revid-research-make-and-post
Research what already goes viral on a topic, make a finished short-form video from the strongest pattern, and publish or schedule it on TikTok, YouTube, Instagram or X. Use when the user wants a video posted, not just made, or asks what to post. Calls the Revid MCP server (search_viral_videos, calculate_credits, render_video, get_project_status, list_social_accounts, schedule_publish).
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- revid-research-make-and-post
- metadata
- { "openclaw": { "requires": { "config": [ "REVID_API_KEY" ] } } }
- description
- Research what already goes viral on a topic, make a finished short-form video from the strongest pattern, and publish or schedule it on TikTok, YouTube, Instagram or X. Use when the user wants a video posted, not just made, or asks what to post. Calls the Revid MCP server (search_viral_videos, calculate_credits, render_video, get_project_status, list_social_accounts, schedule_publish).
03 SKILL.md 正文
Research, make and post
The full loop in one skill: find what works, make a video like it, post it.
Everything runs through the Revid MCP server (https://www.revid.ai/api/mcp).
Install it once, see revid-api-foundations.
When to use this skill
- The user wants a video posted ("make a TikTok about X and post it Friday").
- The user asks what to post, or wants the video based on what already performs.
- For a video the user will post themselves, use
revid-prompt-to-video. - For a script the user already wrote, use
revid-script-to-video.
Steps
- Research. Call
search_viral_videoswith the topic asquery,viralOnly: true, and the platforms the user posts on. Searches cost no credits. Read 5 to 10 results: the hook (first line of the transcript), the length, the format, the engagement. Tell the user in two or three lines which pattern you will use and why. - Write. Draft a 20 to 45 second script that uses the strongest hook pattern for the user's own subject. Never copy a creator's words. Show the script and wait for an OK unless the user said to go ahead.
- Price. Call
calculate_creditswith the exact payload you will render and tell the user the cost in credits. - Make. Call
render_video:
Use{ "workflow": "script-to-video", "source": { "text": "<the approved script>" }, "aspectRatio": "9:16", "voice": { "enabled": true }, "captions": { "enabled": true }, "music": { "generateMusic": true } }prompt-to-videowithsource.promptinstead when the user wants Revid to write the script. Keep the returnedpid. - Wait. Poll
get_project_statuswith thepidevery 20 to 30 seconds until it returnsvideoUrl. Most videos take a few minutes; motion graphics take longer. Share the link and let the user watch it. - Post. Call
list_social_accounts, pick the account the user named, then:schedule_publishwithscheduledTime(ISO 8601 with offset, for example2026-10-30T18:00:00+01:00) for a set time, or without it for the next free slot of the user's posting queue;publish_nowto post right away. Write a caption with 3 to 5 hashtags from the research. Accounts flaggedtokenInvalid: truemust be reconnected in Revid first.
- Confirm. Call
get_publish_statuswith the returnedcontentIdand give the user the post link once it is live.
Rules
- Posting is public: always confirm the account, the caption and the time with the user
before
publish_noworschedule_publish, unless they gave all three already. - Rendering needs an active Revid plan. A
402 SUBSCRIPTION_REQUIREDanswer carries anupgrade.url: pass it to the user. - Never call
render_videotwice for the same video: poll the firstpidinstead.
04 同仓库更多 Skills
migrate-to-e2e
Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, "migrate our tests to e2e", "port these Maestro flows", "move our TesterArmy tests", or when a project has an e2e config and an older suite still running.
e2e
Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.
create-verification-skill
Generate a project-local verify-<app> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for /create-verification-skill, "make a verification skill for this repo", or when a project has no scripted way to prove UI behavior.
deja-search
deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.
deja-reflect
End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.
revid
Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.