Creator Content Workflow
Goals
Connect account positioning, content goals, evidence, platform-specific expression, visual assets, publishing, and performance review into a resumable closed loop. Prioritize trustworthy, platform-native, actionable content rather than treating mass generation as a substitute for genuine judgment.
Core Principles
- Confirm the account positioning, target audience, content goals, and platforms before writing the copy.
- Advance one overarching topic at a time. Content for different platforms should share facts and evidence, not the same body copy.
- Distinguish facts, personal judgments, inferences, and recommendations. Key numbers must have sources.
- Only ask questions that would change the direction. Do not ask for information available in existing files or public sources.
- Save major deliverables at milestones. Keep minor changes in the current version; do not create a new file for every sentence-level edit.
- Use natural phrases such as “save it as a file,” “finished piece,” or “content library” with users; avoid exposing internal terminology.
- Create only drafts or publishing packages; do not mass-send. Any external write operation requires explicit authorization.
- Do not use the primary account's authenticated session for automated competitor research, and do not automatically like, comment, follow, or send direct messages.
- Do not claim to detect the probability of AI-generated content. Check only for templated, vague writing or writing that does not fit the account's voice.
- Follow the current project's , directory rules, and user instructions first.
Resolving the Workspace
Determine the content root directory in this order:
- Use the path explicitly specified by the user.
- Use the content directories and naming conventions already specified in the project documentation.
- Use under the current workspace.
Do not assume that a particular Vault, account, growth plan, or vendor tool exists. Save text deliverables in Markdown by default unless the project rules or the user explicitly require another format.
Request Routing
Load only the modules necessary for the outcome the user actually needs:
| Request | Module | Outcome |
|---|
| Single-piece or multi-platform content creation | → self-media-platform-copywriting
| Content brief and platform-native copy |
| Account positioning, topic pool, content series, and editorial calendar | self-media-content-strategy
| Strategy, topic pool, content series, and schedule |
| Trend tracking, keyword research, and competitor analysis | | Research report and original topics |
| Voice-over scripts, storyboards, subtitles, shot plans, digital-human videos, and animated explainer videos | | Production-ready short-video package; once the user explicitly chooses a digital human, confirms portrait and voice rights, and manually uploads and selects the assets on the chosen platform, the workflow can proceed to digital-human production and final-video delivery; when the user wants an animated final video without an on-camera presenter and the required production capability is available, proceed to animated-explainer production and derive landscape and portrait versions for multiple platforms |
| Video uploading, synchronized multi-platform publishing, private uploads or scheduling on YouTube | self-media-video-publisher
| Platform-specific publishing packages; after authorization is granted platform by platform, upload as private, draft, or scheduled content and write the results back to the task card |
| Single-article, weekly, or monthly performance review | self-media-content-analytics
| Attribution, decisions, and experiments to validate |
| Saving, versioning, publishing packages, and archiving | self-media-content-delivery
| Verified files and content index |
| WeChat Official Account formatting, writing to the draft box, and Xiaolvshu image posts | self-media-wechat-publisher
| Formatted and verified WeChat Official Account drafts |
Before using a sub-Skill, read its entire
. If a module is not installed, run the minimum workflow for the corresponding stage of this Skill; do not invent capabilities that do not exist.
Startup and Resumption
- Search the content root directory for task cards with a status of awaiting the user, in creation, awaiting confirmation, pending publication, or pending review.
- When the user explicitly says “continue,” resume the most recent unfinished task.
- If the user says only “creator content creation” and an unfinished task exists, first report the current status and ask only whether to continue it or start a new one.
- If the user provides a clear overarching topic, link, or assets, proceed directly to the content brief and do not force a new topic selection.
- If the user asks only for strategy, research, or data analysis, follow the corresponding branch and do not create unrelated drafts.
Content Creation State Flow
Requirement clarification → Awaiting direction confirmation → Research and evidence → Awaiting platform confirmation → Publishing preflight → In creation → Awaiting title confirmation → Asset generation → Quality review → Awaiting final-draft approval → Pending publication → Draft created or published → Pending performance review → Performance review completed
The following transitions must be completed by the user:
- Confirm the creative direction.
- Confirm the platform mix.
- Select or modify the title.
- Approve the final draft.
- Authorize draft creation or another external write operation.
Final-draft approval does not imply publishing authorization.
Main Content Creation Workflow
1. Create the Brief and Confirm the Direction
Invoke
. Consolidate the account positioning, target audience, content goals, core thesis, evidence, tone, depth, exclusions, and platform angles into a single confirmation card. If information is insufficient, ask no more than three high-impact questions and allow the user to accept reasonable defaults.
2. Fill in Research and Evidence
Invoke
as needed. Prioritize the user's real experiences, backend data, original assets, official documentation, and first-party publications. Use competitors only to identify demand, structure, and opportunities for expression; do not copy their content.
The evidence package must contain at least:
- A one-sentence thesis.
- Three verifiable evidence points.
- Clear boundaries between facts, judgments, inferences, and recommendations.
- A concrete outcome the reader can take away.
- Anything that cannot yet be stated or proven.
3. Select Platforms and Preflight Capabilities
Read platforms.md. Recommend one primary platform and no more than two expansion platforms. Explain each platform's role, deliverables, and time cost.
Read
preflight-and-registry.md. Check only the capabilities required by the selected platforms: copy, images, raw video or screen recordings, sensitive digital-human assets and platform readiness, video compositing and subtitles, draft creation, and analytics. Inspect the animation production pipeline and music licensing only when the video production mode is animated-explainer production, and inspect video uploading only when the user wants the workflow to upload videos. Inspect sensitive digital-human assets and platform readiness, as well as video compositing and subtitles, only when the video production mode is digital-human production. For other content types and tasks involving a live presenter or asset analysis, mark the digital-human readiness and video compositing or subtitle checks as not applicable, and do not enter
solely for that reason. When a capability is unavailable, provide a fallback such as a manual publishing package. Rights confirmation, manual uploading, third-party data processing, generation, compositing, and acceptance criteria for digital-human production are covered in
digital-human-production.md.
4. Generate Platform-Native First Drafts
Invoke
self-media-platform-copywriting
. Design the title, opening, evidence order, structure, and call to action separately for each platform; do not mechanically shorten one version.
Internally generate 6 to 8 titles covering angles such as outcomes, benefits, identity, conflict, contrast, curiosity, and numbers. After filtering, show only the three strongest to the user and explain the angle that best fits each one.
Save the complete first draft before waiting for title confirmation. Do not generate a cover before the title is confirmed.
5. Generate Visual or Video Assets
Generate assets only after the title is confirmed. First, recommend 2 to 3 styles from the
self-media-platform-copywriting
visual style library (
references/visual-styles.md
) based on the content type and platform, explain the differences in one sentence each, and wait for the user to choose. If the account already has a stable style preference, use it by default and notify the user. If the module is not installed, confirm the art style, color palette, and composition directly with the user.
Record the selected style in the task card's visual anchor, then create a copy-to-visual mapping. For software or product content, use real interface assets when available; otherwise, use scenes or metaphors. Do not fabricate product UI.
Invoke
for video. By default, when no source footage is available, deliver the script, storyboard, subtitles, cover, and publishing fields. If the user explicitly selects digital-human production, portrait and voice rights must first be confirmed, and the user must personally upload, create, and select the digital human and voice in Topview or the chosen digital-human platform. The workflow must not upload the original portrait or audio recording. Only after the user confirms that the platform assets are ready may an available adapter be invoked to generate explanatory segments. Then composite the visual explanations, subtitles, and presenter window, and finally verify the aspect ratio, duration, audio, subtitles, and presenter cropping for the target platform. When paid generation is involved, follow the runtime tool's cost-confirmation rules.
When the user wants a finished animated explainer without an on-camera presenter, such as science, history, or brand-story content, follow the animated-explainer production guidelines in
: confirm the script and facts, select a voice tone after audition, confirm the visual anchor, and only then generate assets in batches and render. Music may use only locally synthesized audio, tracks from a platform music library, or tracks the user is authorized to use, and attribution requirements must be recorded. After the master version is complete, derive versions for each platform: YouTube at 16:9 with SRT subtitles, and Douyin, WeChat Channels, and Xiaohongshu at 9:16 with burned-in subtitles. Record them in the publishing matrix.
6. Perform Quality Review
Read quality-gates.md in full and check:
- Facts and evidence.
- Account voice and templated expressions.
- Platform nativeness.
- Consistency among the title, body, and visuals.
- Content compliance and commercial disclosures.
- Publishing package completeness.
Every failed check must include a corrective action and the result of a recheck. After the review passes, wait for final-draft confirmation.
7. Save, Create Drafts, or Deliver Publishing Packages
Invoke
self-media-content-delivery
to save milestone deliverables and verify them by reading them back. Report only files that have been confirmed to exist and contain non-empty content.
Read
publishing-and-review.md in full. For WeChat Official Account drafts, after the user authorizes the operation, preferably invoke
self-media-wechat-publisher
to format the content and write it to the draft box. If the module or its dependencies are unavailable, deliver a manual publishing package. For finished videos, invoke
self-media-video-publisher
: first deliver platform-specific publishing packages, and after the user authorizes each platform, fill in the metadata, upload privately, or schedule publication according to the granted authorization level. Do not mass-send on any platform.
8. Review Performance and Learn Style
After publication, invoke
self-media-content-analytics
. Record the raw data and compare content on the same platform, with the same content type, and from a similar period. Output key conclusions, attribution, comparisons, next actions, and hypotheses to validate.
Read style-learning.md. A one-time manual edit is recorded only as an observation; it can be promoted to a stable preference only if it recurs or the user explicitly confirms it.
Tool Adaptation Principles
- First discover the search, browser, image, video, document, publishing, and data tools already available in the current environment.
- Digital-human generation, visual compositing, and subtitle rendering follow the same adapter principles. Topview MCP is an optional generation adapter that can be used only after the user manually uploads sensitive assets and confirms readiness; it is not a hard dependency of the core Skill.
- Prefer official APIs, authenticated connectors, or a browser session in which the user is already logged in.
- Do not require the user to install a specific vendor tool for this Skill.
- Reuse the document and data capabilities already available in the current environment for charts, tables, and reports.
- Use the current environment's scheduling capabilities only when the user explicitly requests reminders or periodic reviews.
- Never write Cookies, Tokens, Secrets, or complete credentials to task cards, logs, or repositories.
- Do not write original portrait images, recordings, their local paths, temporary upload or download URLs, object-storage keys, or private identifiers from digital-human platforms to task cards, logs, the content registry, or repositories. Index paths for deliverables such as generated segments, final videos, and subtitles may be recorded normally, while resource identifiers required at runtime should be used only as temporary references for the current operation.
- Collection tools are read-only by default. Stop immediately and hand control back to the user when a CAPTCHA, rate limit, or platform risk control appears.
- Platforms such as Bilibili can serve as public, read-only research sources, but become creation platforms only when the user selects them.
Completion Status
At every pause or end, report the current task, completed stages, artifact paths, known fallbacks, and the single next action. Use the following statuses:
- : Waiting for direction, platform, title, final-draft approval, or publishing authorization, or waiting for the user to manually upload, create, and select assets on the digital-human platform.
- : All authorized steps in the current run have been completed.
- : The run is complete, but explicit fallbacks or degradation remain.
- : A critical dependency has failed and the workflow cannot currently continue.
- : Necessary information that would change the result is missing.
Resources
- Platform Selection: platforms.md
- Publishing Preflight and Content Registry: preflight-and-registry.md
- Quality Review: quality-gates.md
- Publishing and Review: publishing-and-review.md
- Style Learning: style-learning.md
- Digital-Human Video Production: digital-human-production.md
- Animated-Explainer Production: animated-explainer-production.md
- Multi-Platform Video Versions: video-platform-versions.md
- Content Task Template: content-task-template.md
- Content Registry Template: content-registry-template.md