生成 scraperapi.dataify.com/builder curl 请求时，使用此 skill。\"\n---\n\n# Dataify Builder Skill 中文版\n\n这个 skill 用于为 `tiktok.com` 下、以 `tiktok_comment_by-url` 为入口的 Dataify scraper 工具族生成 builder 请求。\n\n## 工作流程\n\n1. 先检查环境变量中是否存在 `DATAIFY_API_TOKEN`。\n2. 如果 token 缺失，提示用户前往 dataify官网 获取。\n3. 先让用户从下面的中文工具列表中明确选择一个工具：\n- 通过URL采集 (tiktok_comment_by-url)\n- 通过URL采集 (tiktok_shop_by-url)\n- 通过列表URL采集 (tiktok_posts_by-listurl)\n- 通过URL采集 (tiktok_profiles_by-url)\n- 通过搜索网址采集 (tiktok_profiles_by-listurl)\n4. 再读取 `references/tool-params.json`，根据 `tool_sign` 或中文工具名找到对应工具。\n5. 对所选工具的每个参数分别处理：\n - 如果 `input_mode` 是 `user_input`，让用户提供值。\n - 如果 `input_mode` 是 `select`，把已保存的可选项展示给用户，让用户选择。\n6. 默认优先使用 `scripts/build-dataify-request.py`，因为它是跨平台版本。\n7. Windows 下也可以使用 `scripts/build-dataify-request.ps1`。\n8. `spider_parameters` 必须是一个 JSON 数组。\n9. `spider_name` 固定取 `tiktok.com`。\n10. `spider_id` 固定取用户所选工具的 `tool_sign`。\n11. 始终包含 `spider_errors=true` 和 `file_name={{TasksID}}`。\n\n## 设置 DATAIFY_API_TOKEN\n\n推荐使用永久环境变量，而不是只在当前终端临时设置。\n\nWindows PowerShell，当前用户永久设置：\n\n```powershell\n[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")\n```\n\n然后重新打开 PowerShell。如果当前会话也要立即生效，再执行：\n\n```powershell\n$env:DATAIFY_API_TOKEN = \"your_token_here\"\n```\n\nmacOS 或 Linux，bash 永久设置：\n\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\nmacOS 或 Linux，zsh 永久设置：\n\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.zshrc\nsource ~/.zshrc\n```\n\n## 脚本用法\n\nPython：\n\n```bash\npython scripts/build-dataify-request.py --tool-sign --values-file values.json\n```\n\nPowerShell：\n\n```powershell\n& \".\\scripts\\build-dataify-request.ps1\" -ToolSign \"\" -ValuesFile \".\\values.json\"\n```\n\n`values.json` 可以是单个对象，也可以是对象数组。\n\n## 输出格式\n\n最终 `curl` 命令应为：\n\n```bash\ncurl -X POST 'https://scraperapi.dataify.com/builder' \\\n -H \"Authorization: Bearer $DATAIFY_API_TOKEN\" \\\n -H 'Content-Type: application/x-www-form-urlencoded' \\\n -d 'spider_name=tiktok.com' \\\n -d 'spider_id=' \\\n -d 'spider_parameters=[{\"param\":\"value\"}]' \\\n -d 'spider_errors=true' \\\n -d 'file_name={{TasksID}}'\n```\n\n## 参考文件\n\n- `references/tool-params.json` 保存了这个 skill 下所有工具及参数选项。\n- `scripts/build-dataify-request.py` 是首选的跨平台实现。\n- `scripts/build-dataify-request.ps1` 是 Windows PowerShell 版本。\n- 如果参数没有预设选项，必须向用户要值。\n- 如果参数有预设选项，先把选项展示给用户，再生成最终请求。\n- 不要假设 `spider_parameters` 永远只有一个对象；多值工具可能需要按索引生成多个对象。\n- `url_example` 仅作为参考，不要默认用户就要用示例值，除非用户明确确认。\n\nFile v1.2.0:agents/openai.yaml\n\ninterface:\n display_name: \"Dataify Tiktok Builder\"\n short_description: \"Prepare Dataify builder calls for tiktok.com\"\n default_prompt: \"Use $dataify-tiktok-comment-by-url to prepare a Dataify builder curl request.\"\n\nArchive v1.1.0: 6 files, 7348 bytes\n\nFiles: agents/openai.yaml (221b), scripts/build-dataify-request.py (3721b), skill-card.md (2119b), SKILL.md (4869b), SKILL.zh-CN.md (3839b), _meta.json (148b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: \"dataify-tiktok-comment-by-url\"\ndescription: \"Prepare Dataify builder requests for the tiktok.com scraper family rooted at tiktok_comment_by-url. Use when needs to work with the successful Dataify scraper detail entry for tiktok_comment_by-url, let the user choose one of its available tools, read saved getToolParams options, and generate a scraperapi.dataify.com/builder curl request with DATAIFY_API_TOKEN.\"\n---\n\n# Dataify Builder Skill\n\nUse this skill to prepare Dataify builder requests for the scraper family rooted at `tiktok_comment_by-url` on `tiktok.com`.\n\n## Workflow\n\n1. Check whether `DATAIFY_API_TOKEN` exists in the environment.\n2. If the token is missing, stop and tell the user to sign in at [Dataify Dashboard](https://dashboard.dataify.com?utm_source=skill) to obtain it.\n3. Ask the user to choose exactly one tool from the following Chinese list:\n- 通过URL采集 (tiktok_comment_by-url)\n- 通过URL采集 (tiktok_shop_by-url)\n- 通过列表URL采集 (tiktok_posts_by-listurl)\n- 通过URL采集 (tiktok_profiles_by-url)\n- 通过搜索网址采集 (tiktok_profiles_by-listurl)\n4. Read `references/tool-params.json` and find the chosen tool by `tool_sign` or Chinese tool name.\n5. For each parameter in the chosen tool:\n - If `input_mode` is `user_input`, ask the user for the value.\n - If `input_mode` is `select`, present the saved options to the user.\n6. Use `scripts/build-dataify-request.py` as the default cross-platform helper.\n7. Use `scripts/build-dataify-request.ps1` as the Windows PowerShell helper when needed.\n8. When a selectable parameter has a human-readable Chinese label, keep that label in `spider_parameters`. Do not replace it with a code such as `HK` unless the user explicitly asks for the coded value.\n9. Build `spider_parameters` as a JSON array.\n10. If every parameter has only one final value, build one object such as `[{\"searchurl\":\"...\",\"country\":\"Hong Kong\"}]`.\n11. If one or more parameters have multiple aligned values, zip them by index and build one object per row. Example: `[{\"search_url\":\"url1\",\"page_turning\":\"1\",\"max_num\":\"15\"},{\"search_url\":\"url2\",\"page_turning\":\"1\",\"max_num\":\"15\"}]`.\n12. If a parameter has one value while another parameter has multiple values, reuse the single value across every generated row.\n13. Set `spider_name` to `tiktok.com`.\n14. Set `spider_id` to the selected tool's `tool_sign`.\n15. Always include `spider_errors=true` and `file_name={{TasksID}}`.\n16. Return a curl command for `https://scraperapi.dataify.com/builder`.\n\n## Set DATAIFY_API_TOKEN\n\nPrefer a permanent environment-variable setup instead of setting the token only for the current terminal session.\n\nWindows PowerShell, permanent for the current user:\n```powershell\n[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")\n```\n\nThen reopen PowerShell. If the current session also needs the token immediately, run:\n```powershell\n$env:DATAIFY_API_TOKEN = \"your_token_here\"\n```\n\nmacOS or Linux, permanent for bash:\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\nmacOS or Linux, permanent for zsh:\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.zshrc\nsource ~/.zshrc\n```\n\n## Script usage\n\nPython:\n```bash\npython scripts/build-dataify-request.py --tool-sign --values-file values.json\n```\n\nPowerShell:\n```powershell\n& \".\\scripts\\build-dataify-request.ps1\" -ToolSign \"\" -ValuesFile \".\\values.json\"\n```\n\nThe `values.json` file should contain either one object or an array of objects. Example:\n```json\n[{\"searchurl\":\"https://www.airbnb.com/s/Greece/homes?...\",\"country\":\"Hong Kong\"}]\n```\n\n## Required output shape\n\nGenerate a curl command in this form:\n\n```bash\ncurl -X POST 'https://scraperapi.dataify.com/builder' \\\n -H \"Authorization: Bearer $DATAIFY_API_TOKEN\" \\\n -H 'Content-Type: application/x-www-form-urlencoded' \\\n -d 'spider_name=tiktok.com' \\\n -d 'spider_id=' \\\n -d 'spider_parameters=[{\"param\":\"value\"}]' \\\n -d 'spider_errors=true' \\\n -d 'file_name={{TasksID}}'\n```\n\n## Reference usage\n\n- `references/tool-params.json` stores the full saved parameter catalog for every available tool in this scraper family.\n- `scripts/build-dataify-request.py` is the portable implementation and should be preferred.\n- `scripts/build-dataify-request.ps1` mirrors the same behavior for Windows users.\n- If a parameter has no options, the user must provide the value.\n- If a parameter has options, present those options back to the user before building the final request.\n- Do not assume `spider_parameters` always contains exactly one object. Multi-value tools may require multiple objects zipped by index.\n- Use the saved `url_example` only as a reference example. Do not assume the user wants the example values unless they explicitly confirm them.\n\nFile v1.1.0:_meta.json\n\n{\n \"ownerId\": \"kn74z5hmmwk21kw8tpphd9w21x86bkdf\",\n \"slug\": \"dataify-tiktok-comment-by-url\",\n \"version\": \"1.1.0\",\n \"publishedAt\": 1780884457615\n}\n\nFile v1.1.0:skill-card.md\n\n## Description:
\nPrepares Dataify builder requests for TikTok scraper tools rooted at tiktok_comment_by-url, including tool selection, parameter collection, and curl command generation for scraperapi.dataify.com/builder.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[dataify-server](https://clawhub.ai/user/dataify-server)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and operators use this skill to prepare Dataify builder calls for TikTok scraper workflows. It helps collect tool parameters, normalize saved option labels, and produce a curl request that can be run against the Dataify builder endpoint.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Generated curl commands can expose DATAIFY_API_TOKEN if pasted into chats, logs, screenshots, backups, or synced shell history.
\nMitigation: Keep the token in a secret manager or session-scoped environment variable, redact Authorization headers before sharing output, and avoid storing generated commands in persistent profiles or logs.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/dataify-server/dataify-tiktok-comment-by-url)
\n- [Dataify dashboard](https://dashboard.dataify.com?utm_source=skill)
\n- [Dataify builder endpoint](https://scraperapi.dataify.com/builder)
\n\n\n## Skill Output:
\n**Output Type(s):** [Shell commands, Configuration, Guidance]
\n**Output Format:** [Markdown with inline shell commands and JSON parameter examples]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Generated requests require a DATAIFY_API_TOKEN environment variable and user-supplied scraper parameter values.]
\n\n## Skill Version(s):
\n1.1.0 (source: server release evidence)
\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\nFile v1.1.0:SKILL.zh-CN.md\n\n---\nname: \"dataify-tiktok-comment-by-url\"\ndescription: \"为 tiktok.com 上以 tiktok_comment_by-url 为根的 scraper 系列准备 Dataify builder 请求。当需要处理成功的 Dataify scraper detail 条目 tiktok_comment_by-url、让用户选择可用工具、读取已保存的 getToolParams 选项，并使用 DATAIFY_API_TOKEN 生成 scraperapi.dataify.com/builder curl 请求时，使用此 skill。\"\n---\n\n# Dataify Builder Skill 中文版\n\n这个 skill 用于为 `tiktok.com` 下、以 `tiktok_comment_by-url` 为入口的 Dataify scraper 工具族生成 builder 请求。\n\n## 工作流程\n\n1. 先检查环境变量中是否存在 `DATAIFY_API_TOKEN`。\n2. 如果 token 缺失，提示用户前往 dataify官网 获取。\n3. 先让用户从下面的中文工具列表中明确选择一个工具：\n- 通过URL采集 (tiktok_comment_by-url)\n- 通过URL采集 (tiktok_shop_by-url)\n- 通过列表URL采集 (tiktok_posts_by-listurl)\n- 通过URL采集 (tiktok_profiles_by-url)\n- 通过搜索网址采集 (tiktok_profiles_by-listurl)\n4. 再读取 `references/tool-params.json`，根据 `tool_sign` 或中文工具名找到对应工具。\n5. 对所选工具的每个参数分别处理：\n - 如果 `input_mode` 是 `user_input`，让用户提供值。\n - 如果 `input_mode` 是 `select`，把已保存的可选项展示给用户，让用户选择。\n6. 默认优先使用 `scripts/build-dataify-request.py`，因为它是跨平台版本。\n7. Windows 下也可以使用 `scripts/build-dataify-request.ps1`。\n8. `spider_parameters` 必须是一个 JSON 数组。\n9. `spider_name` 固定取 `tiktok.com`。\n10. `spider_id` 固定取用户所选工具的 `tool_sign`。\n11. 始终包含 `spider_errors=true` 和 `file_name={{TasksID}}`。\n\n## 设置 DATAIFY_API_TOKEN\n\n推荐使用永久环境变量，而不是只在当前终端临时设置。\n\nWindows PowerShell，当前用户永久设置：\n\n```powershell\n[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")\n```\n\n然后重新打开 PowerShell。如果当前会话也要立即生效，再执行：\n\n```powershell\n$env:DATAIFY_API_TOKEN = \"your_token_here\"\n```\n\nmacOS 或 Linux，bash 永久设置：\n\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\nmacOS 或 Linux，zsh 永久设置：\n\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.zshrc\nsource ~/.zshrc\n```\n\n## 脚本用法\n\nPython：\n\n```bash\npython scripts/build-dataify-request.py --tool-sign --values-file values.json\n```\n\nPowerShell：\n\n```powershell\n& \".\\scripts\\build-dataify-request.ps1\" -ToolSign \"\" -ValuesFile \".\\values.json\"\n```\n\n`values.json` 可以是单个对象，也可以是对象数组。\n\n## 输出格式\n\n最终 `curl` 命令应为：\n\n```bash\ncurl -X POST 'https://scraperapi.dataify.com/builder' \\\n -H \"Authorization: Bearer $DATAIFY_API_TOKEN\" \\\n -H 'Content-Type: application/x-www-form-urlencoded' \\\n -d 'spider_name=tiktok.com' \\\n -d 'spider_id=' \\\n -d 'spider_parameters=[{\"param\":\"value\"}]' \\\n -d 'spider_errors=true' \\\n -d 'file_name={{TasksID}}'\n```\n\n## 参考文件\n\n- `references/tool-params.json` 保存了这个 skill 下所有工具及参数选项。\n- `scripts/build-dataify-request.py` 是首选的跨平台实现。\n- `scripts/build-dataify-request.ps1` 是 Windows PowerShell 版本。\n- 如果参数没有预设选项，必须向用户要值。\n- 如果参数有预设选项，先把选项展示给用户，再生成最终请求。\n- 不要假设 `spider_parameters` 永远只有一个对象；多值工具可能需要按索引生成多个对象。\n- `url_example` 仅作为参考，不要默认用户就要用示例值，除非用户明确确认。\n\nFile v1.1.0:agents/openai.yaml\n\ninterface:\n display_name: \"Dataify Tiktok Builder\"\n short_description: \"Prepare Dataify builder calls for tiktok.com\"\n default_prompt: \"Use $dataify-tiktok-comment-by-url to prepare a Dataify builder curl request.\"\n\nArchive v1.0.0: 6 files, 7124 bytes\n\nFiles: agents/openai.yaml (221b), scripts/build-dataify-request.py (3699b), skill-card.md (2086b), SKILL.md (4852b), SKILL.zh-CN.md (3402b), _meta.json (148b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: \"dataify-tiktok-comment-by-url\"\ndescription: \"Prepare Dataify builder requests for the tiktok.com scraper family rooted at tiktok_comment_by-url. Use when needs to work with the successful Dataify scraper detail entry for tiktok_comment_by-url, let the user choose one of its available tools, read saved getToolParams options, and generate a scraperapi.dataify.com/builder curl request with DATAIFY_API_TOKEN.\"\n---\n\n# Dataify Builder Skill\n\nUse this skill to prepare Dataify builder requests for the scraper family rooted at `tiktok_comment_by-url` on `tiktok.com`.\n\n## Workflow\n\n1. Check whether `DATAIFY_API_TOKEN` exists in the environment.\n2. If the token is missing, stop and tell the user to sign in at [Dataify Dashboard](https://dataify.com/dashboard) to obtain it.\n3. Ask the user to choose exactly one tool from the following Chinese list:\n- 通过URL采集 (tiktok_comment_by-url)\n- 通过URL采集 (tiktok_shop_by-url)\n- 通过列表URL采集 (tiktok_posts_by-listurl)\n- 通过URL采集 (tiktok_profiles_by-url)\n- 通过搜索网址采集 (tiktok_profiles_by-listurl)\n4. Read `references/tool-params.json` and find the chosen tool by `tool_sign` or Chinese tool name.\n5. For each parameter in the chosen tool:\n - If `input_mode` is `user_input`, ask the user for the value.\n - If `input_mode` is `select`, present the saved options to the user.\n6. Use `scripts/build-dataify-request.py` as the default cross-platform helper.\n7. Use `scripts/build-dataify-request.ps1` as the Windows PowerShell helper when needed.\n8. When a selectable parameter has a human-readable Chinese label, keep that label in `spider_parameters`. Do not replace it with a code such as `HK` unless the user explicitly asks for the coded value.\n9. Build `spider_parameters` as a JSON array.\n10. If every parameter has only one final value, build one object such as `[{\"searchurl\":\"...\",\"country\":\"Hong Kong\"}]`.\n11. If one or more parameters have multiple aligned values, zip them by index and build one object per row. Example: `[{\"search_url\":\"url1\",\"page_turning\":\"1\",\"max_num\":\"15\"},{\"search_url\":\"url2\",\"page_turning\":\"1\",\"max_num\":\"15\"}]`.\n12. If a parameter has one value while another parameter has multiple values, reuse the single value across every generated row.\n13. Set `spider_name` to `tiktok.com`.\n14. Set `spider_id` to the selected tool's `tool_sign`.\n15. Always include `spider_errors=true` and `file_name={{TasksID}}`.\n16. Return a curl command for `https://scraperapi.dataify.com/builder`.\n\n## Set DATAIFY_API_TOKEN\n\nPrefer a permanent environment-variable setup instead of setting the token only for the current terminal session.\n\nWindows PowerShell, permanent for the current user:\n```powershell\n[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")\n```\n\nThen reopen PowerShell. If the current session also needs the token immediately, run:\n```powershell\n$env:DATAIFY_API_TOKEN = \"your_token_here\"\n```\n\nmacOS or Linux, permanent for bash:\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\nmacOS or Linux, permanent for zsh:\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.zshrc\nsource ~/.zshrc\n```\n\n## Script usage\n\nPython:\n```bash\npython scripts/build-dataify-request.py --tool-sign --values-file values.json\n```\n\nPowerShell:\n```powershell\n& \".\\scripts\\build-dataify-request.ps1\" -ToolSign \"\" -ValuesFile \".\\values.json\"\n```\n\nThe `values.json` file should contain either one object or an array of objects. Example:\n```json\n[{\"searchurl\":\"https://www.airbnb.com/s/Greece/homes?...\",\"country\":\"Hong Kong\"}]\n```\n\n## Required output shape\n\nGenerate a curl command in this form:\n\n```bash\ncurl -X POST 'https://scraperapi.dataify.com/builder' \\\n -H \"Authorization: Bearer $DATAIFY_API_TOKEN\" \\\n -H 'Content-Type: application/x-www-form-urlencoded' \\\n -d 'spider_name=tiktok.com' \\\n -d 'spider_id=' \\\n -d 'spider_parameters=[{\"param\":\"value\"}]' \\\n -d 'spider_errors=true' \\\n -d 'file_name={{TasksID}}'\n```\n\n## Reference usage\n\n- `references/tool-params.json` stores the full saved parameter catalog for every available tool in this scraper family.\n- `scripts/build-dataify-request.py` is the portable implementation and should be preferred.\n- `scripts/build-dataify-request.ps1` mirrors the same behavior for Windows users.\n- If a parameter has no options, the user must provide the value.\n- If a parameter has options, present those options back to the user before building the final request.\n- Do not assume `spider_parameters` always contains exactly one object. Multi-value tools may require multiple objects zipped by index.\n- Use the saved `url_example` only as a reference example. Do not assume the user wants the example values unless they explicitly confirm them.\n\nFile v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn74z5hmmwk21kw8tpphd9w21x86bkdf\",\n \"slug\": \"dataify-tiktok-comment-by-url\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1780276655869\n}\n\nFile v1.0.0:skill-card.md\n\n## Description:
\nPrepare Dataify builder requests for the tiktok.com scraper family rooted at tiktok_comment_by-url, including tool selection, parameter collection, and curl request generation with DATAIFY_API_TOKEN.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[dataify-server](https://clawhub.ai/user/dataify-server)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers and operators use this skill to prepare Dataify TikTok scraper builder requests, choose the relevant scraper tool, collect required parameters, and generate a curl command for the Dataify builder API.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Generated curl commands may expose DATAIFY_API_TOKEN if shared in chats, screenshots, logs, or issue reports.
\nMitigation: Treat DATAIFY_API_TOKEN as a secret, avoid sharing generated commands that include the token, and rotate the token if exposure occurs.
\nRisk: The referenced parameter catalog was not included in the scanned artifact.
\nMitigation: Verify that references/tool-params.json is present in the installed copy before relying on tool option lookup.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/dataify-server/dataify-tiktok-comment-by-url)
\n- [Dataify Dashboard](https://dataify.com/dashboard)
\n\n\n## Skill Output:
\n**Output Type(s):** [Shell commands, Configuration, Guidance]
\n**Output Format:** [Markdown with inline bash, PowerShell, and JSON examples]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Generates Dataify builder curl commands and normalized spider_parameters payloads.]
\n\n## Skill Version(s):
\n1.0.0 (source: server release evidence)
\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\nFile v1.0.0:SKILL.zh-CN.md\n\n# Dataify Builder Skill 中文版\n\n这个 skill 用于为 `tiktok.com` 下、以 `tiktok_comment_by-url` 为入口的 Dataify scraper 工具族生成 builder 请求。\n\n## 工作流程\n\n1. 先检查环境变量中是否存在 `DATAIFY_API_TOKEN`。\n2. 如果 token 缺失，提示用户前往 dataify官网 获取。\n3. 先让用户从下面的中文工具列表中明确选择一个工具：\n- 通过URL采集 (tiktok_comment_by-url)\n- 通过URL采集 (tiktok_shop_by-url)\n- 通过列表URL采集 (tiktok_posts_by-listurl)\n- 通过URL采集 (tiktok_profiles_by-url)\n- 通过搜索网址采集 (tiktok_profiles_by-listurl)\n4. 再读取 `references/tool-params.json`，根据 `tool_sign` 或中文工具名找到对应工具。\n5. 对所选工具的每个参数分别处理：\n - 如果 `input_mode` 是 `user_input`，让用户提供值。\n - 如果 `input_mode` 是 `select`，把已保存的可选项展示给用户，让用户选择。\n6. 默认优先使用 `scripts/build-dataify-request.py`，因为它是跨平台版本。\n7. Windows 下也可以使用 `scripts/build-dataify-request.ps1`。\n8. `spider_parameters` 必须是一个 JSON 数组。\n9. `spider_name` 固定取 `tiktok.com`。\n10. `spider_id` 固定取用户所选工具的 `tool_sign`。\n11. 始终包含 `spider_errors=true` 和 `file_name={{TasksID}}`。\n\n## 设置 DATAIFY_API_TOKEN\n\n推荐使用永久环境变量，而不是只在当前终端临时设置。\n\nWindows PowerShell，当前用户永久设置：\n\n```powershell\n[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")\n```\n\n然后重新打开 PowerShell。如果当前会话也要立即生效，再执行：\n\n```powershell\n$env:DATAIFY_API_TOKEN = \"your_token_here\"\n```\n\nmacOS 或 Linux，bash 永久设置：\n\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\nmacOS 或 Linux，zsh 永久设置：\n\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.zshrc\nsource ~/.zshrc\n```\n\n## 脚本用法\n\nPython：\n\n```bash\npython scripts/build-dataify-request.py --tool-sign --values-file values.json\n```\n\nPowerShell：\n\n```powershell\n& \".\\scripts\\build-dataify-request.ps1\" -ToolSign \"\" -ValuesFile \".\\values.json\"\n```\n\n`values.json` 可以是单个对象，也可以是对象数组。\n\n## 输出格式\n\n最终 `curl` 命令应为：\n\n```bash\ncurl -X POST 'https://scraperapi.dataify.com/builder' \\\n -H \"Authorization: Bearer $DATAIFY_API_TOKEN\" \\\n -H 'Content-Type: application/x-www-form-urlencoded' \\\n -d 'spider_name=tiktok.com' \\\n -d 'spider_id=' \\\n -d 'spider_parameters=[{\"param\":\"value\"}]' \\\n -d 'spider_errors=true' \\\n -d 'file_name={{TasksID}}'\n```\n\n## 参考文件\n\n- `references/tool-params.json` 保存了这个 skill 下所有工具及参数选项。\n- `scripts/build-dataify-request.py` 是首选的跨平台实现。\n- `scripts/build-dataify-request.ps1` 是 Windows PowerShell 版本。\n- 如果参数没有预设选项，必须向用户要值。\n- 如果参数有预设选项，先把选项展示给用户，再生成最终请求。\n- 不要假设 `spider_parameters` 永远只有一个对象；多值工具可能需要按索引生成多个对象。\n- `url_example` 仅作为参考，不要默认用户就要用示例值，除非用户明确确认。\n\nFile v1.0.0:agents/openai.yaml\n\ninterface:\n display_name: \"Dataify Tiktok Builder\"\n short_description: \"Prepare Dataify builder calls for tiktok.com\"\n default_prompt: \"Use $dataify-tiktok-comment-by-url to prepare a Dataify builder curl request.\"","readmeExcerpt":"Skill: Dataify Tiktok Builder Owner: dataify-server Summary: Collect Tiktok Builder data and return results Tags: latest:1.3.1 Version history: v1.3.1 | 2026-09-08T06:18:54.122Z | user Fix natural-language usage failures: validate required targets and URLs, preserve catalog references, default Amazon region safely, normalize Google News links, and improve UTF-8 error output. v1.3.0 | 2026-09-01T09:15:26.554Z | user 默","codeSnippets":[],"executableExamples":[{"language":"powershell","snippet":"[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")"},{"language":"powershell","snippet":"$env:DATAIFY_API_TOKEN = \"your_token_here\""},{"language":"bash","snippet":"echo 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc"},{"language":"bash","snippet":"echo 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.zshrc\nsource ~/.zshrc"},{"language":"bash","snippet":"python scripts/build-dataify-request.py --tool-sign --values-file values.json"},{"language":"powershell","snippet":"& \".\\scripts\\build-dataify-request.ps1\" -ToolSign \"\" -ValuesFile \".\\values.json\""}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: \"dataify-tiktok-comment-by-url\"\ndescription: \"Collect TikTok comments from a known TikTok content URL. Do not use for video download, profile collection, or general TikTok discovery.\"\n---\n\n# Dataify Builder Skill\n\nUse this skill to prepare Dataify builder requests for the scraper family rooted at `tiktok_comment_by-url` on `tiktok.com`.\n\n## Workflow\n\n1. Check whether `DATAIFY_API_TOKEN` exists in the environment.\n2. If the token is missing, stop and tell the user: `Dataify requires an API token. New accounts get 50 free credits, enough for about 6,000 trial results, valid for 7 days, and only successful requests are billed. Once registration is complete, tell me and I'll continue the current task.`.\n3. Ask the user to choose exactly one tool from the following Chinese list:\n- 通过URL采集 (tiktok_comment_by-url)\n- 通过URL采集 (tiktok_shop_by-url)\n- 通过列表URL采集 (tiktok_posts_by-listurl)\n- 通过URL采集 (tiktok_profiles_by-url)\n- 通过搜索网址采集 (tiktok_profiles_by-listurl)\n4. Read `references/tool-params.json` and find the chosen tool by `tool_sign` or Chinese tool name.\n5. For each parameter in the chosen tool:\n - If `input_mode` is `user_input`, ask the user for the value.\n - If `input_mode` is `select`, present the saved options to the user.\n6. Use `scripts/build-dataify-request.py` as the default cross-platform helper.\n7. Use `scripts/build-dataify-request.ps1` as the Windows PowerShell helper when needed.\n8. When a selectable parameter has a human-readable Chinese label, keep that label in `spider_parameters`. Do not replace it with a code such as `HK` unless the user explicitly asks for the coded value.\n9. Build `spider_parameters` as a JSON array.\n10. If every parameter has only one final value, build one object such as `[{\"searchurl\":\"...\",\"country\":\"Hong Kong\"}]`.\n11. If one or more parameters have multiple aligned values, zip them by index and build one object per row. Example: `[{\"search_url\":\"url1\",\"page_turning\":\"1\",\"max_num\":\"15\"},{\"search_url\":\"url2\",\"page_turning\":\"1\",\"max_num\":\"15\"}]`.\n12. If a parameter has one value while another parameter has multiple values, reuse the single value across every generated row.\n13. Set `spider_name` to `tiktok.com`.\n14. Set `spider_id` to the selected tool's `tool_sign`.\n15. Always include `spider_errors=true` and `file_name={{TasksID}}`.\n16. Return a curl command for `https://scraperapi.dataify.com/builder`.\n\n## Set DATAIFY_API_TOKEN\n\nPrefer a permanent environment-variable setup instead of setting the token only for the current terminal session.\n\nWindows PowerShell, permanent for the current user:\n```powershell\n[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")\n```\n\nThen reopen PowerShell. If the current session also needs the token immediately, run:\n```powershell\n$env:DATAIFY_API_TOKEN = \"your_token_here\"\n```\n\nmacOS or Linux, permanent for bash:\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\nmacOS or Linux, permanent for zs"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn74z5hmmwk21kw8tpphd9w21x86bkdf\",\n \"slug\": \"dataify-tiktok-comment-by-url\",\n \"version\": \"1.3.1\",\n \"publishedAt\": 1788848334122\n}"},{"path":"references/tool-params.json","content":"[{\"tool_name_cn\":\"评论URL\",\"tool_sign\":\"tiktok_comment_by-url\",\"spider_name\":\"tiktok.com\",\"params\":[{\"param\":\"url\",\"required\":true,\"input_mode\":\"user_input\",\"format\":\"url\",\"url_example\":\"https://www.tiktok.com/@user/video/1234567890\"}]},{\"tool_name_cn\":\"店铺URL\",\"tool_sign\":\"tiktok_shop_by-url\",\"spider_name\":\"tiktok.com\",\"params\":[{\"param\":\"url\",\"required\":true,\"input_mode\":\"user_input\",\"format\":\"url\",\"url_example\":\"https://www.tiktok.com/@shop\"}]},{\"tool_name_cn\":\"帖子列表URL\",\"tool_sign\":\"tiktok_posts_by-listurl\",\"spider_name\":\"tiktok.com\",\"params\":[{\"param\":\"listurl\",\"required\":true,\"input_mode\":\"user_input\",\"format\":\"url\",\"url_example\":\"https://www.tiktok.com/@user\"}]},{\"tool_name_cn\":\"个人资料URL\",\"tool_sign\":\"tiktok_profiles_by-url\",\"spider_name\":\"tiktok.com\",\"params\":[{\"param\":\"url\",\"required\":true,\"input_mode\":\"user_input\",\"format\":\"url\",\"url_example\":\"https://www.tiktok.com/@user\"}]},{\"tool_name_cn\":\"个人资料列表URL\",\"tool_sign\":\"tiktok_profiles_by-listurl\",\"spider_name\":\"tiktok.com\",\"params\":[{\"param\":\"listurl\",\"required\":true,\"input_mode\":\"user_input\",\"format\":\"url\",\"url_example\":\"https://www.tiktok.com/search/user?q=creator\"}]}]"},{"path":"skill-card.md","content":"## Description:\n\nCollect TikTok comments from a known TikTok content URL. Do not use for video download, profile collection, or general TikTok discovery.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[dataify-server](https://clawhub.ai/user/dataify-server)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and developers use this skill to prepare and optionally submit Dataify scraper requests for TikTok comment collection from a known content URL, then monitor the asynchronous task and return JSON results.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The artifact catalog exposes broader TikTok profile, shop, and post collection beyond the declared comment-by-URL task.\n\nMitigation: Narrow the catalog to the declared comment-by-URL task or require explicit tool selection review before execution.\n\nRisk: Credential setup guidance and helper scripts involve DATAIFY_API_TOKEN handling.\n\nMitigation: Use environment or secret-management controls, never paste or commit tokens, and verify only token presence rather than printing token values.\n\nRisk: Submitting Dataify tasks may spend credits and may collect profile-level data when broader tools are selected.\n\nMitigation: Require explicit confirmation before submissions that may spend credits, use high-volume settings, or collect profile-level data.\n\nRisk: Generated curl commands and task IDs can expose sensitive task access details.\n\nMitigation: Treat generated commands, task IDs, and result files as sensitive and avoid sharing them in public logs or tickets.\n\n## Reference(s):\n\n- [Tool parameter catalog](references/tool-params.json)\n- [ClawHub skill page](https://clawhub.ai/dataify-server/skills/dataify-tiktok-comment-by-url)\n- [Dataify Builder endpoint](https://scraperapi.dataify.com/builder)\n\n## Skill Output:\n\n**Output Type(s):** [Shell commands, JSON, Code, Configuration instructions, Guidance]\n\n**Output Format:** [Markdown with inline shell commands and JSON results]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires DATAIFY_API_TOKEN; generated curl commands, task IDs, and returned data should be treated as sensitive.]\n\n## Skill Version(s):\n\n1.3.1 (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."},{"path":"SKILL.zh-CN.md","content":"---\nname: \"dataify-tiktok-comment-by-url\"\ndescription: \"为 tiktok.com 上以 tiktok_comment_by-url 为根的 scraper 系列准备 Dataify builder 请求。当需要处理成功的 Dataify scraper detail 条目 tiktok_comment_by-url、让用户选择可用工具、读取已保存的 getToolParams 选项，并使用 DATAIFY_API_TOKEN 生成 scraperapi.dataify.com/builder curl 请求时，使用此 skill。\"\n---\n\n# Dataify Builder Skill 中文版\n\n这个 skill 用于为 `tiktok.com` 下、以 `tiktok_comment_by-url` 为入口的 Dataify scraper 工具族生成 builder 请求。\n\n## 工作流程\n\n1. 先检查环境变量中是否存在 `DATAIFY_API_TOKEN`。\n2. 如果 token 缺失，告诉用户：`Dataify 需要 API Token。新账号注册即得 50 免费积分，约可获得 6000 条试用结果，7 天有效，仅成功请求计费。注册完成后告诉我，我会继续当前任务。`。\n3. 先让用户从下面的中文工具列表中明确选择一个工具：\n- 通过URL采集 (tiktok_comment_by-url)\n- 通过URL采集 (tiktok_shop_by-url)\n- 通过列表URL采集 (tiktok_posts_by-listurl)\n- 通过URL采集 (tiktok_profiles_by-url)\n- 通过搜索网址采集 (tiktok_profiles_by-listurl)\n4. 再读取 `references/tool-params.json`，根据 `tool_sign` 或中文工具名找到对应工具。\n5. 对所选工具的每个参数分别处理：\n - 如果 `input_mode` 是 `user_input`，让用户提供值。\n - 如果 `input_mode` 是 `select`，把已保存的可选项展示给用户，让用户选择。\n6. 默认优先使用 `scripts/build-dataify-request.py`，因为它是跨平台版本。\n7. Windows 下也可以使用 `scripts/build-dataify-request.ps1`。\n8. `spider_parameters` 必须是一个 JSON 数组。\n9. `spider_name` 固定取 `tiktok.com`。\n10. `spider_id` 固定取用户所选工具的 `tool_sign`。\n11. 始终包含 `spider_errors=true` 和 `file_name={{TasksID}}`。\n\n## 设置 DATAIFY_API_TOKEN\n\n推荐使用永久环境变量，而不是只在当前终端临时设置。\n\nWindows PowerShell，当前用户永久设置：\n\n```powershell\n[Environment]::SetEnvironmentVariable(\"DATAIFY_API_TOKEN\", \"your_token_here\", \"User\")\n```\n\n然后重新打开 PowerShell。如果当前会话也要立即生效，再执行：\n\n```powershell\n$env:DATAIFY_API_TOKEN = \"your_token_here\"\n```\n\nmacOS 或 Linux，bash 永久设置：\n\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\nmacOS 或 Linux，zsh 永久设置：\n\n```bash\necho 'export DATAIFY_API_TOKEN=\"your_token_here\"' >> ~/.zshrc\nsource ~/.zshrc\n```\n\n## 脚本用法\n\nPython：\n\n```bash\npython scripts/build-dataify-request.py --tool-sign --values-file values.json\n```\n\nPowerShell：\n\n```powershell\n& \".\\scripts\\build-dataify-request.ps1\" -ToolSign \"\" -ValuesFile \".\\values.json\"\n```\n\n`values.json` 可以是单个对象，也可以是对象数组。\n\n## 输出格式\n\n最终 `curl` 命令应为：\n\n```bash\ncurl -X POST 'https://scraperapi.dataify.com/builder' \\\n -H \"Authorization: Bearer $DATAIFY_API_TOKEN\" \\\n -H 'Content-Type: application/x-www-form-urlencoded' \\\n -d 'spider_name=tiktok.com' \\\n -d 'spider_id=' \\\n -d 'spider_parameters=[{\"param\":\"value\"}]' \\\n -d 'spider_errors=true' \\\n -d 'file_name={{TasksID}}'\n```\n\n## 参考文件\n\n- `references/tool-params.json` 保存了这个 skill 下所有工具及参数选项。\n- `scripts/build-dataify-request.py` 是首选的跨平台实现。\n- `scripts/build-dataify-request.ps1` 是 Windows PowerShell 版本。\n- 如果参数没有预设选项，必须向用户要值。\n- 不要假设 `spider_parameters` 永远只有一个对象；多值工具可能需要按索引生成多个对象。\n- `url_example` 仅作为参考，不要默认用户就要用示例值，除非用户明确确认。\n\n## 参数交互策略\n\n- 当请求意图明确、只读、低风险且成本较低时，使用安全默认值直接执行。可以用一句话说明执行内容，但不要暂停等待确认。\n- 只在缺少必填输入、存在会明显改变结果的歧义、大批量或多页采集、媒体下载、会明显增加积分消耗、不可逆操作，或用户明确要求查看参数时询问。\n- 必须确认时，只展示会影响目标、范围、输出或成本的用户参数。优先使用一句简短说明；只有三个及以上关键值确实需要比较时才使用精简表格。\n- 不要展示固定字段、空的可选字段、未修改的默认值、凭据或内部实现参数，例如引擎选择、响应格式"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1592,"uniquenessScore":39,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T16:09:29.872Z","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":"2026-10-11T16:09:29.872Z","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":"2026-10-11T20:56:10.172Z","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"}]}}}