{"id":"3c2e6021-b0b4-42dc-80a6-6a1118241679","entityType":"agent","slug":"clawhub-a2888409-clipcat","name":"Clipcat - AI Viral Video Maker for TikTok Shop","canonicalUrl":"https://www.xpersona.co/agent/clawhub-a2888409-clipcat","canonicalPath":"/agent/clawhub-a2888409-clipcat","generatedAt":"2026-10-09T17:31:53.267Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T16:55:25.643Z","emptyReason":null},"description":"Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2.3K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s170hqqvyf7k3yzyvye2y7rdc983k940:clipcat","sourceUrl":"https://clawhub.ai/a2888409/clipcat","homepage":"https://clawhub.ai/a2888409/skills/clipcat","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/a2888409/clipcat","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/a2888409/skills/clipcat","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":51,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Clipcat - AI Viral Video Maker for TikTok Shop technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T16:55:25.643Z","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":"2026-10-09T16:55:25.643Z","emptyReason":null},"stars":null,"forks":null,"downloads":2263,"packageName":null,"latestVersion":"1.0.24","tractionLabel":"2.3K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T16:55:25.643Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T16:55:25.643Z","lastCrawledAt":"2026-10-09T16:55:25.643Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T16:55:25.643Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.24","createdAt":"2026-07-08T15:57:27.722Z","changelog":"- Updated Clipcat CLI download URLs to version 1.0.24 for all platforms. - API key setup instructions now include explicit configuration of the `--base-url` parameter. - Expanded instructions for handling commands that consume credits, including quoting and confirmation workflow. - Removed the file: skill-card.md.","fileCount":3,"zipByteSize":8970},{"version":"1.0.14","createdAt":"2026-06-27T13:31:24.200Z","changelog":"- Updated Clipcat CLI installers to version 1.0.18 for all platforms. - Expanded documentation to cover TikTok e-commerce data commands for 6 entity domains (creators, products, shops, videos, lives, keyword/image search). - Added detailed reference for new noun-verb entity commands and their usage. - Removed the skill-card.md file. - No changes to core functionality; improvements are documentation and installation updates.","fileCount":3,"zipByteSize":7163},{"version":"1.0.13","createdAt":"2026-05-21T10:38:52.557Z","changelog":"- Updated CLI installer URLs to v1.0.13 for all platforms. - No functional or documentation changes beyond version bump in installation sources.","fileCount":3,"zipByteSize":5366},{"version":"1.0.12","createdAt":"2026-05-02T14:16:23.404Z","changelog":"- Updated CLI binary download URLs to version 1.0.12 for all platforms. - Clarified async task flow: tasks always return immediately, with status polling done across turns—never block inside a single call. - Added typical task durations for image, breakdown, product_video, and replicate commands. - Recommended polling intervals for task status: ~30s for images, ~1-2 min for video-related tasks. - Reinforced best practices for agents using the skill in automated workflows.","fileCount":2,"zipByteSize":3676},{"version":"1.0.9","createdAt":"2026-04-29T14:03:43.357Z","changelog":"**Clipcat 1.0.9 → 1.0.11 changelog** - Updated all CLI installer URLs to use version 1.0.11 binaries for all supported platforms. - The list of available video models in documentation is updated, including new options: `grok_imagine` and `sora2_official_exp` with their durations, resolutions, and notes. - No behavioral or command-line changes detected apart from version bump and model documentation updates.","fileCount":2,"zipByteSize":3450},{"version":"1.0.8","createdAt":"2026-04-28T06:03:38.924Z","changelog":"- Updated Clipcat CLI to version 1.0.9 for all platforms (new download URLs). - Updated the list of available video generation models; only `veo3.1fast` model is now documented. - No code or logic changes—this is solely a CLI/tooling/platform update.","fileCount":2,"zipByteSize":3302},{"version":"1.0.7","createdAt":"2026-04-28T04:14:57.816Z","changelog":"- Updated Clipcat CLI binary URLs to version 1.0.8 for all supported platforms. - No other changes detected.","fileCount":2,"zipByteSize":3337},{"version":"1.0.6","createdAt":"2026-04-24T07:19:00.628Z","changelog":"- Added mention of GPT Image 2 for the `image` command, clarifying the image generation model in use. - Updated command descriptions to specify that image generation uses GPT Image 2. - No code or installation changes; documentation update only.","fileCount":2,"zipByteSize":3339}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s170hqqvyf7k3yzyvye2y7rdc983k940:clipcat","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s170hqqvyf7k3yzyvye2y7rdc983k940:clipcat` 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/a2888409/clipcat 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-a2888409-clipcat/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-a2888409-clipcat/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-a2888409-clipcat/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-a2888409-clipcat/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-a2888409-clipcat/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-a2888409-clipcat/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T17:31:53.262Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-a2888409-clipcat/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-a2888409-clipcat/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-a2888409-clipcat/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-a2888409-clipcat/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":"2026-10-09T16:55:25.643Z","emptyReason":null},"readme":"Skill: Clipcat - AI Viral Video Maker for TikTok Shop\n\nOwner: a2888409\n\nSummary: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.\n\nTags: latest:1.0.24\n\nVersion history:\n\nv1.0.24 | 2026-07-08T15:57:27.722Z | user\n\n- Updated Clipcat CLI download URLs to version 1.0.24 for all platforms.\n- API key setup instructions now include explicit configuration of the `--base-url` parameter.\n- Expanded instructions for handling commands that consume credits, including quoting and confirmation workflow.\n- Removed the file: skill-card.md.\n\nv1.0.14 | 2026-06-27T13:31:24.200Z | user\n\n- Updated Clipcat CLI installers to version 1.0.18 for all platforms.\n- Expanded documentation to cover TikTok e-commerce data commands for 6 entity domains (creators, products, shops, videos, lives, keyword/image search).\n- Added detailed reference for new noun-verb entity commands and their usage.\n- Removed the skill-card.md file.\n- No changes to core functionality; improvements are documentation and installation updates.\n\nv1.0.13 | 2026-05-21T10:38:52.557Z | user\n\n- Updated CLI installer URLs to v1.0.13 for all platforms.\n- No functional or documentation changes beyond version bump in installation sources.\n\nv1.0.12 | 2026-05-02T14:16:23.404Z | user\n\n- Updated CLI binary download URLs to version 1.0.12 for all platforms.\n- Clarified async task flow: tasks always return immediately, with status polling done across turns—never block inside a single call.\n- Added typical task durations for image, breakdown, product_video, and replicate commands.\n- Recommended polling intervals for task status: ~30s for images, ~1-2 min for video-related tasks.\n- Reinforced best practices for agents using the skill in automated workflows.\n\nv1.0.9 | 2026-04-29T14:03:43.357Z | user\n\n**Clipcat 1.0.9 → 1.0.11 changelog**\n\n- Updated all CLI installer URLs to use version 1.0.11 binaries for all supported platforms.\n- The list of available video models in documentation is updated, including new options: `grok_imagine` and `sora2_official_exp` with their durations, resolutions, and notes.\n- No behavioral or command-line changes detected apart from version bump and model documentation updates.\n\nv1.0.8 | 2026-04-28T06:03:38.924Z | user\n\n- Updated Clipcat CLI to version 1.0.9 for all platforms (new download URLs).\n- Updated the list of available video generation models; only `veo3.1fast` model is now documented.\n- No code or logic changes—this is solely a CLI/tooling/platform update.\n\nv1.0.7 | 2026-04-28T04:14:57.816Z | user\n\n- Updated Clipcat CLI binary URLs to version 1.0.8 for all supported platforms.\n- No other changes detected.\n\nv1.0.6 | 2026-04-24T07:19:00.628Z | user\n\n- Added mention of GPT Image 2 for the `image` command, clarifying the image generation model in use.\n- Updated command descriptions to specify that image generation uses GPT Image 2.\n- No code or installation changes; documentation update only.\n\nv1.0.5 | 2026-04-24T06:58:26.977Z | user\n\nclipcat 1.0.5\n\n- Updated Clipcat CLI installer to use version 1.0.7 binaries for all supported platforms.\n- Expanded SKILL.md documentation to include more detailed command options, new parameters, and improved workflow descriptions.\n- Clarified CLI command flags, especially for advanced usage, async behavior, and supported models/languages.\n- Adjusted examples and instructions for improved clarity and to match current CLI capabilities.\n\nv1.0.4 | 2026-04-12T03:10:41.416Z | user\n\n- Renamed skill from \"openclaw-support\" to \"clipcat\" for clarity.\n- Added an explicit, versioned, platform-specific installation spec for auto-install in OpenClaw, with direct download URLs for Windows, macOS (Intel/Apple), and Linux.\n- Install process now uses versioned binaries from trusted sources, instead of requiring users to run a shell script.\n- Updated installation instructions to reflect automated handling by OpenClaw.\n- No core functional changes to command usage or workflows.\n\nv1.0.3 | 2026-04-11T16:13:50.312Z | user\n\n- Switched from API documentation to CLI usage: documentation now focuses on using the Clipcat CLI instead of API endpoints.\n- Removed detailed endpoint and parameter information; directs users to `clipcat -h` and subcommand help for details.\n- Added concise overviews of CLI commands and workflows, including async task handling and local resume features.\n- Improved instructions on good usage patterns (JSON output, task ID management, CLI installation).\n- Removed README.md file.\n\nv1.0.2 | 2026-03-25T08:26:38.853Z | auto\n\n**Added viral TikTok video search and improved documentation.**\n\n- Introduced `/search` endpoint for finding viral TikTok videos by keyword, region, and time range.\n- Updated API overview and parameters to include video search and new documentation structure.\n- Improved endpoint descriptions and clarified available models and options.\n- Refined skill name/description for clearer TikTok e-commerce video creation focus.\n\nv1.0.1 | 2026-03-17T06:53:53.368Z | user\n\n- Updated the skill description to clarify that Clipcat integrates OpenClaw and Claude Code for end-to-end TikTok growth, in addition to the Clipcat.ai API.\n- No code changes; documentation only.\n\nv1.0.0 | 2026-03-17T06:48:51.847Z | user\n\nInitial release of Clipcat skill for TikTok e-commerce video creation.\n\n- Provides endpoints for analyzing, replicating, and generating TikTok-style e-commerce videos.\n- Supports viral video replication from TikTok/Douyin URLs, direct video URLs, or product images.\n- Includes video analysis to extract scripts, scenes, music, and more.\n- Allows one-click video downloads.\n- Supports multiple AI models, durations, resolutions, and languages.\n- Enforces task confirmation and prevents duplicate submissions for efficient task management.\n\nArchive index:\n\nArchive v1.0.24: 3 files, 8970 bytes\n\nFiles: skill-card.md (2965b), SKILL.md (18420b), _meta.json (127b)\n\nFile v1.0.24:SKILL.md\n\n---\nname: clipcat\ndescription: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.\nuser-invocable: true\nmetadata:\n {\n \"openclaw\":\n {\n \"skillKey\": \"clipcat\",\n \"requires\": { \"env\": [\"CLIPCAT_API_KEY\"] },\n \"primaryEnv\": \"CLIPCAT_API_KEY\",\n \"install\":\n [\n {\n \"id\": \"download-darwin-arm64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.24/clipcat_darwin_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Apple Silicon)\",\n },\n {\n \"id\": \"download-darwin-x64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.24/clipcat_darwin_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Intel)\",\n },\n {\n \"id\": \"download-linux-x64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.24/clipcat_linux_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux x86_64)\",\n },\n {\n \"id\": \"download-linux-arm64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.24/clipcat_linux_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux arm64)\",\n },\n {\n \"id\": \"download-windows-x64\",\n \"kind\": \"download\",\n \"os\": [\"win32\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.24/clipcat_windows_amd64.zip\",\n \"archive\": \"zip\",\n \"bins\": [\"clipcat.exe\"],\n \"label\": \"Install Clipcat CLI (Windows x86_64)\",\n },\n ],\n },\n \"homepage\": \"https://clipcat.ai\",\n }\n---\n\n# Clipcat CLI\n\nUse this skill when you need TikTok e-commerce video creation through `clipcat`.\n\nGet API key: https://clipcat.ai/workspace?modal=settings&tab=apikeys\n\nThis skill is intentionally short. Detailed flags and supported values belong to the CLI itself — always treat `clipcat -h` and `clipcat -h` as the primary reference.\n\n## Installation\n\nThis skill is auto-installed by OpenClaw using the declared `install` spec in the frontmatter above. OpenClaw downloads the platform-specific binary from versioned, immutable URLs under `https://static.clipcat.ai/public/cli/vX.Y.Z/` and places it under `~/.openclaw/tools/clipcat/`. No remote shell script is executed.\n\nAfter installation, configure your API key once:\n\n```bash\nclipcat config --api-key --base-url https://clipcat.ai\n```\n\n## What this CLI is for\n\n`clipcat` is the local entrypoint for all Clipcat AI video generation workflows:\n\n- Query TikTok e-commerce data across 6 entity domains: creators, products, shops, videos, lives, and keyword/image search (market intelligence, leaderboards, trends, relationships)\n- Replicate viral videos with your product\n- Generate product videos from images\n- Generate AI images from text prompts using GPT Image 2 (with optional reference images)\n- Analyze videos (script, scenes, music)\n- Download TikTok/Douyin videos\n- Query async task status\n\n## Default agent workflow\n\n1. Start with `clipcat -h` to see all commands.\n2. Before using any command, run `clipcat -h` to see flags.\n3. Default to JSON output. Only use `--pretty` when the result is meant for human terminal reading.\n4. Before any credit-consuming video command, quote the exact cost with\n `clipcat quote`, confirm it with the user, and submit with\n `--expected-credits` (see \"Confirming cost before paid video commands\").\n\n## Choosing the right command\n\n### TikTok e-commerce data — entity commands\n\nNoun-verb commands: `clipcat `. Run `clipcat -h` for verbs\nand `clipcat -h` for flags.\n\n- `creator ` — creators/influencers\n- `product ` — TikTok Shop products\n- `seller ` — TikTok Shop shops\n- `video ` — videos\n- `live detail` — live-room detail (only while live)\n- `find ` — keyword/image search; `find all` is the broad fallback\n\n**`--mode offline|realtime`** (only on `creator detail|videos`, `product comments`,\n`seller products`, `video detail`): default is the safe choice — omit unless the\nuser needs latest/current (realtime) vs history/trend/leaderboard (offline). Never\nsay \"offline/realtime\" to users; phrase as latest vs historical.\n\n**Pagination**: offline list/rank commands take `--page` / `--page-size` (and\n`--max-pages` to auto-fetch several pages); realtime lists take `--offset` /\n`--cursor` / `--scroll-param` echoed back from a prior page.\n\n**Data-query playbook (dense):**\n\n- **Chain ids, don't guess them.** Discover first (` list|rank`, `find …`),\n take the id from the result, then call `detail` / `trend` / relationship verbs.\n Detail verbs take **comma-separated batches** (`--user-ids`, `--product-ids`,\n `--video-ids`, ≤10).\n- **Seed relationships from commerce-active entities.** Sub-resource verbs\n (`creator products|lives`, `product creators|videos|lives`, `seller lives`,\n `video products`) return `[]` for low-activity ids. Pull seeds from `… rank` or a\n sorted `… list` (top sales/followers), not an arbitrary row, or expect empties.\n- **`… rank` needs a _recent_ `--date`.** Pass any day in the target period — the backend\n auto-snaps it to the period anchor (week→that week's Monday, month→that month's 1st) and\n back to the latest _complete_ period (data is T+1), so a mid-week / mid-month date, or even\n _today_, still resolves. But it must fall within the freshness window keyed to `--rank-type`:\n **day ≤30d, week ≤6mo, month ≤12mo** back from _today_. A too-**old** date (e.g. last year)\n is rejected upstream as `rant_type N only support …` — move it **forward toward today**;\n don't switch rank-type.\n- **Category filtering is numeric and split by level.** To scope `rank` / `list` to a\n category, first run `category resolve --keyword ` (e.g. `lipstick` / `口红`; CJK\n auto-uses the zh tree). It returns each match's level + ancestor ids `{l1_id, l2_id?,\nl3_id?}` (ids work for any region). Pass the id for the level the target command takes:\n **product/seller** rank/list use **L1→`--category-id`, L2→`--category-l2-id`,\n L3→`--category-l3-id`** (`--category-id` is L1-only — don't put an L2/L3 id there);\n **creator** rank takes any level via `--product-category-id`; **video** rank only\n accepts L1 (`l1_id`). Low-confidence `hint` → run `category tree` (L1+L2 overview), pick\n the branch by meaning, then `category tree --parent ` to drill into its L3\n leaves. For plain keyword _search_ (no leaderboard), `find products --keyword` needs no id.\n- **`find products` returns product_id only** (it's a search index). For title /\n price / metrics, chain the ids into `product detail`.\n- **Empty `[]` / `null` means \"none\", not an error.** Known thin/quirky:\n `creator region` (unreliable → read `region` from `creator detail` instead),\n `video captions` (many videos have none), `live detail` (only while a room is\n live), `seller products --mode realtime` (empty when no live inventory; the\n offline default already covers it).\n- Responses are **server-trimmed to signal** (ids, core metrics, names, key links;\n images already converted to accessible URLs) — no raw-blob handling needed.\n\n### Video generation & tools\n\n- `quote` — return the exact credit cost of one specific generation (`--model` + `--resolution` + `--duration`, plus `--url`/`--social` for a TikTok/Douyin replicate, plus `--enhance` for super-resolution). The primary way to quote a paid command: the server does all the math and hands back `totalCredits` (already includes the enhance fee) plus `enhanceCredits` / `enhanceBlocked` (see \"Confirming cost before paid video commands\" and \"Super-resolution\").\n- `models` — browse all available video models with their credit costs (discrete → `prices`, range → `creditsPerSecond`) and your balance. Use it when the user hasn't picked a model yet, or an unavailable one is reported.\n- `replicate` — replicate a viral video with your product images (auto-detects URL type); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed; supports `--model`, `--duration`, `--size` (only `9:16` or `16:9`), `--lang`, `--resolution`, `--enhance` (super-resolution, see below), `--character-id`, `--expected-credits`\n- `product_video` — generate video from product images only (no reference video); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed; `--size` only accepts `9:16` or `16:9`; supports `--enhance` (super-resolution, see below), `--expected-credits`\n- `image` — generate an AI image from a text prompt using **GPT Image 2** model; optionally supply up to 5 reference images via `--image` (local file) or `--image-url` (URL). Use `--aspect-ratio` to pick `1:1` (default) / `16:9` / `9:16`. **Dimension hints (9:16/16:9/1:1, portrait/landscape/square, 竖版/横版/方图, banner, wallpaper) must appear in BOTH `--prompt` and `--aspect-ratio`** — `--aspect-ratio` sets canvas, the prompt hint anchors framing. Don't invent dimensions the user didn't ask for.\n- `list_images` — list image generation tasks from server; supports `--status` / `--limit` / `--page` filters\n- `breakdown` — analyze a video (script, scenes, music); returns cached result immediately if previously analyzed\n- `download` — download TikTok/Douyin video (returns signed URL); cached results return immediately\n- `query_task` — check status of a task by ID and type (`--type replicate | product | breakdown | download | image`). Omit `--task-id` to resume the latest local task. With `--enhance`, each `videos[]` item carries its own `status` / `enhanceStatus` (see \"Super-resolution\").\n- `list_tasks` — list recent **video-related** tasks from server (`--type` required: `replicate | product | breakdown | download`). Image tasks use `list_images`.\n\n## Confirming cost before paid video commands\n\n`replicate` and `product_video` consume credits. Always confirm cost first — and\n**never compute the credits yourself**, let `clipcat quote` return them:\n\n1. Run `clipcat quote` with the SAME parameters you'll submit (`--model`,\n `--resolution`, `--duration`; for a TikTok/Douyin replicate also pass the\n `--url`, which auto-adds the download surcharge; for super-resolution also pass\n `--enhance`). It returns `totalCredits` (the server does all the math —\n per-second rates, download surcharge, deferred enhance fee) and your\n `remainingCredits`.\n2. Show the user the model, duration, resolution and that `totalCredits`, and get\n explicit approval.\n3. Submit with `--expected-credits `. The server rejects the request\n only if the real cost is **higher** than what you pass, so you can never\n overcharge (a cheaper real cost — cache hit, promo — just goes through). On a\n rejection it returns the current cost — re-confirm that number with the user\n and resubmit with the updated `--expected-credits`.\n\nWhen the user hasn't chosen a model yet (or you need the full menu), run `clipcat\nmodels` to list every available model and its cost, then `clipcat quote` the pick.\n\nPremium models (e.g. `seedance2`, `happyhorse10`) require a paid plan; `clipcat\nquote` flags them (`premiumBlocked`) and the server rejects them for free users.\n\n## Super-resolution (`--enhance`)\n\n`replicate` and `product_video` accept `--enhance 720p|1080p|2k` to upscale the\nfinished video. Rules:\n\n- **Tier must be strictly higher than the generated resolution**: 480p → 720p /\n 1080p / 2k, 720p → 1080p / 2k, 1080p → 2k, 2k → no option. The CLI only\n enum-checks the value; the server enforces the tier ladder.\n- **Paid plans only.** Free users are rejected on submit; `clipcat quote --enhance`\n flags this as `enhanceBlocked: true` (upgrade needed).\n- **Cost** = ceil(duration_sec / 10) × tier rate (`720p`=10, `1080p`=20, `2k`=30\n credits per 10s). It is **deferred** — charged only after the base video\n succeeds. `quote` returns it as `enhanceCredits`, already folded into\n `totalCredits`; submit that `totalCredits` via `--expected-credits`.\n- **Status semantics** (`query_task`): once the base video is ready it appears in\n `videos[]` with `status: enhancing` and a usable `videoUrl` (the original), but\n the **task reaches its final completed state only after enhance finishes** (a\n standard 1-min video takes ~6-10 min extra). `enhanceStatus: failed` → the task\n still completes and delivers the original video, and the enhance fee is refunded.\n\n```bash\nclipcat quote --model seedance2 --resolution 480p --duration 8 --enhance 1080p\n# → seedance2 480p 8s → 320 credits + 20 enhance (1080p) → total 340 credits\nclipcat product_video --image product.jpg --model seedance2 --duration 8 \\\n --resolution 480p --size 9:16 --enhance 1080p --expected-credits 340\n```\n\n## replicate: URL type auto-detection\n\n`clipcat replicate` automatically detects the URL type:\n\n- **TikTok/Douyin link** → calls `/replicate_from_social` (costs **10 extra credits** for download)\n- **Direct video URL** → calls `/replicate`\n\nAlways inform the user about the extra credits before running with a social URL.\n\n## clipcat:// asset references\n\n`clipcat://...` strings seen in earlier turns are stable asset references. Pass them **verbatim** to any `--image-url` / `--character-id` flag — never prepend `https://` or modify them. See subcommand `-h` for details.\n\n## Async task rules\n\n`replicate`, `product_video`, `image`, and `breakdown` are async. All four\n**submit and return immediately** with a task ID — they never block.\n\nTypical durations: `image` ~3 min, `breakdown` a few minutes, `product_video` /\n`replicate` 10+ min. **Never try to wait synchronously inside a single tool\ncall** — every realistic agent harness has a tool-call timeout (commonly 60s)\nthat will kill the call long before the task is done. Always go submit → return\n→ poll across turns.\n\n1. Task ID is saved locally to `~/.clipcat/tasks.json` automatically.\n2. Check status with `clipcat query_task --task-id --type `. Each\n call returns immediately with the current status. Omit `--task-id` to resume\n the latest task. Re-invoke the command across turns (suggested cadence:\n ~30s for `image`, ~1-2 min for `breakdown` / `product_video` / `replicate`)\n until `status` is `completed` or `failed`.\n3. Use `clipcat list_tasks --type ` to\n see tasks of a given type from the server.\n\n## query_task: auto-resume\n\n`clipcat query_task` with no flags automatically reads the latest task from `~/.clipcat/tasks.json` and resumes it. No need to remember task IDs.\n\n## Available models\n\nTrial models are available to all users; standard models require a paid plan.\n\n| Model ID | Duration | Resolution | Notes |\n| -------------------- | ------------------- | ----------------- | ------------------------------------------------------------- |\n| `veo3.1fast` | 8s, 16s, 24s | 720p, 1080p | **Trial**. Google Veo 3.1 Fast, balanced quality and cost |\n| `veo3.1pro` | 8s, 16s, 24s | 720p, 1080p | **Trial**. Google Veo 3.1 Pro, high-quality variant |\n| `omini_flash` | 10s | 720p, 1080p | **Trial**. Gemini Omni Flash, Google's newest model |\n| `grok_imagine` | 10s, 15s, 20s, 30s | 720p | **Trial**, default. 9:16 aspect ratio only, longer clips |\n| `seedance2` | 4-15s (any integer) | 480p, 720p, 1080p | Standard (paid). ByteDance Seedance 2, top quality |\n| `seedance2_fast` | 4-15s (any integer) | 480p, 720p, 1080p | Standard (paid). ByteDance Seedance 2 Fast, fast variant |\n| `happyhorse10` | 3-15s (any integer) | 720p, 1080p | Standard (paid). Alibaba HappyHorse 1.0 |\n| `sora2_official_exp` | 4s, 8s, 12s | 720p | Standard (paid). OpenAI Sora 2 official channel, 9:16 or 16:9 |\n\nAlways check `clipcat replicate -h` for the current model list, and `clipcat\nmodels` for the authoritative live per-combination credit costs and your balance.\n\n## Supported languages (`--lang`)\n\n`en` `zh` `fr` `de` `ms` `vi` `th` `ja` `ko` `id` `fil` `es`\n\n## Region (`--region`)\n\nISO 3166-1 alpha-2, uppercase: `US` `GB` `DE` `ES` `FR` `IT` `JP` `MX` `BR` `ID` `MY` `PH` `SG` `TH` `VN`. Server-enforced; an out-of-range code returns the current allowed list.\n\n## Good agent behavior\n\n- Run `clipcat -h` first if unsure which command to use.\n- For paid video commands (`replicate`, `product_video`): quote the exact cost with `clipcat quote` (same params you'll submit), show the user the model / duration / resolution / `totalCredits`, get explicit approval, then submit with `--expected-credits `. Never compute the credits yourself — let `clipcat quote` return them.\n- Keep record of task IDs; re-invoke `query_task` across turns to track long-running tasks.\n- Preserve signed video URLs intact — they contain `X-Amz-*` params that break if truncated.\n- Agents should prefer the default JSON output.\n- Use `--pretty` only for human-facing terminal display.\n\nFile v1.0.24:_meta.json\n\n{\n \"ownerId\": \"kn7f8ddmmnk1fjgrhxfxbhcmgs831vq7\",\n \"slug\": \"clipcat\",\n \"version\": \"1.0.24\",\n \"publishedAt\": 1783526247722\n}\n\nFile v1.0.24:skill-card.md\n\n## Description:\n\nClipcat helps agents use the Clipcat CLI for TikTok e-commerce video search, product insights, viral video replication, product-to-video generation, video analysis, and video download workflows.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[a2888409](https://clawhub.ai/user/a2888409)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal developers, creators, and commerce teams use this skill to direct agents through Clipcat CLI workflows for TikTok Shop research, product video generation, viral video replication, and asynchronous task tracking.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill installs a third-party native Clipcat CLI without pinned checksums or signature verification.\n\nMitigation: Install only when the Clipcat distribution channel is trusted, and request or verify pinned checksums or signatures for platform archives before deployment.\n\nRisk: The Clipcat CLI uses a Clipcat API key and may process local media paths or remote asset URLs supplied by the user.\n\nMitigation: Use a scoped API key where available, avoid sharing unnecessary local media, and review commands before exposing sensitive file paths or assets.\n\nRisk: Some video generation commands consume paid credits.\n\nMitigation: Run `clipcat quote` with the same parameters, show the returned total cost, get explicit user approval, and submit with `--expected-credits`.\n\n## Reference(s):\n\n- [Clipcat Skill Page](https://clawhub.ai/a2888409/skills/clipcat)\n- [Clipcat Homepage](https://clipcat.ai)\n- [Clipcat API Key Settings](https://clipcat.ai/workspace?modal=settings&tab=apikeys)\n- [Clipcat CLI macOS Apple Silicon archive](https://static.clipcat.ai/public/cli/v1.0.24/clipcat_darwin_arm64.tar.gz)\n- [Clipcat CLI macOS Intel archive](https://static.clipcat.ai/public/cli/v1.0.24/clipcat_darwin_amd64.tar.gz)\n- [Clipcat CLI Linux x86_64 archive](https://static.clipcat.ai/public/cli/v1.0.24/clipcat_linux_amd64.tar.gz)\n- [Clipcat CLI Linux arm64 archive](https://static.clipcat.ai/public/cli/v1.0.24/clipcat_linux_arm64.tar.gz)\n- [Clipcat CLI Windows x86_64 archive](https://static.clipcat.ai/public/cli/v1.0.24/clipcat_windows_amd64.zip)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Code, Shell commands, Configuration, Guidance]\n\n**Output Format:** [Markdown guidance with inline shell commands and CLI JSON output expectations]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires CLIPCAT_API_KEY and the Clipcat CLI; paid video commands should be quoted and explicitly confirmed before submission.]\n\n## Skill Version(s):\n\n1.0.24 (source: server-resolved 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\nArchive v1.0.14: 3 files, 7163 bytes\n\nFiles: skill-card.md (2632b), SKILL.md (14041b), _meta.json (127b)\n\nFile v1.0.14:SKILL.md\n\n---\nname: clipcat\ndescription: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.\nuser-invocable: true\nmetadata:\n {\n \"openclaw\":\n {\n \"skillKey\": \"clipcat\",\n \"requires\": { \"env\": [\"CLIPCAT_API_KEY\"] },\n \"primaryEnv\": \"CLIPCAT_API_KEY\",\n \"install\":\n [\n {\n \"id\": \"download-darwin-arm64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.18/clipcat_darwin_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Apple Silicon)\",\n },\n {\n \"id\": \"download-darwin-x64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.18/clipcat_darwin_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Intel)\",\n },\n {\n \"id\": \"download-linux-x64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.18/clipcat_linux_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux x86_64)\",\n },\n {\n \"id\": \"download-linux-arm64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.18/clipcat_linux_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux arm64)\",\n },\n {\n \"id\": \"download-windows-x64\",\n \"kind\": \"download\",\n \"os\": [\"win32\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.18/clipcat_windows_amd64.zip\",\n \"archive\": \"zip\",\n \"bins\": [\"clipcat.exe\"],\n \"label\": \"Install Clipcat CLI (Windows x86_64)\",\n },\n ],\n },\n \"homepage\": \"https://clipcat.ai\",\n }\n---\n\n# Clipcat CLI\n\nUse this skill when you need TikTok e-commerce video creation through `clipcat`.\n\nGet API key: https://clipcat.ai/workspace?modal=settings&tab=apikeys\n\nThis skill is intentionally short. Detailed flags and supported values belong to the CLI itself — always treat `clipcat -h` and `clipcat -h` as the primary reference.\n\n## Installation\n\nThis skill is auto-installed by OpenClaw using the declared `install` spec in the frontmatter above. OpenClaw downloads the platform-specific binary from versioned, immutable URLs under `https://static.clipcat.ai/public/cli/vX.Y.Z/` and places it under `~/.openclaw/tools/clipcat/`. No remote shell script is executed.\n\nAfter installation, configure your API key once:\n\n```bash\nclipcat config --api-key \n```\n\n## What this CLI is for\n\n`clipcat` is the local entrypoint for all Clipcat AI video generation workflows:\n\n- Query TikTok e-commerce data across 6 entity domains: creators, products, shops, videos, lives, and keyword/image search (market intelligence, leaderboards, trends, relationships)\n- Replicate viral videos with your product\n- Generate product videos from images\n- Generate AI images from text prompts using GPT Image 2 (with optional reference images)\n- Analyze videos (script, scenes, music)\n- Download TikTok/Douyin videos\n- Query async task status\n\n## Default agent workflow\n\n1. Start with `clipcat -h` to see all commands.\n2. Before using any command, run `clipcat -h` to see flags.\n3. Default to JSON output. Only use `--pretty` when the result is meant for human terminal reading.\n4. Warn the user before running commands that consume credits.\n\n## Choosing the right command\n\n### TikTok e-commerce data — entity commands\n\nNoun-verb commands: `clipcat `. Run `clipcat -h` for verbs\nand `clipcat -h` for flags.\n\n- `creator ` — creators/influencers\n- `product ` — TikTok Shop products\n- `seller ` — TikTok Shop shops\n- `video ` — videos\n- `live detail` — live-room detail (only while live)\n- `find ` — keyword/image search; `find all` is the broad fallback\n\n**`--mode offline|realtime`** (only on `creator detail|videos`, `product comments`,\n`seller products`, `video detail`): default is the safe choice — omit unless the\nuser needs latest/current (realtime) vs history/trend/leaderboard (offline). Never\nsay \"offline/realtime\" to users; phrase as latest vs historical.\n\n**Pagination**: offline list/rank commands take `--page` / `--page-size` (and\n`--max-pages` to auto-fetch several pages); realtime lists take `--offset` /\n`--cursor` / `--scroll-param` echoed back from a prior page.\n\n**Data-query playbook (dense):**\n\n- **Chain ids, don't guess them.** Discover first (` list|rank`, `find …`),\n take the id from the result, then call `detail` / `trend` / relationship verbs.\n Detail verbs take **comma-separated batches** (`--user-ids`, `--product-ids`,\n `--video-ids`, ≤10).\n- **Seed relationships from commerce-active entities.** Sub-resource verbs\n (`creator products|lives`, `product creators|videos|lives`, `seller lives`,\n `video products`) return `[]` for low-activity ids. Pull seeds from `… rank` or a\n sorted `… list` (top sales/followers), not an arbitrary row, or expect empties.\n- **`… rank` needs a *recent* `--date`.** Pass any day in the target period — the backend\n auto-snaps it to the period anchor (week→that week's Monday, month→that month's 1st) and\n back to the latest *complete* period (data is T+1), so a mid-week / mid-month date, or even\n *today*, still resolves. But it must fall within the freshness window keyed to `--rank-type`:\n **day ≤30d, week ≤6mo, month ≤12mo** back from *today*. A too-**old** date (e.g. last year)\n is rejected upstream as `rant_type N only support …` — move it **forward toward today**;\n don't switch rank-type.\n- **Category filtering is numeric and split by level.** To scope `rank` / `list` to a\n category, first run `category resolve --keyword ` (e.g. `lipstick` / `口红`; CJK\n auto-uses the zh tree). It returns each match's level + ancestor ids `{l1_id, l2_id?,\n l3_id?}` (ids work for any region). Pass the id for the level the target command takes:\n **product/seller** rank/list use **L1→`--category-id`, L2→`--category-l2-id`,\n L3→`--category-l3-id`** (`--category-id` is L1-only — don't put an L2/L3 id there);\n **creator** rank takes any level via `--product-category-id`; **video** rank only\n accepts L1 (`l1_id`). Low-confidence `hint` → run `category tree` (L1+L2 overview), pick\n the branch by meaning, then `category tree --parent ` to drill into its L3\n leaves. For plain keyword *search* (no leaderboard), `find products --keyword` needs no id.\n- **`find products` returns product_id only** (it's a search index). For title /\n price / metrics, chain the ids into `product detail`.\n- **Empty `[]` / `null` means \"none\", not an error.** Known thin/quirky:\n `creator region` (unreliable → read `region` from `creator detail` instead),\n `video captions` (many videos have none), `live detail` (only while a room is\n live), `seller products --mode realtime` (empty when no live inventory; the\n offline default already covers it).\n- Responses are **server-trimmed to signal** (ids, core metrics, names, key links;\n images already converted to accessible URLs) — no raw-blob handling needed.\n\n### Video generation & tools\n\n- `replicate` — replicate a viral video with your product images (auto-detects URL type); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed; supports `--model`, `--duration`, `--size` (only `9:16` or `16:9`), `--lang`, `--resolution`, `--character-id`\n- `product_video` — generate video from product images only (no reference video); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed; `--size` only accepts `9:16` or `16:9`\n- `image` — generate an AI image from a text prompt using **GPT Image 2** model; optionally supply up to 5 reference images via `--image` (local file) or `--image-url` (URL). Use `--aspect-ratio` to pick `1:1` (default) / `16:9` / `9:16`. **Dimension hints (9:16/16:9/1:1, portrait/landscape/square, 竖版/横版/方图, banner, wallpaper) must appear in BOTH `--prompt` and `--aspect-ratio`** — `--aspect-ratio` sets canvas, the prompt hint anchors framing. Don't invent dimensions the user didn't ask for.\n- `list_images` — list image generation tasks from server; supports `--status` / `--limit` / `--page` filters\n- `breakdown` — analyze a video (script, scenes, music); returns cached result immediately if previously analyzed\n- `download` — download TikTok/Douyin video (returns signed URL); cached results return immediately\n- `query_task` — check status of a task by ID and type (`--type replicate | product | breakdown | download | image`). Omit `--task-id` to resume the latest local task.\n- `list_tasks` — list recent **video-related** tasks from server (`--type` required: `replicate | product | breakdown | download`). Image tasks use `list_images`.\n\n## replicate: URL type auto-detection\n\n`clipcat replicate` automatically detects the URL type:\n\n- **TikTok/Douyin link** → calls `/replicate_from_social` (costs **1 extra credit** for download)\n- **Direct video URL** → calls `/replicate`\n\nAlways inform the user about the extra credit before running with a social URL.\n\n## clipcat:// asset references\n\n`clipcat://...` strings seen in earlier turns are stable asset references. Pass them **verbatim** to any `--image-url` / `--character-id` flag — never prepend `https://` or modify them. See subcommand `-h` for details.\n\n## Async task rules\n\n`replicate`, `product_video`, `image`, and `breakdown` are async. All four\n**submit and return immediately** with a task ID — they never block.\n\nTypical durations: `image` ~3 min, `breakdown` a few minutes, `product_video` /\n`replicate` 10+ min. **Never try to wait synchronously inside a single tool\ncall** — every realistic agent harness has a tool-call timeout (commonly 60s)\nthat will kill the call long before the task is done. Always go submit → return\n→ poll across turns.\n\n1. Task ID is saved locally to `~/.clipcat/tasks.json` automatically.\n2. Check status with `clipcat query_task --task-id --type `. Each\n call returns immediately with the current status. Omit `--task-id` to resume\n the latest task. Re-invoke the command across turns (suggested cadence:\n ~30s for `image`, ~1-2 min for `breakdown` / `product_video` / `replicate`)\n until `status` is `completed` or `failed`.\n3. Use `clipcat list_tasks --type ` to\n see tasks of a given type from the server.\n\n## query_task: auto-resume\n\n`clipcat query_task` with no flags automatically reads the latest task from `~/.clipcat/tasks.json` and resumes it. No need to remember task IDs.\n\n## Available models\n\nTrial channels are per-clip pricing; standard channels are per-second pricing.\n\n| Model ID | Duration | Resolution | Notes |\n| -------------------- | --------------------- | ----------------- | ----------------------------------------------------------------- |\n| `sora2_official_exp` | 4s, 8s, 12s | 720p | **Trial**, default. OpenAI Sora 2 official channel, 9:16 or 16:9 |\n| `veo3.1fast` | 8s, 16s, 24s | 720p, 1080p | **Trial**. Google Veo 3.1 Fast, balanced quality and cost |\n| `veo3.1pro` | 8s, 16s, 24s | 720p, 1080p | **Trial**. Google Veo 3.1 Pro, high-quality variant |\n| `omini_flash` | 10s | 720p, 1080p | **Trial**. Gemini Omni Flash, Google's newest model |\n| `grok_imagine` | 10s, 15s, 20s, 30s | 720p | **Trial**. 9:16 aspect ratio only, longer clips |\n| `seedance2` | 4-15s (any integer) | 480p, 720p, 1080p | Standard. ByteDance Seedance 2, top quality |\n| `seedance2_fast` | 4-15s (any integer) | 480p, 720p, 1080p | Standard. ByteDance Seedance 2 Fast, fast variant |\n| `happyhorse10` | 3-15s (any integer) | 720p, 1080p | Standard. Alibaba HappyHorse 1.0 |\n\nAlways check `clipcat replicate -h` for the current model list.\n\n## Supported languages (`--lang`)\n\n`en` `zh` `fr` `de` `ms` `vi` `th` `ja` `ko` `id` `fil` `es`\n\n## Region (`--region`)\n\nISO 3166-1 alpha-2, uppercase: `US` `GB` `DE` `ES` `FR` `IT` `JP` `MX` `BR` `ID` `MY` `PH` `SG` `TH` `VN`. Server-enforced; an out-of-range code returns the current allowed list.\n\n## Good agent behavior\n\n- Run `clipcat -h` first if unsure which command to use.\n- Show parameters to user and get confirmation before running paid commands.\n- Keep record of task IDs; re-invoke `query_task` across turns to track long-running tasks.\n- Preserve signed video URLs intact — they contain `X-Amz-*` params that break if truncated.\n- Agents should prefer the default JSON output.\n- Use `--pretty` only for human-facing terminal display.\n\nFile v1.0.14:_meta.json\n\n{\n \"ownerId\": \"kn7f8ddmmnk1fjgrhxfxbhcmgs831vq7\",\n \"slug\": \"clipcat\",\n \"version\": \"1.0.14\",\n \"publishedAt\": 1782567084200\n}\n\nFile v1.0.14:skill-card.md\n\n## Description:
\nClipcat is a TikTok e-commerce video creation skill for video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download through the Clipcat CLI.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[a2888409](https://clawhub.ai/user/a2888409)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nDevelopers, operators, and e-commerce marketers use this skill to operate the Clipcat CLI for TikTok Shop research, AI video and image generation, viral-video replication, breakdown analysis, downloads, and async task tracking.
\n\n### Deployment Geography for Use:
\nGlobal, subject to Clipcat service availability and supported marketplace region flags.
\n\n## Known Risks and Mitigations:
\nRisk: Review before execution as proposals could introduce incorrect or misleading guidance into skills.
\nMitigation: Review and scan skill before deployment.
\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/a2888409/skills/clipcat)
\n- [Clipcat homepage](https://clipcat.ai)
\n- [Clipcat API key settings](https://clipcat.ai/workspace?modal=settings&tab=apikeys)
\n- [Clipcat CLI macOS Apple Silicon installer](https://static.clipcat.ai/public/cli/v1.0.18/clipcat_darwin_arm64.tar.gz)
\n- [Clipcat CLI macOS Intel installer](https://static.clipcat.ai/public/cli/v1.0.18/clipcat_darwin_amd64.tar.gz)
\n- [Clipcat CLI Linux x86_64 installer](https://static.clipcat.ai/public/cli/v1.0.18/clipcat_linux_amd64.tar.gz)
\n- [Clipcat CLI Linux arm64 installer](https://static.clipcat.ai/public/cli/v1.0.18/clipcat_linux_arm64.tar.gz)
\n- [Clipcat CLI Windows x86_64 installer](https://static.clipcat.ai/public/cli/v1.0.18/clipcat_windows_amd64.zip)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, shell commands, configuration, guidance]
\n**Output Format:** [Markdown guidance with CLI commands and JSON-oriented command output.]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Requires CLIPCAT_API_KEY. Commands may consume Clipcat credits and may return task IDs, generated media links, or signed output URLs that should be treated as sensitive access links.]
\n\n## Skill Version(s):
\n1.0.14 (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\nArchive v1.0.13: 3 files, 5366 bytes\n\nFiles: skill-card.md (2647b), SKILL.md (10121b), _meta.json (127b)\n\nFile v1.0.13:SKILL.md\n\n---\nname: clipcat\ndescription: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.\nuser-invocable: true\nmetadata:\n {\n \"openclaw\":\n {\n \"skillKey\": \"clipcat\",\n \"requires\": { \"env\": [\"CLIPCAT_API_KEY\"] },\n \"primaryEnv\": \"CLIPCAT_API_KEY\",\n \"install\":\n [\n {\n \"id\": \"download-darwin-arm64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.13/clipcat_darwin_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Apple Silicon)\",\n },\n {\n \"id\": \"download-darwin-x64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.13/clipcat_darwin_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Intel)\",\n },\n {\n \"id\": \"download-linux-x64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.13/clipcat_linux_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux x86_64)\",\n },\n {\n \"id\": \"download-linux-arm64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.13/clipcat_linux_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux arm64)\",\n },\n {\n \"id\": \"download-windows-x64\",\n \"kind\": \"download\",\n \"os\": [\"win32\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.13/clipcat_windows_amd64.zip\",\n \"archive\": \"zip\",\n \"bins\": [\"clipcat.exe\"],\n \"label\": \"Install Clipcat CLI (Windows x86_64)\",\n },\n ],\n },\n \"homepage\": \"https://clipcat.ai\",\n }\n---\n\n# Clipcat CLI\n\nUse this skill when you need TikTok e-commerce video creation through `clipcat`.\n\nGet API key: https://clipcat.ai/workspace?modal=settings&tab=apikeys\n\nThis skill is intentionally short. Detailed flags and supported values belong to the CLI itself — always treat `clipcat -h` and `clipcat -h` as the primary reference.\n\n## Installation\n\nThis skill is auto-installed by OpenClaw using the declared `install` spec in the frontmatter above. OpenClaw downloads the platform-specific binary from versioned, immutable URLs under `https://static.clipcat.ai/public/cli/vX.Y.Z/` and places it under `~/.openclaw/tools/clipcat/`. No remote shell script is executed.\n\nAfter installation, configure your API key once:\n\n```bash\nclipcat config --api-key \n```\n\n## What this CLI is for\n\n`clipcat` is the local entrypoint for all Clipcat AI video generation workflows:\n\n- Search viral TikTok videos by keyword\n- Search TikTok Shop products by keyword (market intelligence)\n- Get TikTok Shop product details and reviews\n- Replicate viral videos with your product\n- Generate product videos from images\n- Generate AI images from text prompts using GPT Image 2 (with optional reference images)\n- Analyze videos (script, scenes, music)\n- Download TikTok/Douyin videos\n- Query async task status\n\n## Default agent workflow\n\n1. Start with `clipcat -h` to see all commands.\n2. Before using any command, run `clipcat -h` to see flags.\n3. Default to JSON output. Only use `--pretty` when the result is meant for human terminal reading.\n4. Warn the user before running commands that consume credits.\n\n## Choosing the right command\n\n- `search` — find viral TikTok videos by keyword; supports `--region`, `--sort-by relevance|likes`, `--time-range any|day|week|month|quarter|half_year`, `--require-shop`\n- `search_items` — search TikTok Shop products by keyword; returns market insights, competitor shops, and product intelligence; supports `--region`, `--offset`, `--page-token` for pagination\n- `product_detail` — get product info by `--input `; supports `--region`\n- `product_comment` — get product reviews by `--input `; supports `--region`, `--sort-rule`, `--filter-type`, `--filter-value`\n- `replicate` — replicate a viral video with your product images (auto-detects URL type); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed; supports `--model`, `--duration`, `--size`, `--lang`, `--resolution`, `--character-id`\n- `product_video` — generate video from product images only (no reference video); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed\n- `image` — generate an AI image from a text prompt using **GPT Image 2** model; optionally supply up to 5 reference images via `--image` (local file) or `--image-url` (URL). Use `--aspect-ratio` to pick `1:1` (default) / `16:9` / `9:16`\n- `list_images` — list image generation tasks from server; supports `--status` / `--limit` / `--page` filters\n- `breakdown` — analyze a video (script, scenes, music); returns cached result immediately if previously analyzed\n- `download` — download TikTok/Douyin video (returns signed URL); cached results return immediately\n- `user_videos` — get a TikTok user's video list with analytics (plays, likes, shares, comments, e-commerce cart data); `--unique-id` required; pass `--sec-user-id` to skip ID resolution and speed up response; supports `--max-cursor` pagination and `--sort-type 0|1`\n- `query_task` — check status of a task by ID and type (`--type replicate | product | breakdown | download | image`). Omit `--task-id` to resume the latest local task.\n- `list_tasks` — list recent **video-related** tasks from server (`--type` required: `replicate | product | breakdown | download`). Image tasks use `list_images`.\n\n## replicate: URL type auto-detection\n\n`clipcat replicate` automatically detects the URL type:\n\n- **TikTok/Douyin link** → calls `/replicate_from_social` (costs **1 extra credit** for download)\n- **Direct video URL** → calls `/replicate`\n\nAlways inform the user about the extra credit before running with a social URL.\n\n## clipcat:// asset references\n\n`clipcat://...` strings seen in earlier turns are stable asset references. Pass them **verbatim** to any `--image-url` / `--character-id` flag — never prepend `https://` or modify them. See subcommand `-h` for details.\n\n## Async task rules\n\n`replicate`, `product_video`, `image`, and `breakdown` are async. All four\n**submit and return immediately** with a task ID — they never block.\n\nTypical durations: `image` ~3 min, `breakdown` a few minutes, `product_video` /\n`replicate` 10+ min. **Never try to wait synchronously inside a single tool\ncall** — every realistic agent harness has a tool-call timeout (commonly 60s)\nthat will kill the call long before the task is done. Always go submit → return\n→ poll across turns.\n\n1. Task ID is saved locally to `~/.clipcat/tasks.json` automatically.\n2. Check status with `clipcat query_task --task-id --type `. Each\n call returns immediately with the current status. Omit `--task-id` to resume\n the latest task. Re-invoke the command across turns (suggested cadence:\n ~30s for `image`, ~1-2 min for `breakdown` / `product_video` / `replicate`)\n until `status` is `completed` or `failed`.\n3. Use `clipcat list_tasks --type ` to\n see tasks of a given type from the server.\n\n## query_task: auto-resume\n\n`clipcat query_task` with no flags automatically reads the latest task from `~/.clipcat/tasks.json` and resumes it. No need to remember task IDs.\n\n## Available models\n\nTrial channels are per-clip pricing; standard channels are per-second pricing.\n\n| Model ID | Duration | Resolution | Notes |\n| -------------------- | --------------------- | ----------------- | ---------------------------------------------------- |\n| `veo3.1fast` | 8s, 16s, 24s | 720p, 1080p | **Trial**, default. Balanced quality and cost |\n| `veo3.1pro` | 8s, 16s, 24s | 720p, 1080p | **Trial**. Google Veo 3.1 Pro, high-quality variant |\n| `omini_flash` | 10s | 720p, 1080p | **Trial**. Gemini Omni Flash, Google's newest model |\n| `grok_imagine` | 10s, 15s, 20s, 30s | 720p | **Trial**. 9:16 aspect ratio only, longer clips |\n| `sora2_official_exp` | 4s, 8s, 12s | 720p | **Trial**. OpenAI Sora 2 official channel, 9:16/16:9 |\n| `seedance2` | 4-15s (any integer) | 480p, 720p, 1080p | Standard. ByteDance Seedance 2, top quality |\n| `seedance2_fast` | 4-15s (any integer) | 480p, 720p, 1080p | Standard. ByteDance Seedance 2 Fast, fast variant |\n| `happyhorse10` | 3-15s (any integer) | 720p, 1080p | Standard. Alibaba HappyHorse 1.0 |\n\nAlways check `clipcat replicate -h` for the current model list.\n\n## Supported languages (`--lang`)\n\n`en` `zh` `fr` `de` `ms` `vi` `th` `ja` `ko` `id` `fil` `es`\n\n## Good agent behavior\n\n- Run `clipcat -h` first if unsure which command to use.\n- Show parameters to user and get confirmation before running paid commands.\n- Keep record of task IDs; re-invoke `query_task` across turns to track long-running tasks.\n- Preserve signed video URLs intact — they contain `X-Amz-*` params that break if truncated.\n- Agents should prefer the default JSON output.\n- Use `--pretty` only for human-facing terminal display.\n\nFile v1.0.13:_meta.json\n\n{\n \"ownerId\": \"kn7f8ddmmnk1fjgrhxfxbhcmgs831vq7\",\n \"slug\": \"clipcat\",\n \"version\": \"1.0.13\",\n \"publishedAt\": 1779359932557\n}\n\nFile v1.0.13:skill-card.md\n\n## Description:
\nClipcat is a TikTok e-commerce video creation skill for video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download through the Clipcat CLI.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[a2888409](https://clawhub.ai/user/a2888409)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nExternal users and agents use this skill to operate the Clipcat CLI for TikTok Shop market research, viral video replication, product video generation, image generation, video analysis, downloads, and asynchronous task tracking.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: The skill downloads and runs a third-party Clipcat CLI binary.
\nMitigation: Install only when the user trusts Clipcat as the provider and the versioned download source shown in the metadata is acceptable.
\nRisk: The CLI requires a Clipcat API key and uses it for authenticated requests.
\nMitigation: Configure only the intended API key, keep it out of prompts and logs, and rotate it if exposure is suspected.
\nRisk: Some video generation and social-video replication commands can consume paid credits.
\nMitigation: Review parameters and obtain confirmation before running commands that consume credits, especially social URL replication that may add a download credit.
\nRisk: Async task IDs are stored locally for resume behavior.
\nMitigation: Treat local task history as user data and avoid sharing task IDs or generated signed URLs outside the intended workflow.
\n\n\n## Reference(s):
\n- [Clipcat homepage](https://clipcat.ai)
\n- [Clipcat API key settings](https://clipcat.ai/workspace?modal=settings&tab=apikeys)
\n- [ClawHub skill page](https://clawhub.ai/a2888409/clipcat)
\n\n\n## Skill Output:
\n**Output Type(s):** [Shell commands, Configuration, JSON, Guidance]
\n**Output Format:** [Markdown guidance with inline shell commands and JSON-oriented CLI output]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [May submit asynchronous video or image tasks and return task IDs, signed URLs, or JSON results through the Clipcat CLI.]
\n\n## Skill Version(s):
\n1.0.13 (source: server release metadata and OpenClaw install URLs)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v1.0.12: 2 files, 3676 bytes\n\nFiles: SKILL.md (9067b), _meta.json (127b)\n\nFile v1.0.12:SKILL.md\n\n---\nname: clipcat\ndescription: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.\nuser-invocable: true\nmetadata:\n {\n \"openclaw\":\n {\n \"skillKey\": \"clipcat\",\n \"requires\": { \"env\": [\"CLIPCAT_API_KEY\"] },\n \"primaryEnv\": \"CLIPCAT_API_KEY\",\n \"install\":\n [\n {\n \"id\": \"download-darwin-arm64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.12/clipcat_darwin_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Apple Silicon)\",\n },\n {\n \"id\": \"download-darwin-x64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.12/clipcat_darwin_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Intel)\",\n },\n {\n \"id\": \"download-linux-x64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.12/clipcat_linux_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux x86_64)\",\n },\n {\n \"id\": \"download-linux-arm64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.12/clipcat_linux_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux arm64)\",\n },\n {\n \"id\": \"download-windows-x64\",\n \"kind\": \"download\",\n \"os\": [\"win32\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.12/clipcat_windows_amd64.zip\",\n \"archive\": \"zip\",\n \"bins\": [\"clipcat.exe\"],\n \"label\": \"Install Clipcat CLI (Windows x86_64)\",\n },\n ],\n },\n \"homepage\": \"https://clipcat.ai\",\n }\n---\n\n# Clipcat CLI\n\nUse this skill when you need TikTok e-commerce video creation through `clipcat`.\n\nGet API key: https://clipcat.ai/workspace?modal=settings&tab=apikeys\n\nThis skill is intentionally short. Detailed flags and supported values belong to the CLI itself — always treat `clipcat -h` and `clipcat -h` as the primary reference.\n\n## Installation\n\nThis skill is auto-installed by OpenClaw using the declared `install` spec in the frontmatter above. OpenClaw downloads the platform-specific binary from versioned, immutable URLs under `https://static.clipcat.ai/public/cli/vX.Y.Z/` and places it under `~/.openclaw/tools/clipcat/`. No remote shell script is executed.\n\nAfter installation, configure your API key once:\n\n```bash\nclipcat config --api-key \n```\n\n## What this CLI is for\n\n`clipcat` is the local entrypoint for all Clipcat AI video generation workflows:\n\n- Search viral TikTok videos by keyword\n- Search TikTok Shop products by keyword (market intelligence)\n- Get TikTok Shop product details and reviews\n- Replicate viral videos with your product\n- Generate product videos from images\n- Generate AI images from text prompts using GPT Image 2 (with optional reference images)\n- Analyze videos (script, scenes, music)\n- Download TikTok/Douyin videos\n- Query async task status\n\n## Default agent workflow\n\n1. Start with `clipcat -h` to see all commands.\n2. Before using any command, run `clipcat -h` to see flags.\n3. Default to JSON output. Only use `--pretty` when the result is meant for human terminal reading.\n4. Warn the user before running commands that consume credits.\n\n## Choosing the right command\n\n- `search` — find viral TikTok videos by keyword; supports `--region`, `--sort-by relevance|likes`, `--time-range any|day|week|month|quarter|half_year`, `--require-shop`\n- `search_items` — search TikTok Shop products by keyword; returns market insights, competitor shops, and product intelligence; supports `--region`, `--offset`, `--page-token` for pagination\n- `product_detail` — get product info by `--input `; supports `--region`\n- `product_comment` — get product reviews by `--input `; supports `--region`, `--sort-rule`, `--filter-type`, `--filter-value`\n- `replicate` — replicate a viral video with your product images (auto-detects URL type); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed; supports `--model`, `--duration`, `--size`, `--lang`, `--resolution`, `--character-id`\n- `product_video` — generate video from product images only (no reference video); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed\n- `image` — generate an AI image from a text prompt using **GPT Image 2** model; optionally supply up to 5 reference images via `--image` (local file) or `--image-url` (URL). Use `--aspect-ratio` to pick `1:1` (default) / `16:9` / `9:16`\n- `list_images` — list image generation tasks from server; supports `--status` / `--limit` / `--page` filters\n- `breakdown` — analyze a video (script, scenes, music); returns cached result immediately if previously analyzed\n- `download` — download TikTok/Douyin video (returns signed URL); cached results return immediately\n- `user_videos` — get a TikTok user's video list with analytics (plays, likes, shares, comments, e-commerce cart data); `--unique-id` required; pass `--sec-user-id` to skip ID resolution and speed up response; supports `--max-cursor` pagination and `--sort-type 0|1`\n- `query_task` — check status of a task by ID and type (`--type replicate | product | breakdown | download | image`). Omit `--task-id` to resume the latest local task.\n- `list_tasks` — list recent **video-related** tasks from server (`--type` required: `replicate | product | breakdown | download`). Image tasks use `list_images`.\n\n## replicate: URL type auto-detection\n\n`clipcat replicate` automatically detects the URL type:\n\n- **TikTok/Douyin link** → calls `/replicate_from_social` (costs **1 extra credit** for download)\n- **Direct video URL** → calls `/replicate`\n\nAlways inform the user about the extra credit before running with a social URL.\n\n## Async task rules\n\n`replicate`, `product_video`, `image`, and `breakdown` are async. All four\n**submit and return immediately** with a task ID — they never block.\n\nTypical durations: `image` ~3 min, `breakdown` a few minutes, `product_video` /\n`replicate` 10+ min. **Never try to wait synchronously inside a single tool\ncall** — every realistic agent harness has a tool-call timeout (commonly 60s)\nthat will kill the call long before the task is done. Always go submit → return\n→ poll across turns.\n\n1. Task ID is saved locally to `~/.clipcat/tasks.json` automatically.\n2. Check status with `clipcat query_task --task-id --type `. Each\n call returns immediately with the current status. Omit `--task-id` to resume\n the latest task. Re-invoke the command across turns (suggested cadence:\n ~30s for `image`, ~1-2 min for `breakdown` / `product_video` / `replicate`)\n until `status` is `completed` or `failed`.\n3. Use `clipcat list_tasks --type ` to\n see tasks of a given type from the server.\n\n## query_task: auto-resume\n\n`clipcat query_task` with no flags automatically reads the latest task from `~/.clipcat/tasks.json` and resumes it. No need to remember task IDs.\n\n## Available models\n\n| Model ID | Duration | Resolution | Notes |\n| -------------------- | ------------------ | ----------- | ----------------------------------------- |\n| `veo3.1fast` | 8s, 16s, 24s | 720p, 1080p | Default, balanced quality and cost |\n| `grok_imagine` | 10s, 15s, 20s, 30s | 720p | 9:16 aspect ratio only, longer clips |\n| `sora2_official_exp` | 4s, 8s, 12s | 720p | OpenAI Sora 2 trial channel, 9:16 or 16:9 |\n\nAlways check `clipcat replicate -h` for the current model list.\n\n## Supported languages (`--lang`)\n\n`en` `zh` `fr` `de` `ms` `vi` `th` `ja` `ko` `id` `fil` `es`\n\n## Good agent behavior\n\n- Run `clipcat -h` first if unsure which command to use.\n- Show parameters to user and get confirmation before running paid commands.\n- Keep record of task IDs; re-invoke `query_task` across turns to track long-running tasks.\n- Preserve signed video URLs intact — they contain `X-Amz-*` params that break if truncated.\n- Agents should prefer the default JSON output.\n- Use `--pretty` only for human-facing terminal display.\n\nFile v1.0.12:_meta.json\n\n{\n \"ownerId\": \"kn7f8ddmmnk1fjgrhxfxbhcmgs831vq7\",\n \"slug\": \"clipcat\",\n \"version\": \"1.0.12\",\n \"publishedAt\": 1777731383404\n}\n\nArchive v1.0.9: 2 files, 3450 bytes\n\nFiles: SKILL.md (8558b), _meta.json (126b)\n\nFile v1.0.9:SKILL.md\n\n---\nname: clipcat\ndescription: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.\nuser-invocable: true\nmetadata:\n {\n \"openclaw\":\n {\n \"skillKey\": \"clipcat\",\n \"requires\": { \"env\": [\"CLIPCAT_API_KEY\"] },\n \"primaryEnv\": \"CLIPCAT_API_KEY\",\n \"install\":\n [\n {\n \"id\": \"download-darwin-arm64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.11/clipcat_darwin_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Apple Silicon)\",\n },\n {\n \"id\": \"download-darwin-x64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.11/clipcat_darwin_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Intel)\",\n },\n {\n \"id\": \"download-linux-x64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.11/clipcat_linux_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux x86_64)\",\n },\n {\n \"id\": \"download-linux-arm64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.11/clipcat_linux_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux arm64)\",\n },\n {\n \"id\": \"download-windows-x64\",\n \"kind\": \"download\",\n \"os\": [\"win32\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.11/clipcat_windows_amd64.zip\",\n \"archive\": \"zip\",\n \"bins\": [\"clipcat.exe\"],\n \"label\": \"Install Clipcat CLI (Windows x86_64)\",\n },\n ],\n },\n \"homepage\": \"https://clipcat.ai\",\n }\n---\n\n# Clipcat CLI\n\nUse this skill when you need TikTok e-commerce video creation through `clipcat`.\n\nGet API key: https://clipcat.ai/workspace?modal=settings&tab=apikeys\n\nThis skill is intentionally short. Detailed flags and supported values belong to the CLI itself — always treat `clipcat -h` and `clipcat -h` as the primary reference.\n\n## Installation\n\nThis skill is auto-installed by OpenClaw using the declared `install` spec in the frontmatter above. OpenClaw downloads the platform-specific binary from versioned, immutable URLs under `https://static.clipcat.ai/public/cli/vX.Y.Z/` and places it under `~/.openclaw/tools/clipcat/`. No remote shell script is executed.\n\nAfter installation, configure your API key once:\n\n```bash\nclipcat config --api-key \n```\n\n## What this CLI is for\n\n`clipcat` is the local entrypoint for all Clipcat AI video generation workflows:\n\n- Search viral TikTok videos by keyword\n- Search TikTok Shop products by keyword (market intelligence)\n- Get TikTok Shop product details and reviews\n- Replicate viral videos with your product\n- Generate product videos from images\n- Generate AI images from text prompts using GPT Image 2 (with optional reference images)\n- Analyze videos (script, scenes, music)\n- Download TikTok/Douyin videos\n- Query async task status\n\n## Default agent workflow\n\n1. Start with `clipcat -h` to see all commands.\n2. Before using any command, run `clipcat -h` to see flags.\n3. Default to JSON output. Only use `--pretty` when the result is meant for human terminal reading.\n4. Warn the user before running commands that consume credits.\n\n## Choosing the right command\n\n- `search` — find viral TikTok videos by keyword; supports `--region`, `--sort-by relevance|likes`, `--time-range any|day|week|month|quarter|half_year`, `--require-shop`\n- `search_items` — search TikTok Shop products by keyword; returns market insights, competitor shops, and product intelligence; supports `--region`, `--offset`, `--page-token` for pagination\n- `product_detail` — get product info by `--input `; supports `--region`\n- `product_comment` — get product reviews by `--input `; supports `--region`, `--sort-rule`, `--filter-type`, `--filter-value`\n- `replicate` — replicate a viral video with your product images (auto-detects URL type); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed; supports `--model`, `--duration`, `--size`, `--lang`, `--resolution`, `--character-id`\n- `product_video` — generate video from product images only (no reference video); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed\n- `image` — generate an AI image from a text prompt using **GPT Image 2** model; optionally supply up to 5 reference images via `--image` (local file) or `--image-url` (URL). Use `--aspect-ratio` to pick `1:1` (default) / `16:9` / `9:16`\n- `list_images` — list image generation tasks from server; supports `--status` / `--limit` / `--page` filters\n- `breakdown` — analyze a video (script, scenes, music); returns cached result immediately if previously analyzed\n- `download` — download TikTok/Douyin video (returns signed URL); cached results return immediately\n- `user_videos` — get a TikTok user's video list with analytics (plays, likes, shares, comments, e-commerce cart data); `--unique-id` required; pass `--sec-user-id` to skip ID resolution and speed up response; supports `--max-cursor` pagination and `--sort-type 0|1`\n- `query_task` — check status of a task by ID and type (`--type replicate | product | breakdown | download | image`). Omit `--task-id` to resume the latest local task.\n- `list_tasks` — list recent **video-related** tasks from server (`--type` required: `replicate | product | breakdown | download`). Image tasks use `list_images`.\n\n## replicate: URL type auto-detection\n\n`clipcat replicate` automatically detects the URL type:\n\n- **TikTok/Douyin link** → calls `/replicate_from_social` (costs **1 extra credit** for download)\n- **Direct video URL** → calls `/replicate`\n\nAlways inform the user about the extra credit before running with a social URL.\n\n## Async task rules\n\n`replicate`, `product_video`, `image`, and `breakdown` are async. All four\n**submit and return immediately** with a task ID — they never block.\n\n1. Task ID is saved locally to `~/.clipcat/tasks.json` automatically.\n2. Poll with `clipcat query_task --task-id --type --poll `\n (e.g. `--poll 600` = wait up to 10 min). Omit `--task-id` to resume the latest.\n3. If poll times out, re-run `query_task` later.\n4. Use `clipcat list_tasks --type ` to see tasks of a given type from the server.\n\n## query_task: auto-resume\n\n`clipcat query_task` with no flags automatically reads the latest task from `~/.clipcat/tasks.json` and resumes it. No need to remember task IDs.\n\n## Available models\n\n| Model ID | Duration | Resolution | Notes |\n| -------------------- | ------------------ | ----------- | ----------------------------------------- |\n| `veo3.1fast` | 8s, 16s, 24s | 720p, 1080p | Default, balanced quality and cost |\n| `grok_imagine` | 10s, 15s, 20s, 30s | 720p | 9:16 aspect ratio only, longer clips |\n| `sora2_official_exp` | 4s, 8s, 12s | 720p | OpenAI Sora 2 trial channel, 9:16 or 16:9 |\n\nAlways check `clipcat replicate -h` for the current model list.\n\n## Supported languages (`--lang`)\n\n`en` `zh` `fr` `de` `ms` `vi` `th` `ja` `ko` `id` `fil` `es`\n\n## Good agent behavior\n\n- Run `clipcat -h` first if unsure which command to use.\n- Show parameters to user and get confirmation before running paid commands.\n- Keep record of task IDs; use `query_task` to resume if poll times out.\n- Preserve signed video URLs intact — they contain `X-Amz-*` params that break if truncated.\n- Agents should prefer the default JSON output.\n- Use `--pretty` only for human-facing terminal display.\n\nFile v1.0.9:_meta.json\n\n{\n \"ownerId\": \"kn7f8ddmmnk1fjgrhxfxbhcmgs831vq7\",\n \"slug\": \"clipcat\",\n \"version\": \"1.0.9\",\n \"publishedAt\": 1777471423357\n}\n\nArchive v1.0.8: 2 files, 3302 bytes\n\nFiles: SKILL.md (8168b), _meta.json (126b)\n\nFile v1.0.8:SKILL.md\n\n---\nname: clipcat\ndescription: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.\nuser-invocable: true\nmetadata:\n {\n \"openclaw\":\n {\n \"skillKey\": \"clipcat\",\n \"requires\": { \"env\": [\"CLIPCAT_API_KEY\"] },\n \"primaryEnv\": \"CLIPCAT_API_KEY\",\n \"install\":\n [\n {\n \"id\": \"download-darwin-arm64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.9/clipcat_darwin_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Apple Silicon)\",\n },\n {\n \"id\": \"download-darwin-x64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.9/clipcat_darwin_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Intel)\",\n },\n {\n \"id\": \"download-linux-x64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.9/clipcat_linux_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux x86_64)\",\n },\n {\n \"id\": \"download-linux-arm64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.9/clipcat_linux_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux arm64)\",\n },\n {\n \"id\": \"download-windows-x64\",\n \"kind\": \"download\",\n \"os\": [\"win32\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.9/clipcat_windows_amd64.zip\",\n \"archive\": \"zip\",\n \"bins\": [\"clipcat.exe\"],\n \"label\": \"Install Clipcat CLI (Windows x86_64)\",\n },\n ],\n },\n \"homepage\": \"https://clipcat.ai\",\n }\n---\n\n# Clipcat CLI\n\nUse this skill when you need TikTok e-commerce video creation through `clipcat`.\n\nGet API key: https://clipcat.ai/workspace?modal=settings&tab=apikeys\n\nThis skill is intentionally short. Detailed flags and supported values belong to the CLI itself — always treat `clipcat -h` and `clipcat -h` as the primary reference.\n\n## Installation\n\nThis skill is auto-installed by OpenClaw using the declared `install` spec in the frontmatter above. OpenClaw downloads the platform-specific binary from versioned, immutable URLs under `https://static.clipcat.ai/public/cli/vX.Y.Z/` and places it under `~/.openclaw/tools/clipcat/`. No remote shell script is executed.\n\nAfter installation, configure your API key once:\n\n```bash\nclipcat config --api-key \n```\n\n## What this CLI is for\n\n`clipcat` is the local entrypoint for all Clipcat AI video generation workflows:\n\n- Search viral TikTok videos by keyword\n- Search TikTok Shop products by keyword (market intelligence)\n- Get TikTok Shop product details and reviews\n- Replicate viral videos with your product\n- Generate product videos from images\n- Generate AI images from text prompts using GPT Image 2 (with optional reference images)\n- Analyze videos (script, scenes, music)\n- Download TikTok/Douyin videos\n- Query async task status\n\n## Default agent workflow\n\n1. Start with `clipcat -h` to see all commands.\n2. Before using any command, run `clipcat -h` to see flags.\n3. Default to JSON output. Only use `--pretty` when the result is meant for human terminal reading.\n4. Warn the user before running commands that consume credits.\n\n## Choosing the right command\n\n- `search` — find viral TikTok videos by keyword; supports `--region`, `--sort-by relevance|likes`, `--time-range any|day|week|month|quarter|half_year`, `--require-shop`\n- `search_items` — search TikTok Shop products by keyword; returns market insights, competitor shops, and product intelligence; supports `--region`, `--offset`, `--page-token` for pagination\n- `product_detail` — get product info by `--input `; supports `--region`\n- `product_comment` — get product reviews by `--input `; supports `--region`, `--sort-rule`, `--filter-type`, `--filter-value`\n- `replicate` — replicate a viral video with your product images (auto-detects URL type); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed; supports `--model`, `--duration`, `--size`, `--lang`, `--resolution`, `--character-id`\n- `product_video` — generate video from product images only (no reference video); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed\n- `image` — generate an AI image from a text prompt using **GPT Image 2** model; optionally supply up to 5 reference images via `--image` (local file) or `--image-url` (URL). Use `--aspect-ratio` to pick `1:1` (default) / `16:9` / `9:16`\n- `list_images` — list image generation tasks from server; supports `--status` / `--limit` / `--page` filters\n- `breakdown` — analyze a video (script, scenes, music); returns cached result immediately if previously analyzed\n- `download` — download TikTok/Douyin video (returns signed URL); cached results return immediately\n- `user_videos` — get a TikTok user's video list with analytics (plays, likes, shares, comments, e-commerce cart data); `--unique-id` required; pass `--sec-user-id` to skip ID resolution and speed up response; supports `--max-cursor` pagination and `--sort-type 0|1`\n- `query_task` — check status of a task by ID and type (`--type replicate | product | breakdown | download | image`). Omit `--task-id` to resume the latest local task.\n- `list_tasks` — list recent **video-related** tasks from server (`--type` required: `replicate | product | breakdown | download`). Image tasks use `list_images`.\n\n## replicate: URL type auto-detection\n\n`clipcat replicate` automatically detects the URL type:\n\n- **TikTok/Douyin link** → calls `/replicate_from_social` (costs **1 extra credit** for download)\n- **Direct video URL** → calls `/replicate`\n\nAlways inform the user about the extra credit before running with a social URL.\n\n## Async task rules\n\n`replicate`, `product_video`, `image`, and `breakdown` are async. All four\n**submit and return immediately** with a task ID — they never block.\n\n1. Task ID is saved locally to `~/.clipcat/tasks.json` automatically.\n2. Poll with `clipcat query_task --task-id --type --poll `\n (e.g. `--poll 600` = wait up to 10 min). Omit `--task-id` to resume the latest.\n3. If poll times out, re-run `query_task` later.\n4. Use `clipcat list_tasks --type ` to see tasks of a given type from the server.\n\n## query_task: auto-resume\n\n`clipcat query_task` with no flags automatically reads the latest task from `~/.clipcat/tasks.json` and resumes it. No need to remember task IDs.\n\n## Available models\n\n| Model ID | Duration | Resolution |\n| ------------ | ------------ | ---------- |\n| `veo3.1fast` | 8s, 16s, 24s | 720p, 4K |\n\nAlways check `clipcat replicate -h` for the current model list.\n\n## Supported languages (`--lang`)\n\n`en` `zh` `fr` `de` `ms` `vi` `th` `ja` `ko` `id` `fil` `es`\n\n## Good agent behavior\n\n- Run `clipcat -h` first if unsure which command to use.\n- Show parameters to user and get confirmation before running paid commands.\n- Keep record of task IDs; use `query_task` to resume if poll times out.\n- Preserve signed video URLs intact — they contain `X-Amz-*` params that break if truncated.\n- Agents should prefer the default JSON output.\n- Use `--pretty` only for human-facing terminal display.\n\nFile v1.0.8:_meta.json\n\n{\n \"ownerId\": \"kn7f8ddmmnk1fjgrhxfxbhcmgs831vq7\",\n \"slug\": \"clipcat\",\n \"version\": \"1.0.8\",\n \"publishedAt\": 1777356218924\n}\n\nArchive v1.0.7: 2 files, 3337 bytes\n\nFiles: SKILL.md (8278b), _meta.json (126b)\n\nFile v1.0.7:SKILL.md\n\n---\nname: clipcat\ndescription: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.\nuser-invocable: true\nmetadata:\n {\n \"openclaw\":\n {\n \"skillKey\": \"clipcat\",\n \"requires\": { \"env\": [\"CLIPCAT_API_KEY\"] },\n \"primaryEnv\": \"CLIPCAT_API_KEY\",\n \"install\":\n [\n {\n \"id\": \"download-darwin-arm64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.8/clipcat_darwin_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Apple Silicon)\",\n },\n {\n \"id\": \"download-darwin-x64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.8/clipcat_darwin_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Intel)\",\n },\n {\n \"id\": \"download-linux-x64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.8/clipcat_linux_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux x86_64)\",\n },\n {\n \"id\": \"download-linux-arm64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.8/clipcat_linux_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux arm64)\",\n },\n {\n \"id\": \"download-windows-x64\",\n \"kind\": \"download\",\n \"os\": [\"win32\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.8/clipcat_windows_amd64.zip\",\n \"archive\": \"zip\",\n \"bins\": [\"clipcat.exe\"],\n \"label\": \"Install Clipcat CLI (Windows x86_64)\",\n },\n ],\n },\n \"homepage\": \"https://clipcat.ai\",\n }\n---\n\n# Clipcat CLI\n\nUse this skill when you need TikTok e-commerce video creation through `clipcat`.\n\nGet API key: https://clipcat.ai/workspace?modal=settings&tab=apikeys\n\nThis skill is intentionally short. Detailed flags and supported values belong to the CLI itself — always treat `clipcat -h` and `clipcat -h` as the primary reference.\n\n## Installation\n\nThis skill is auto-installed by OpenClaw using the declared `install` spec in the frontmatter above. OpenClaw downloads the platform-specific binary from versioned, immutable URLs under `https://static.clipcat.ai/public/cli/vX.Y.Z/` and places it under `~/.openclaw/tools/clipcat/`. No remote shell script is executed.\n\nAfter installation, configure your API key once:\n\n```bash\nclipcat config --api-key \n```\n\n## What this CLI is for\n\n`clipcat` is the local entrypoint for all Clipcat AI video generation workflows:\n\n- Search viral TikTok videos by keyword\n- Search TikTok Shop products by keyword (market intelligence)\n- Get TikTok Shop product details and reviews\n- Replicate viral videos with your product\n- Generate product videos from images\n- Generate AI images from text prompts using GPT Image 2 (with optional reference images)\n- Analyze videos (script, scenes, music)\n- Download TikTok/Douyin videos\n- Query async task status\n\n## Default agent workflow\n\n1. Start with `clipcat -h` to see all commands.\n2. Before using any command, run `clipcat -h` to see flags.\n3. Default to JSON output. Only use `--pretty` when the result is meant for human terminal reading.\n4. Warn the user before running commands that consume credits.\n\n## Choosing the right command\n\n- `search` — find viral TikTok videos by keyword; supports `--region`, `--sort-by relevance|likes`, `--time-range any|day|week|month|quarter|half_year`, `--require-shop`\n- `search_items` — search TikTok Shop products by keyword; returns market insights, competitor shops, and product intelligence; supports `--region`, `--offset`, `--page-token` for pagination\n- `product_detail` — get product info by `--input `; supports `--region`\n- `product_comment` — get product reviews by `--input `; supports `--region`, `--sort-rule`, `--filter-type`, `--filter-value`\n- `replicate` — replicate a viral video with your product images (auto-detects URL type); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed; supports `--model`, `--duration`, `--size`, `--lang`, `--resolution`, `--character-id`\n- `product_video` — generate video from product images only (no reference video); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed\n- `image` — generate an AI image from a text prompt using **GPT Image 2** model; optionally supply up to 5 reference images via `--image` (local file) or `--image-url` (URL). Use `--aspect-ratio` to pick `1:1` (default) / `16:9` / `9:16`\n- `list_images` — list image generation tasks from server; supports `--status` / `--limit` / `--page` filters\n- `breakdown` — analyze a video (script, scenes, music); returns cached result immediately if previously analyzed\n- `download` — download TikTok/Douyin video (returns signed URL); cached results return immediately\n- `user_videos` — get a TikTok user's video list with analytics (plays, likes, shares, comments, e-commerce cart data); `--unique-id` required; pass `--sec-user-id` to skip ID resolution and speed up response; supports `--max-cursor` pagination and `--sort-type 0|1`\n- `query_task` — check status of a task by ID and type (`--type replicate | product | breakdown | download | image`). Omit `--task-id` to resume the latest local task.\n- `list_tasks` — list recent **video-related** tasks from server (`--type` required: `replicate | product | breakdown | download`). Image tasks use `list_images`.\n\n## replicate: URL type auto-detection\n\n`clipcat replicate` automatically detects the URL type:\n\n- **TikTok/Douyin link** → calls `/replicate_from_social` (costs **1 extra credit** for download)\n- **Direct video URL** → calls `/replicate`\n\nAlways inform the user about the extra credit before running with a social URL.\n\n## Async task rules\n\n`replicate`, `product_video`, `image`, and `breakdown` are async. All four\n**submit and return immediately** with a task ID — they never block.\n\n1. Task ID is saved locally to `~/.clipcat/tasks.json` automatically.\n2. Poll with `clipcat query_task --task-id --type --poll `\n (e.g. `--poll 600` = wait up to 10 min). Omit `--task-id` to resume the latest.\n3. If poll times out, re-run `query_task` later.\n4. Use `clipcat list_tasks --type ` to see tasks of a given type from the server.\n\n## query_task: auto-resume\n\n`clipcat query_task` with no flags automatically reads the latest task from `~/.clipcat/tasks.json` and resumes it. No need to remember task IDs.\n\n## Available models\n\n| Model ID | Duration | Resolution |\n| ---------------- | ------------ | ---------- |\n| `sora2` | 10s, 15s | 720p |\n| `sora2_official` | 4s, 8s, 12s | 720p |\n| `veo3.1fast` | 8s, 16s, 24s | 720p, 4K |\n\nAlways check `clipcat replicate -h` for the current model list.\n\n## Supported languages (`--lang`)\n\n`en` `zh` `fr` `de` `ms` `vi` `th` `ja` `ko` `id` `fil` `es`\n\n## Good agent behavior\n\n- Run `clipcat -h` first if unsure which command to use.\n- Show parameters to user and get confirmation before running paid commands.\n- Keep record of task IDs; use `query_task` to resume if poll times out.\n- Preserve signed video URLs intact — they contain `X-Amz-*` params that break if truncated.\n- Agents should prefer the default JSON output.\n- Use `--pretty` only for human-facing terminal display.\n\nFile v1.0.7:_meta.json\n\n{\n \"ownerId\": \"kn7f8ddmmnk1fjgrhxfxbhcmgs831vq7\",\n \"slug\": \"clipcat\",\n \"version\": \"1.0.7\",\n \"publishedAt\": 1777349697816\n}\n\nArchive v1.0.6: 2 files, 3339 bytes\n\nFiles: SKILL.md (8278b), _meta.json (126b)\n\nFile v1.0.6:SKILL.md\n\n---\nname: clipcat\ndescription: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.\nuser-invocable: true\nmetadata:\n {\n \"openclaw\":\n {\n \"skillKey\": \"clipcat\",\n \"requires\": { \"env\": [\"CLIPCAT_API_KEY\"] },\n \"primaryEnv\": \"CLIPCAT_API_KEY\",\n \"install\":\n [\n {\n \"id\": \"download-darwin-arm64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.7/clipcat_darwin_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Apple Silicon)\",\n },\n {\n \"id\": \"download-darwin-x64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.7/clipcat_darwin_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Intel)\",\n },\n {\n \"id\": \"download-linux-x64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.7/clipcat_linux_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux x86_64)\",\n },\n {\n \"id\": \"download-linux-arm64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.7/clipcat_linux_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux arm64)\",\n },\n {\n \"id\": \"download-windows-x64\",\n \"kind\": \"download\",\n \"os\": [\"win32\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.7/clipcat_windows_amd64.zip\",\n \"archive\": \"zip\",\n \"bins\": [\"clipcat.exe\"],\n \"label\": \"Install Clipcat CLI (Windows x86_64)\",\n },\n ],\n },\n \"homepage\": \"https://clipcat.ai\",\n }\n---\n\n# Clipcat CLI\n\nUse this skill when you need TikTok e-commerce video creation through `clipcat`.\n\nGet API key: https://clipcat.ai/workspace?modal=settings&tab=apikeys\n\nThis skill is intentionally short. Detailed flags and supported values belong to the CLI itself — always treat `clipcat -h` and `clipcat -h` as the primary reference.\n\n## Installation\n\nThis skill is auto-installed by OpenClaw using the declared `install` spec in the frontmatter above. OpenClaw downloads the platform-specific binary from versioned, immutable URLs under `https://static.clipcat.ai/public/cli/vX.Y.Z/` and places it under `~/.openclaw/tools/clipcat/`. No remote shell script is executed.\n\nAfter installation, configure your API key once:\n\n```bash\nclipcat config --api-key \n```\n\n## What this CLI is for\n\n`clipcat` is the local entrypoint for all Clipcat AI video generation workflows:\n\n- Search viral TikTok videos by keyword\n- Search TikTok Shop products by keyword (market intelligence)\n- Get TikTok Shop product details and reviews\n- Replicate viral videos with your product\n- Generate product videos from images\n- Generate AI images from text prompts using GPT Image 2 (with optional reference images)\n- Analyze videos (script, scenes, music)\n- Download TikTok/Douyin videos\n- Query async task status\n\n## Default agent workflow\n\n1. Start with `clipcat -h` to see all commands.\n2. Before using any command, run `clipcat -h` to see flags.\n3. Default to JSON output. Only use `--pretty` when the result is meant for human terminal reading.\n4. Warn the user before running commands that consume credits.\n\n## Choosing the right command\n\n- `search` — find viral TikTok videos by keyword; supports `--region`, `--sort-by relevance|likes`, `--time-range any|day|week|month|quarter|half_year`, `--require-shop`\n- `search_items` — search TikTok Shop products by keyword; returns market insights, competitor shops, and product intelligence; supports `--region`, `--offset`, `--page-token` for pagination\n- `product_detail` — get product info by `--input `; supports `--region`\n- `product_comment` — get product reviews by `--input `; supports `--region`, `--sort-rule`, `--filter-type`, `--filter-value`\n- `replicate` — replicate a viral video with your product images (auto-detects URL type); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed; supports `--model`, `--duration`, `--size`, `--lang`, `--resolution`, `--character-id`\n- `product_video` — generate video from product images only (no reference video); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed\n- `image` — generate an AI image from a text prompt using **GPT Image 2** model; optionally supply up to 5 reference images via `--image` (local file) or `--image-url` (URL). Use `--aspect-ratio` to pick `1:1` (default) / `16:9` / `9:16`\n- `list_images` — list image generation tasks from server; supports `--status` / `--limit` / `--page` filters\n- `breakdown` — analyze a video (script, scenes, music); returns cached result immediately if previously analyzed\n- `download` — download TikTok/Douyin video (returns signed URL); cached results return immediately\n- `user_videos` — get a TikTok user's video list with analytics (plays, likes, shares, comments, e-commerce cart data); `--unique-id` required; pass `--sec-user-id` to skip ID resolution and speed up response; supports `--max-cursor` pagination and `--sort-type 0|1`\n- `query_task` — check status of a task by ID and type (`--type replicate | product | breakdown | download | image`). Omit `--task-id` to resume the latest local task.\n- `list_tasks` — list recent **video-related** tasks from server (`--type` required: `replicate | product | breakdown | download`). Image tasks use `list_images`.\n\n## replicate: URL type auto-detection\n\n`clipcat replicate` automatically detects the URL type:\n\n- **TikTok/Douyin link** → calls `/replicate_from_social` (costs **1 extra credit** for download)\n- **Direct video URL** → calls `/replicate`\n\nAlways inform the user about the extra credit before running with a social URL.\n\n## Async task rules\n\n`replicate`, `product_video`, `image`, and `breakdown` are async. All four\n**submit and return immediately** with a task ID — they never block.\n\n1. Task ID is saved locally to `~/.clipcat/tasks.json` automatically.\n2. Poll with `clipcat query_task --task-id --type --poll `\n (e.g. `--poll 600` = wait up to 10 min). Omit `--task-id` to resume the latest.\n3. If poll times out, re-run `query_task` later.\n4. Use `clipcat list_tasks --type ` to see tasks of a given type from the server.\n\n## query_task: auto-resume\n\n`clipcat query_task` with no flags automatically reads the latest task from `~/.clipcat/tasks.json` and resumes it. No need to remember task IDs.\n\n## Available models\n\n| Model ID | Duration | Resolution |\n| ---------------- | ------------ | ---------- |\n| `sora2` | 10s, 15s | 720p |\n| `sora2_official` | 4s, 8s, 12s | 720p |\n| `veo3.1fast` | 8s, 16s, 24s | 720p, 4K |\n\nAlways check `clipcat replicate -h` for the current model list.\n\n## Supported languages (`--lang`)\n\n`en` `zh` `fr` `de` `ms` `vi` `th` `ja` `ko` `id` `fil` `es`\n\n## Good agent behavior\n\n- Run `clipcat -h` first if unsure which command to use.\n- Show parameters to user and get confirmation before running paid commands.\n- Keep record of task IDs; use `query_task` to resume if poll times out.\n- Preserve signed video URLs intact — they contain `X-Amz-*` params that break if truncated.\n- Agents should prefer the default JSON output.\n- Use `--pretty` only for human-facing terminal display.\n\nFile v1.0.6:_meta.json\n\n{\n \"ownerId\": \"kn7f8ddmmnk1fjgrhxfxbhcmgs831vq7\",\n \"slug\": \"clipcat\",\n \"version\": \"1.0.6\",\n \"publishedAt\": 1777015140628\n}\n\nArchive v1.0.5: 2 files, 3315 bytes\n\nFiles: SKILL.md (8227b), _meta.json (126b)\n\nFile v1.0.5:SKILL.md\n\n---\nname: clipcat\ndescription: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.\nuser-invocable: true\nmetadata:\n {\n \"openclaw\":\n {\n \"skillKey\": \"clipcat\",\n \"requires\": { \"env\": [\"CLIPCAT_API_KEY\"] },\n \"primaryEnv\": \"CLIPCAT_API_KEY\",\n \"install\":\n [\n {\n \"id\": \"download-darwin-arm64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.7/clipcat_darwin_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Apple Silicon)\",\n },\n {\n \"id\": \"download-darwin-x64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.7/clipcat_darwin_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Intel)\",\n },\n {\n \"id\": \"download-linux-x64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.7/clipcat_linux_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux x86_64)\",\n },\n {\n \"id\": \"download-linux-arm64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.7/clipcat_linux_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux arm64)\",\n },\n {\n \"id\": \"download-windows-x64\",\n \"kind\": \"download\",\n \"os\": [\"win32\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.7/clipcat_windows_amd64.zip\",\n \"archive\": \"zip\",\n \"bins\": [\"clipcat.exe\"],\n \"label\": \"Install Clipcat CLI (Windows x86_64)\",\n },\n ],\n },\n \"homepage\": \"https://clipcat.ai\",\n }\n---\n\n# Clipcat CLI\n\nUse this skill when you need TikTok e-commerce video creation through `clipcat`.\n\nGet API key: https://clipcat.ai/workspace?modal=settings&tab=apikeys\n\nThis skill is intentionally short. Detailed flags and supported values belong to the CLI itself — always treat `clipcat -h` and `clipcat -h` as the primary reference.\n\n## Installation\n\nThis skill is auto-installed by OpenClaw using the declared `install` spec in the frontmatter above. OpenClaw downloads the platform-specific binary from versioned, immutable URLs under `https://static.clipcat.ai/public/cli/vX.Y.Z/` and places it under `~/.openclaw/tools/clipcat/`. No remote shell script is executed.\n\nAfter installation, configure your API key once:\n\n```bash\nclipcat config --api-key \n```\n\n## What this CLI is for\n\n`clipcat` is the local entrypoint for all Clipcat AI video generation workflows:\n\n- Search viral TikTok videos by keyword\n- Search TikTok Shop products by keyword (market intelligence)\n- Get TikTok Shop product details and reviews\n- Replicate viral videos with your product\n- Generate product videos from images\n- Generate AI images from text prompts (with optional reference images)\n- Analyze videos (script, scenes, music)\n- Download TikTok/Douyin videos\n- Query async task status\n\n## Default agent workflow\n\n1. Start with `clipcat -h` to see all commands.\n2. Before using any command, run `clipcat -h` to see flags.\n3. Default to JSON output. Only use `--pretty` when the result is meant for human terminal reading.\n4. Warn the user before running commands that consume credits.\n\n## Choosing the right command\n\n- `search` — find viral TikTok videos by keyword; supports `--region`, `--sort-by relevance|likes`, `--time-range any|day|week|month|quarter|half_year`, `--require-shop`\n- `search_items` — search TikTok Shop products by keyword; returns market insights, competitor shops, and product intelligence; supports `--region`, `--offset`, `--page-token` for pagination\n- `product_detail` — get product info by `--input `; supports `--region`\n- `product_comment` — get product reviews by `--input `; supports `--region`, `--sort-rule`, `--filter-type`, `--filter-value`\n- `replicate` — replicate a viral video with your product images (auto-detects URL type); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed; supports `--model`, `--duration`, `--size`, `--lang`, `--resolution`, `--character-id`\n- `product_video` — generate video from product images only (no reference video); images via `--image` (local) or `--image-url` (URL); local files and URLs can be mixed\n- `image` — generate an AI image from a text prompt; optionally supply up to 5 reference images via `--image` (local file) or `--image-url` (URL). Use `--aspect-ratio` to pick `1:1` (default) / `16:9` / `9:16`\n- `list_images` — list image generation tasks from server; supports `--status` / `--limit` / `--page` filters\n- `breakdown` — analyze a video (script, scenes, music); returns cached result immediately if previously analyzed\n- `download` — download TikTok/Douyin video (returns signed URL); cached results return immediately\n- `user_videos` — get a TikTok user's video list with analytics (plays, likes, shares, comments, e-commerce cart data); `--unique-id` required; pass `--sec-user-id` to skip ID resolution and speed up response; supports `--max-cursor` pagination and `--sort-type 0|1`\n- `query_task` — check status of a task by ID and type (`--type replicate | product | breakdown | download | image`). Omit `--task-id` to resume the latest local task.\n- `list_tasks` — list recent **video-related** tasks from server (`--type` required: `replicate | product | breakdown | download`). Image tasks use `list_images`.\n\n## replicate: URL type auto-detection\n\n`clipcat replicate` automatically detects the URL type:\n\n- **TikTok/Douyin link** → calls `/replicate_from_social` (costs **1 extra credit** for download)\n- **Direct video URL** → calls `/replicate`\n\nAlways inform the user about the extra credit before running with a social URL.\n\n## Async task rules\n\n`replicate`, `product_video`, `image`, and `breakdown` are async. All four\n**submit and return immediately** with a task ID — they never block.\n\n1. Task ID is saved locally to `~/.clipcat/tasks.json` automatically.\n2. Poll with `clipcat query_task --task-id --type --poll `\n (e.g. `--poll 600` = wait up to 10 min). Omit `--task-id` to resume the latest.\n3. If poll times out, re-run `query_task` later.\n4. Use `clipcat list_tasks --type ` to see tasks of a given type from the server.\n\n## query_task: auto-resume\n\n`clipcat query_task` with no flags automatically reads the latest task from `~/.clipcat/tasks.json` and resumes it. No need to remember task IDs.\n\n## Available models\n\n| Model ID | Duration | Resolution |\n| ---------------- | ----------- | ---------- |\n| `sora2` | 10s, 15s | 720p |\n| `sora2_official` | 4s, 8s, 12s | 720p |\n| `veo3.1fast` | 8s, 16s, 24s | 720p, 4K |\n\nAlways check `clipcat replicate -h` for the current model list.\n\n## Supported languages (`--lang`)\n\n`en` `zh` `fr` `de` `ms` `vi` `th` `ja` `ko` `id` `fil` `es`\n\n## Good agent behavior\n\n- Run `clipcat -h` first if unsure which command to use.\n- Show parameters to user and get confirmation before running paid commands.\n- Keep record of task IDs; use `query_task` to resume if poll times out.\n- Preserve signed video URLs intact — they contain `X-Amz-*` params that break if truncated.\n- Agents should prefer the default JSON output.\n- Use `--pretty` only for human-facing terminal display.\n\nFile v1.0.5:_meta.json\n\n{\n \"ownerId\": \"kn7f8ddmmnk1fjgrhxfxbhcmgs831vq7\",\n \"slug\": \"clipcat\",\n \"version\": \"1.0.5\",\n \"publishedAt\": 1777013906977\n}\n\nArchive v1.0.4: 2 files, 2808 bytes\n\nFiles: SKILL.md (6902b), _meta.json (126b)\n\nFile v1.0.4:SKILL.md\n\n---\nname: clipcat\ndescription: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.\nuser-invocable: true\nmetadata:\n {\n \"openclaw\":\n {\n \"skillKey\": \"clipcat\",\n \"requires\": { \"env\": [\"CLIPCAT_API_KEY\"] },\n \"primaryEnv\": \"CLIPCAT_API_KEY\",\n \"install\":\n [\n {\n \"id\": \"download-darwin-arm64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.6/clipcat_darwin_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Apple Silicon)\",\n },\n {\n \"id\": \"download-darwin-x64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.6/clipcat_darwin_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Intel)\",\n },\n {\n \"id\": \"download-linux-x64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.6/clipcat_linux_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux x86_64)\",\n },\n {\n \"id\": \"download-linux-arm64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.6/clipcat_linux_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux arm64)\",\n },\n {\n \"id\": \"download-windows-x64\",\n \"kind\": \"download\",\n \"os\": [\"win32\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.6/clipcat_windows_amd64.zip\",\n \"archive\": \"zip\",\n \"bins\": [\"clipcat.exe\"],\n \"label\": \"Install Clipcat CLI (Windows x86_64)\",\n },\n ],\n },\n \"homepage\": \"https://clipcat.ai\",\n }\n---\n\n# Clipcat CLI\n\nUse this skill when you need TikTok e-commerce video creation through `clipcat`.\n\nGet API key: https://clipcat.ai/workspace?modal=settings&tab=apikeys\n\nThis skill is intentionally short. Detailed flags and supported values belong to the CLI itself — always treat `clipcat -h` and `clipcat -h` as the primary reference.\n\n## Installation\n\nThis skill is auto-installed by OpenClaw using the declared `install` spec in the frontmatter above. OpenClaw downloads the platform-specific binary from versioned, immutable URLs under `https://static.clipcat.ai/public/cli/vX.Y.Z/` and places it under `~/.openclaw/tools/clipcat/`. No remote shell script is executed.\n\nAfter installation, configure your API key once:\n\n```bash\nclipcat config --api-key \n```\n\n## What this CLI is for\n\n`clipcat` is the local entrypoint for all Clipcat AI video generation workflows:\n\n- Search viral TikTok videos by keyword\n- Search TikTok Shop products by keyword (market intelligence)\n- Get TikTok Shop product details and reviews\n- Replicate viral videos with your product\n- Generate product videos from images\n- Generate AI images from text prompts (with optional reference images)\n- Analyze videos (script, scenes, music)\n- Download TikTok/Douyin videos\n- Query async task status\n\n## Default agent workflow\n\n1. Start with `clipcat -h` to see all commands.\n2. Before using any command, run `clipcat -h` to see flags.\n3. Default to JSON output. Only use `--pretty` when the result is meant for human terminal reading.\n4. Warn the user before running commands that consume credits.\n\n## Choosing the right command\n\n- `search` — find viral TikTok videos by keyword\n- `search_items` — search TikTok Shop products by keyword; returns market insights, competitor shops, and product intelligence\n- `product_detail` — get product info by ID or URL\n- `product_comment` — get product reviews\n- `replicate` — replicate a viral video with your product images (auto-detects URL type)\n- `product_video` — generate video from product images only (no reference video)\n- `image` — generate an AI image from a text prompt; optionally supply up to 5 reference images via `--image` (local file) or `--image-url` (URL)\n- `list_images` — list image generation tasks from server; supports `--status` / `--limit` / `--page` filters\n- `breakdown` — analyze a video (script, scenes, music)\n- `download` — download TikTok/Douyin video (returns signed URL)\n- `user_videos` — get a TikTok user's video list with analytics (plays, likes, shares, comments, e-commerce cart data)\n- `query_task` — check status of an async task\n- `list_tasks` — list recent tasks from server\n\n## replicate: URL type auto-detection\n\n`clipcat replicate` automatically detects the URL type:\n\n- **TikTok/Douyin link** → calls `/replicate_from_social` (costs **1 extra credit** for download)\n- **Direct video URL** → calls `/replicate`\n\nAlways inform the user about the extra credit before running with a social URL.\n\n## Async task rules\n\n`replicate`, `product_video`, `image`, and `breakdown` are async. After submission:\n\n1. Task ID is saved locally to `~/.clipcat/tasks.json` automatically.\n2. Use `--poll ` to wait inline (e.g. `--poll 600` = wait up to 10 min).\n3. If poll times out, the CLI prints a resume command — save it.\n4. Use `clipcat query_task` (no args) to resume the **latest** local task.\n5. Use `clipcat list_tasks` to see all tasks from the server.\n\n## query_task: auto-resume\n\n`clipcat query_task` with no flags automatically reads the latest task from `~/.clipcat/tasks.json` and resumes it. No need to remember task IDs.\n\n## Available models\n\n| Model ID | Duration | Resolution |\n| ---------------- | ----------- | ---------- |\n| `sora2` | 10s, 15s | 720p |\n| `sora2_official` | 4s, 8s, 12s | 720p |\n| `veo3.1fast` | 8s,16s,24s | 720p, 4K |\n\nAlways check `clipcat replicate -h` for the current model list.\n\n## Good agent behavior\n\n- Run `clipcat -h` first if unsure which command to use.\n- Show parameters to user and get confirmation before running paid commands.\n- Keep record of task IDs; use `query_task` to resume if poll times out.\n- Preserve signed video URLs intact — they contain `X-Amz-*` params that break if truncated.\n- Agents should prefer the default JSON output.\n- Use `--pretty` only for human-facing terminal display.\n\nFile v1.0.4:_meta.json\n\n{\n \"ownerId\": \"kn7f8ddmmnk1fjgrhxfxbhcmgs831vq7\",\n \"slug\": \"clipcat\",\n \"version\": \"1.0.4\",\n \"publishedAt\": 1775963441416\n}","readmeExcerpt":"Skill: Clipcat - AI Viral Video Maker for TikTok Shop Owner: a2888409 Summary: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI. Tags: latest:1.0.24 Version history: v1.0.24 | 2026-07-08T15:57:27.722Z | user - Updated Clipcat CLI download URLs to version 1.0.24 for all platforms. - A","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"clipcat config --api-key --base-url https://clipcat.ai"},{"language":"bash","snippet":"clipcat quote --model seedance2 --resolution 480p --duration 8 --enhance 1080p\n# → seedance2 480p 8s → 320 credits + 20 enhance (1080p) → total 340 credits\nclipcat product_video --image product.jpg --model seedance2 --duration 8 \\\n --resolution 480p --size 9:16 --enhance 1080p --expected-credits 340"},{"language":"bash","snippet":"clipcat config --api-key "},{"language":"bash","snippet":"clipcat config --api-key "},{"language":"bash","snippet":"clipcat config --api-key "},{"language":"bash","snippet":"clipcat config --api-key "}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: clipcat\ndescription: Clipcat - TikTok e-commerce video creation skill. Video search, product insights, viral replication, product-to-video generation, breakdown analysis, and video download via Clipcat CLI.\nuser-invocable: true\nmetadata:\n {\n \"openclaw\":\n {\n \"skillKey\": \"clipcat\",\n \"requires\": { \"env\": [\"CLIPCAT_API_KEY\"] },\n \"primaryEnv\": \"CLIPCAT_API_KEY\",\n \"install\":\n [\n {\n \"id\": \"download-darwin-arm64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.24/clipcat_darwin_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Apple Silicon)\",\n },\n {\n \"id\": \"download-darwin-x64\",\n \"kind\": \"download\",\n \"os\": [\"darwin\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.24/clipcat_darwin_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (macOS Intel)\",\n },\n {\n \"id\": \"download-linux-x64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.24/clipcat_linux_amd64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux x86_64)\",\n },\n {\n \"id\": \"download-linux-arm64\",\n \"kind\": \"download\",\n \"os\": [\"linux\"],\n \"arch\": [\"arm64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.24/clipcat_linux_arm64.tar.gz\",\n \"archive\": \"tar.gz\",\n \"bins\": [\"clipcat\"],\n \"label\": \"Install Clipcat CLI (Linux arm64)\",\n },\n {\n \"id\": \"download-windows-x64\",\n \"kind\": \"download\",\n \"os\": [\"win32\"],\n \"arch\": [\"x64\"],\n \"url\": \"https://static.clipcat.ai/public/cli/v1.0.24/clipcat_windows_amd64.zip\",\n \"archive\": \"zip\",\n \"bins\": [\"clipcat.exe\"],\n \"label\": \"Install Clipcat CLI (Windows x86_64)\",\n },\n ],\n },\n \"homepage\": \"https://clipcat.ai\",\n }\n---\n\n# Clipcat CLI\n\nUse this skill when you need TikTok e-commerce video creation through `clipcat`.\n\nGet API key: https://clipcat.ai/workspace?modal=settings&tab=apikeys\n\nThis skill is intentionally short. Detailed flags and supported values belong to the CLI itself — always treat `clipcat -h` and `clipcat -h` as the primary reference.\n\n## Installation\n\nThis skill is auto-installed by OpenClaw using the declared `install` spec in the frontmatter above. OpenClaw downloads the platform-specific "},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn7f8ddmmnk1fjgrhxfxbhcmgs831vq7\",\n \"slug\": \"clipcat\",\n \"version\": \"1.0.24\",\n \"publishedAt\": 1783526247722\n}"},{"path":"skill-card.md","content":"## Description:\n\nClipcat helps agents use the Clipcat CLI for TikTok e-commerce video search, product insights, viral video replication, product-to-video generation, video analysis, and video download workflows.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[a2888409](https://clawhub.ai/user/a2888409)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal developers, creators, and commerce teams use this skill to direct agents through Clipcat CLI workflows for TikTok Shop research, product video generation, viral video replication, and asynchronous task tracking.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill installs a third-party native Clipcat CLI without pinned checksums or signature verification.\n\nMitigation: Install only when the Clipcat distribution channel is trusted, and request or verify pinned checksums or signatures for platform archives before deployment.\n\nRisk: The Clipcat CLI uses a Clipcat API key and may process local media paths or remote asset URLs supplied by the user.\n\nMitigation: Use a scoped API key where available, avoid sharing unnecessary local media, and review commands before exposing sensitive file paths or assets.\n\nRisk: Some video generation commands consume paid credits.\n\nMitigation: Run `clipcat quote` with the same parameters, show the returned total cost, get explicit user approval, and submit with `--expected-credits`.\n\n## Reference(s):\n\n- [Clipcat Skill Page](https://clawhub.ai/a2888409/skills/clipcat)\n- [Clipcat Homepage](https://clipcat.ai)\n- [Clipcat API Key Settings](https://clipcat.ai/workspace?modal=settings&tab=apikeys)\n- [Clipcat CLI macOS Apple Silicon archive](https://static.clipcat.ai/public/cli/v1.0.24/clipcat_darwin_arm64.tar.gz)\n- [Clipcat CLI macOS Intel archive](https://static.clipcat.ai/public/cli/v1.0.24/clipcat_darwin_amd64.tar.gz)\n- [Clipcat CLI Linux x86_64 archive](https://static.clipcat.ai/public/cli/v1.0.24/clipcat_linux_amd64.tar.gz)\n- [Clipcat CLI Linux arm64 archive](https://static.clipcat.ai/public/cli/v1.0.24/clipcat_linux_arm64.tar.gz)\n- [Clipcat CLI Windows x86_64 archive](https://static.clipcat.ai/public/cli/v1.0.24/clipcat_windows_amd64.zip)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Code, Shell commands, Configuration, Guidance]\n\n**Output Format:** [Markdown guidance with inline shell commands and CLI JSON output expectations]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires CLIPCAT_API_KEY and the Clipcat CLI; paid video commands should be quoted and explicitly confirmed before submission.]\n\n## Skill Version(s):\n\n1.0.24 (source: server-resolved 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."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1434,"uniquenessScore":42,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T16:55:25.643Z","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":"2026-10-09T16:55:25.643Z","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":"2026-10-09T17:31:53.267Z","emptyReason":null},"items":[{"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":"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":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","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"}]}}}