Individual skill

wechat-group-daily-report

单群图文日报：将指定微信群一天或明确时间段的聊天，编辑为结论式话题卡、观点总结、选题线索、个人提醒和今日链接，输出 PNG 长图、HTML、Markdown。用于群聊总结、单群日报、群日报长图及每日定时生成；依托 wechat-intelligence-hub 读取证据。不负责跨群综合情报、联系人私聊、商机状态更新或微信发送。

SKILL.md

Read pinned source

Source commit 50ce21866f127a33214222f77e3d321172c7a006

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: No
Observed behavior: Not checked yet
Last checked: Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 29
Repository last updated: Oct 24, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skill Repository topic
ai-agent Repository topic
claude-code Repository topic
daily-report Repository topic
python Repository topic
wechat Repository topic
wechat-group Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

.github/workflows/test.ymlasset · 2,724 bytes
.gitignoreasset · 210 bytes
LICENSEasset · 1,068 bytes
README.mddoc · 14,527 bytes
SKILL.mdcore · 2,699 bytes
SKILL.mdcore · 2,699 bytes
SKILL.mdcore · 2,699 bytes
SKILL.mdcore · 2,699 bytes
agents/interface.yamlasset · 1,262 bytes
agents/openai.yamlasset · 1,262 bytes
assets/config.example.jsonasset · 360 bytes
docs/ecosystem.mddoc · 3,345 bytes
evals/semantic_config.jsonasset · 765 bytes
evals/trigger_cases.jsonasset · 1,204 bytes
examples/README.mddoc · 2,533 bytes
examples/editorial.jsonasset · 3,139 bytes
examples/group-messages.jsonasset · 2,781 bytes
examples/preview.htmlasset · 12,143 bytes
examples/preview.mddoc · 2,977 bytes
examples/preview.pngasset · 822,738 bytes
references/contracts.mddoc · 7,208 bytes
references/editorial.mddoc · 7,566 bytes
references/scheduling.mddoc · 4,684 bytes
references/workflow.mddoc · 4,403 bytes
requirements.txtdoc · 515 bytes
scripts/daily_report.pyruns · 42,842 bytes
scripts/group_nicknames.pyruns · 7,373 bytes
scripts/layout_check.pyruns · 4,022 bytes
scripts/report_view.pyruns · 14,881 bytes
scripts/run_daily.pyruns · 23,370 bytes
tests/test_daily_report.pyruns · 13,835 bytes
tests/test_examples.pyruns · 4,775 bytes
tests/test_group_nicknames.pyruns · 8,240 bytes
tests/test_reference_layout.pyruns · 7,720 bytes
tests/test_run_daily.pyruns · 14,676 bytes

Read excerpt


# 微信个人情报助手 · 单群图文日报

目标是让人读懂发生了什么、讨论揭示了什么，不是聊天缩写。保留情报库原功能。

## 执行

1. 读 [流程](references/workflow.md)。准确群名与半开时间窗必须明确；定时默认用户时区昨日自然日，不能混用机器日期。
2. 已有原始 JSON 就复用；最新请求限定单群刷新，不运行全微信扫描。不把旧摘要当消息源。
3. 发言人默认用**群昵称**（`names` 子命令或 `--names auto --chat-id` 生成映射）；只有显式 `--name-mode display` 才用联系人备注/昵称。用 `scripts/daily_report.py prepare` 生成素材与证据 ID；读完整素材和 [编辑准则](references/editorial.md)，按format_version=2写 `editorial.json`。像熟悉群聊的编辑说话，姓名加粗、重点句高亮、总结轻快但不虚构。不允许停在骨架或机器初筛。
4. 用 `validate --strict` 校验并修正，再 `render --png`。固定模板和版式合同，不让模型自由设计HTML。PNG失败仍交Markdown/HTML，明确降级，不能声称出图成功。
5. 交付最终三种文件与覆盖说明；JSON/素材仅供本机核查。

```bash
python3 "$SKILL/scripts/daily_report.py" names --chat-id "$CHATROOM_ID" --out "$NAMES_JSON"   # 首次/昵称有变时