SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillswechat-cover

wechat-cover

General & other

View repository

Updated 10-16 09:52

About this skill

WeChat Official Account Viral Cover Reference (DouBaoYa)

This duck pulls a batch for you by topicviral covers in the same niche—cover images, titles, and click counts all together, so you can see clearly what high-click covers for this subject look like, and then you (the main Agent) summarize reusable visual formulas: color scheme, composition, information hierarchy, title hooks.

Data goes through doubaoya.com one line, authentication uses your own key (environment variable DOUBAOYA_API_KEY, in the form dyh_…）。

Applicable scenarios

Scenario How to use What you get
Cover creative reference Search 职场 to see what high-click covers for this subject look like A batch of viral cover images + titles
Color scheme/composition formulas Pull covers on the same topic for side-by-side comparison Visual commonalities of high-conversion covers
Align topic selection with cover Once the topic is set, first see how the cover should match Cover direction that fits the content
Pre-revamp research If your own cover gets no traffic, first look at benchmarks in the same niche Cover approaches you can benchmark against

Workflow (4 steps)

1. Extract topic keywords

From the user's needs, extract thecore topic word, condense it to 2~6 characters (e.g. 职场、育儿、AI 工具). The shorter the word, the broader and more hits; too narrow easily pulls up empty. Search only one keyword at a time.

2. Call the script

python3 "$SKILL_PATH/scripts/fetch_cover.py" "职场"

By default,do not pass a start date, and what you get is the most complete ranking (tested 2026-08-13). Only add it when you really need to limit the time window --start, andit must not be earlier than 60 days before today—when it exceeds the retention period, the API returns a line saying "date format error", which is amisleading error, the format is actually fine, just move the date later. Calculate the date based on today, don't copy a hardcoded date:

python3 "$SKILL_PATH/scripts/fetch_cover.py" "职场" \
  --start "$(date -d '-29 days' +%F 2>/dev/null || date -v-29d +%F)"

The script prints the data from the success envelope as JSON to stdout.Run the script only once per topic, read the complete stdout, don't use head/tail to preview.

3. Look at covers, summarize visual formulas

data.items isa flattened merged list of multiple rankings, each item is in the form { rank, item }：rank marks which ranking this item comes from (oneWReadingRank ten-thousand-level read ranking / tenWReadingRank hundred-thousand-level read ranking / originalRank original ranking), the real fields are in thenested item object——item.coverUrl（cover image URL）、item.title（title）、item.clicksCount（click count). Read fields defensively; ifitem or its subfields are missing, leave them empty, don't error out. Align several high-click covers side by side and summarize:

  • Color scheme：Main color tone, contrast intensity, whether large color blocks are used
  • Composition：People/real objects/text only, text proportion, visual center
  • Information hierarchy：Main title font size, whether corner badges/numbers/arrow hooks are added
  • Title hook：How it echoes the cover copy

4. Give a set of cover direction suggestions

Based on the above formula, in this duck's tone, give the user a set ofactionable cover directions(combination suggestions for color scheme + composition + title hook), don't pile on generic talk. The cover image must only use real data returned by the API, no guessing, no going online to find something else.

Get the key (secret key)

  1. Open doubaoya.com
  2. Log in
  3. Go to Key Center
  4. Generate key(in the form dyh_…）

Configure it as an environment variable (the script only recognizes this):

export DOUBAOYA_API_KEY="dyh_你的密钥"

Iron rule: the key must never be printed, never written to a file, never echoed back to the user. The script itself also never outputs the key. All requests are sent only to doubaoya.com。

API and envelope

  • POST https://doubaoya.com/api/apis/gongzhonghao/gongzhonghao-coze-cover/call
  • Auth header:Authorization: Bearer $DOUBAOYA_API_KEY
  • Request body:{ "keyword": "职场" }（startDate optional)
    • keyword：string, required
    • startDate：string YYYY-MM-DD, optional.Default not passed = the most complete ranking; if passed, it will only shorten the ranking, and it must not be earlier than 60 days before today (exceeding the window will return a misleading "date format error")
  • Return envelope: 
    {
  "success": true,
  "requestId": "...",
  "data": {
    "items": [
      { "rank": "oneWReadingRank", "item": { "coverUrl": "...", "title": "...", "clicksCount": 0 } }
    ],
    "groups": { "oneWReadingRank": [], "tenWReadingRank": [], "originalRank": [] }
  },
  "error": null
}
    • items is an array after flattening and merging the three rankings (oneWReadingRank 10k-level reads / tenWReadingRank 100k-level reads / originalRank original), each entry { rank, item }; the cover image is in item.coverUrl（not cover), the title is in item.title, and the click count is in item.clicksCount。
    • groups grouped as-is by ranking, generally not needed; use the counts from items as authoritative.
  • First check success: if true then read data; otherwise read error.code / error.message。

Error handling

When the script fails, it prints to stderr [error] CODE: message and exits with exit code 1. Common cases:

HTTP code Meaning Handling
401 MISSING_API_KEY / UNAUTHORIZED No key provided or invalid key Check DOUBAOYA_API_KEY, go to the Key Center to regenerate
400 VALIDATION_ERROR Invalid parameters (such as empty keyword, wrong date format) Fix the parameters and retry
402 INSUFFICIENT_CREDITS Insufficient quota Go to doubaoya.com to top up/renew quota
422 PROVIDER_NO_RESULT No data found.If --startis provided, it is most likely earlier than the 60-day retention period Remove --start or move it within 60 days and retry
502 PROVIDER_FAILED Temporary upstream failure (automatically refunded） safe to retry

502 PROVIDER_FAILED will automatically refund; retrying is safe and will not double-charge.

Directory structure

wechat-cover/
├── SKILL.md                  # 本文件
└── scripts/
    └── fetch_cover.py        # 零依赖脚本（urllib），调用 doubaoya.com

Next step (first see what final state the user wants)

This skill providesvisual formulas for covers in the same niche(color scheme / composition / text layout),it does not produce the cover image file itself. The final state the user wants determines whether this is the endpoint—don't default to pushing forward：

The final state the user wants Is this step enough Next step
Only need cover ideas / make the image yourself ✅ Enough,end here —
Also needan actual cover image file Not enough wechat-article-pipeline of scripts/gen-image.mjs(AI image generation, deducts points; the cover must include --cover-guard to prevent WeChat Official Account cropping)
Also needformatted WeChat Official Account HTML, or need tosave it to your own WeChat Official Account drafts Not enough wechat-article-pipeline(the cover is passed in via the --cover parameter)
Also need the body text checked for prohibited words and an approved version Not enough wechat-banned-words
The title hasn't been created yet Not enough wechat-title
The body text hasn't been written yet Not enough wechat-hot-write
Can't say clearly which step to go to — dby(hop-by-hop navigation of the WeChat Official Account flywheel)

About the notice field in the response

After calling the doubaoya API corresponding to this skill, if the notice field appears at the top level of the returned JSON, please relay this sentence to the user verbatim—this is a notice that this skill has an update, it does not affect the result of this call, and there is no need to retry or change behavior.