What makes tencent-meeting-ingest notable?

1.6K downloads. Trust evidence available

How should tencent-meeting-ingest be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

tencent-meeting-ingest

Ingest Tencent Meeting recordings, minutes, and transcripts into the Research KB by delegating platform fetching to tencent-meeting-skill, then letting OpenClaw generate structured meeting wiki pages and related KB updates.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.6k

Updated

Oct 10, 2026

Version

1.0.14

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.6K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.6K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.14release · observed Aug 7, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: medium.

clawhub skill install s175zrvz5m28epr76c6rt4dtex8474t6:tencent-meeting-ingest

Install using `clawhub skill install s175zrvz5m28epr76c6rt4dtex8474t6:tencent-meeting-ingest` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/myd2002/tencent-meeting-ingest before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-myd2002-tencent-meeting-ingest/snapshot"

Documentation

CLAWHUB

101,377 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: tencent-meeting-ingest
description: Ingest Tencent Meeting recordings, minutes, and transcripts into the Research KB by delegating platform fetching to tencent-meeting-skill, then letting OpenClaw generate structured meeting wiki pages and related KB updates.
---

# tencent-meeting-ingest

## 职责边界

本 skill 只负责“腾讯会议资料入库编译”。腾讯会议平台能力不在这里重新实现：会议列表、录制列表、智能纪要、转写全文、录制地址和权限错误都必须通过已安装的 `tencent-meeting-skill` / `tencent-meeting-mcp` 调用。

后端负责创建资料源、触发任务、保存任务状态和传递 payload/resultFile。Python 脚本只负责确定性动作：读取 payload、调用外部腾讯会议 skill、归档源材料到 `source_files/tencent_meeting/`、准备 OpenClaw 上下文和任务专用草稿目录、校验短 manifest 与 Markdown 草稿、读取草稿正文、写入 Gitea、维护 `catalog.json`/`index.md`、写 `resultFile`。OpenClaw 负责智能判断：理解会议内容、把 Wiki 正文写成普通 Markdown 草稿、选择页面、判断是否需要更新项目页/概念页/资源页/其他相关页、组织页面之间的链接。

本 skill 不做会议创建、取消、改期、权限申请提交、邮件通知、issue 草稿、问答沉淀，也不保留“没有 OpenClaw 时自动生成简陋页面”的 fallback。

会议入库不只是生成会议纪要页。写 Markdown 草稿和 manifest 前，OpenClaw 应私下做一次知识图谱规划：每场会议先落到 `meetings/` 实体页，再判断它是否改变项目路线、研究主题、实验计划、资源选择、团队导航或已有概念/资源页。没有证据时不要硬建关系页；但会议明确带来决策、路线变化或跨页面综合价值时，应更新相关 `overview/`、`projects/`、`concepts/`、`resources/` 或其他页面，并保留解释性跳转。

## 依赖环境

必须在 OpenClaw 运行环境中具备：

- 已安装并可调用的 `tencent-meeting-skill` 或 `tencent-meeting-mcp`。
- `TENCENT_MEETING_TOKEN`，供腾讯会议 skill 使用。
- `GITEA_URL`
- `GITEA_BOT_TOKEN`
- `GITEA_BOT_USERNAME` 或 `GITEA_ORG`
- `TEAM_KB_REPO`

可选：

- `TENCENT_MEETING_SKILL_COMMAND`：显式指定腾讯会议 skill CLI，例如 `python3 /path/to/tencent-meeting-skill/scripts/tencent_meeting.py`。未配置时，脚本会查找同级 skill 目录 `tencent-meeting-skill/scripts/tencent_meeting.py` 或 `tencent-meeting-mcp/scripts/tencent_meeting.py`。

## 运行协议

本 skill 使用 `prepare -> Markdown drafts + compact manifest -> validate-manifest -> apply` 流程。长正文不进入 JSON；manifest 只承担短元数据交接。

### 1. prepare

```bash
python3 scripts/run_task.py prepare --input <payload.json> --context-output <context.json>
```

`prepare` 会：

1. 读取后端 payload 中的资料源、配置和 `lastSnapshot`。
2. 初次扫描时默认按最近 `historyLookbackDays` 天扫描历史会议，默认 14 天；默认拆成 31 天窗口以减少 MCP 列表调用次数，`windowDays` 可配置且最大不超过 31 天；默认 `pageSize=10`、`maxRecords=30`，`maxRecords` 强制限制在 1 到 500，并会提前停止列表分页，不是拉完全部记录后才截断。每场会议写入 `context.json` 的 `contentPreview` 默认最多 12000 字符，完整智能纪要/转写仍归档到 `source_files/tencent_meeting/`。若腾讯会议 MCP 对大窗口表现不稳定，可在资料源配置中将 `windowDays` 下调到 7 或 14。
3. 增量扫描时从 `lastSnapshot.scanUntil` 往前重叠 `incrementalOverlapDays` 天，默认 1 天，避免会议纪要延迟生成导致漏扫，同时减少重复 MCP 调用。
4. 调用腾讯会议 skill：
   - 默认优先用 `get_records_list` 按时间窗口查询录制文件，这是最节省额度且最贴近“可入库纪要/转写”的入口；
   - 若某个时间窗口的 `get_records_list` 返回空，且未配置 `fallbackToEndedMeetings=false`，默认仅对最近 `endedMeetingsFallbackRecentDays` 天（默认 14 天）的窗口自动调用 `get_user_ended_meetings` 补充已结束会议，再按会议 ID/会议号查询录制，避免历史空窗口大量消耗 MCP 额度；
   - 若配置 `includeEndedMeetings=true`，则无论录制时间窗口是否返回内容，都额外调用 `get_user_ended_meetings` 补充已结束会议；
   - `get_smart_minutes` 优先获取 AI 智能纪要；
   - `get_transcripts_details(pid=0)` 优先获取转写全文；若返回空或失败，再用 `get_transcripts_paragraphs` 获取段落 ID，并按段落调用 `get_transcripts_details` 补全文。
   - 计数口径：inputItems[] 按逻辑会议发生次数计数，不按腾讯会议原始录制文件计数；`get_records

_meta.json

{
  "ownerId": "kn7cp7eb6ymqv898hke0ersmc1847fed",
  "slug": "tencent-meeting-ingest",
  "version": "1.0.14",
  "publishedAt": 1786120959111
}

skill-card.md

## Description:

Ingest Tencent Meeting recordings, minutes, and transcripts into the Research KB by delegating platform fetching to tencent-meeting-skill, then letting OpenClaw generate structured meeting wiki pages and related KB updates.

This skill is ready for commercial/non-commercial use.

## Publisher:

[myd2002](https://clawhub.ai/user/myd2002)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and research operations teams use this skill to ingest Tencent Meeting recordings, minutes, and transcripts into a Research KB. It helps an agent prepare meeting source context, create Markdown drafts and compact manifests, validate them, and apply the resulting wiki pages and KB updates.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Task payloads can redirect Gitea uploads carrying the bot token and meeting content.

Mitigation: Install only where backend task payloads are trusted or validated, and require the Gitea endpoint to come from administrator-controlled configuration or an allowlist.

Risk: A broad Gitea bot token could expose or modify repositories beyond the intended KB.

Mitigation: Use a bot token limited to the intended Team KB repository and the minimum permissions needed for KB updates.

Risk: Full meeting minutes and transcripts may be archived into the repository or shared work area.

Mitigation: Keep the shared work directory private, confirm repository access controls, and make users aware that meeting content can be persisted.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/myd2002/skills/tencent-meeting-ingest)

## Skill Output:

**Output Type(s):** [Text, Markdown, JSON, Shell commands, Configuration]

**Output Format:** [Markdown drafts, compact JSON manifests, and backend result JSON]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Produces task-scoped draft and manifest paths; meeting source material may be archived as files.]

## Skill Version(s):

1.0.14 (source: ClawHub release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

env-example.txt

GITEA_URL=http://127.0.0.1:3000
GITEA_BOT_TOKEN=
GITEA_BOT_USERNAME=research-kb-bot
GITEA_ORG=
TEAM_KB_REPO=team-kb
OPENCLAW_SHARED_DIR=/srv/research-kb/shared
TENCENT_MEETING_TOKEN=
# Optional when tencent-meeting-skill is not installed as a sibling skill directory:
TENCENT_MEETING_SKILL_COMMAND=python3 /path/to/tencent-meeting-skill/scripts/tencent_meeting.py

requirements.txt

# Uses only the Python 3 standard library. Platform fetching is delegated to tencent-meeting-skill.

Github ReposUpdated 15h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.