Daily AI Agent Aigc Top News Dingtalk

Daily AI / Agent / AIGC Top News Briefing (DingTalk Edition)

Overview

This skill runs a daily AI / Agent / AIGC morning briefing workflow.

It collects candidates from news aggregators and source-of-truth pages, filters for high-signal items, writes a Chinese 24h report, publishes it as a DingTalk document, fetches it back for validation, and optionally archives the result to a DingTalk multidimensional table.

Core rule: truth first, no quota-filling. If there are only a few important items, keep the report short.

When to Use

Use this skill when the task asks for any of these:

• daily AI / Agent / AIGC top news
• 过去24小时 AI / Agent / AIGC 早报
• cron-generated AI morning briefing
• DingTalk document delivery
• AI news archive into DingTalk multidimensional table
• recurring report that must include Agent, AIGC image/video, GitHub Trending, and a mandatory project check

Do not use this for:

• broad weekly reports with a different time window
• pure finance/news briefings unrelated to AI / Agent / AIGC
• one-off research notes that do not need DingTalk publishing or multidimensional table archival

Required Inputs

A cron prompt should be self-contained and include:

Task: Generate the past-24h AI / Agent / AIGC Top News briefing.
Timezone: Asia/Shanghai.
Delivery: create DingTalk doc, fetch-back validate, optionally archive to DingTalk multidimensional table, send result to origin chat.
Archive base_id: <DINGTALK_BASE_ID>
Archive table_id: <DINGTALK_TABLE_ID>
Aitable URL: https://alidocs.dingtalk.com/i/nodes/<DINGTALK_BASE_ID>
Required project check: <owner>/<repo>

If no DingTalk folder ID is supplied, create the document in the default DingTalk location. Do not block.

Output Contract

Final answer must include:

已完成。

- 文档标题：...
- doc_url：...
- aitable_url：...  # if archival is enabled
- record_id：...    # if archival is enabled
- 摘要：
  - ...
  - ...
  - ...

If archival fails but doc publishing succeeds, say so explicitly and include the doc URL plus a short error summary.

Phase 1 — Preflight

Always check live time. Do not infer time mentally.

date -u '+UTC=%Y-%m-%d %H:%M:%S' && TZ='Asia/Shanghai' date '+CST=%Y-%m-%d %H:%M:%S %Z'

No Feishu auth check needed. DingTalk document and multidimensional table operations go through dws CLI which handles auth automatically.

Phase 2 — Source Collection

Prefer a local news aggregator as the first pass. It gives candidates, not final truth.

Example commands, adapt paths to your local setup:

python3 path/to/news_aggregator_run.py smoke-test --quick
python3 path/to/news_aggregator_run.py fetch --source hackernews --limit 30 --deep --save --outdir /tmp/<run>/hn
python3 path/to/news_aggregator_run.py fetch --source github --limit 30 --deep --save --outdir /tmp/<run>/github
python3 path/to/news_aggregator_run.py fetch --source huggingface --limit 30 --deep --save --outdir /tmp/<run>/hf

Also perform targeted checks against official/source-of-truth pages. At minimum check:

• OpenAI models / image / video updates
• Google Gemini / Imagen / Veo updates
• Anthropic / Claude / coding-agent updates
• Runway
• Pika
• Kling / 可灵
• ByteDance / 即梦 / Seedance
• Midjourney
• Ideogram
• Adobe Firefly
• Stability AI
• GitHub Trending Today for AI / Agent / AIGC / developer-tool / infra projects

Use web search/extract for current facts. If a page blocks extraction, combine search-result snippets, official docs/API pages, and one reputable secondary source.

Phase 3 — Mandatory Project Check

Always check the configured project separately. External popularity does not decide whether it appears.

Default recommended project for this workflow:

NousResearch/hermes-agent

A. Local clone, if available

REPO_DIR="/path/to/local/repo"
if git -C "$REPO_DIR" rev-parse --is-inside-work-tree >/dev/null 2>&1; then
  git -C "$REPO_DIR" fetch origin --prune
  git -C "$REPO_DIR" log origin/main --since='24 hours ago' --pretty=format:'%h | %ad | %s' --date=iso
fi

B. Latest release

python3 - <<'PY'
import json, urllib.request
owner_repo = 'NousResearch/hermes-agent'
req = urllib.request.Request(
    f'https://api.github.com/repos/{owner_repo}/releases/latest',
    headers={'User-Agent':'Daily-AI-Agent-Briefing'}
)
with urllib.request.urlopen(req, timeout=30) as r:
    data = json.load(r)
print(json.dumps({k:data.get(k) for k in ['tag_name','name','published_at','html_url']}, ensure_ascii=False, indent=2))
PY

C. Recent merged PRs

python3 - <<'PY'
import json, urllib.parse, urllib.request, datetime
owner_repo = 'NousResearch/hermes-agent'
start = (datetime.datetime.now(datetime.timezone.utc)-datetime.timedelta(hours=24)).date().isoformat()
q = f'repo:{owner_repo} is:pr merged:>={start} sort:updated-desc'
url = 'https://api.github.com/search/issues?' + urllib.parse.urlencode({'q':q,'per_page':10})
req = urllib.request.Request(url, headers={'User-Agent':'Daily-AI-Agent-Briefing'})
with urllib.request.urlopen(req, timeout=30) as r:
    data = json.load(r)
for item in data.get('items',[])[:10]:
    print(json.dumps({'number':item['number'],'title':item['title'],'html_url':item['html_url']}, ensure_ascii=False))
PY

Include the checked project if any of these occurred in the window:

• release
• dashboard / admin / gateway changes
• platform adapter or messaging fixes
• provider/model routing changes
• memory / facts / skills / cron / backup / debug workflow changes
• onboarding/auth/config stability improvements

If there is no material update, still mention that the check was performed in source notes or omit the section only if truly empty. Never skip the check.

Phase 4 — Selection Rules

Use this priority order:

1. official release / changelog / docs / API evidence
2. GitHub release / merged PR / commit evidence
3. reputable media report
4. HN / social discussion as secondary signal
5. GitHub Trending as trend signal only

Hard rules:

• Do not write rumors as releases.
• Do not convert GitHub Trending Today into "past 24h launched". Say "今日趋势信号".
• HN Algolia is noisy. Treat it as discovery, not proof.
• Verify important HN links using original objectID / hn_url; do not guess item IDs.
• If official naming differs from media naming, state the official name clearly.
• AIGC image/video must be checked daily, even if no item survives final selection.
• Prefer fewer strong items over many weak items.