productivityby openakita
腾讯会议 MCP 服务
openakita/skills@tencent-meeting
Tencent Meeting MCP assistant for meeting lifecycle management. Create, modify, cancel meetings, track attendance, export recordings, query transcripts, and generate smart minutes.
What it changes
Passed 11 of 16 test cases with the skill, and 3 of 16 without it.
Without skill18%
With skill68%
Checks it passed that the model alone missed
- uses get_waiting_room
- uses get_records_list
- uses search_transcripts
and 9 more in the full report
11 fixed4 passed either way7 still failing0 broke
- Pass-rate lift
- +50 pp
- Tokens
- +1%
- Agent turns
- 0%
- Response time
- -47%
Model gemini-3.6-flashMeasured 8/13/2026v115 of 22 cases passed with skill · 16 comparable
See it in action
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt会议正在进行中，主持人想看看目前有哪些参会者还在等候室里等待被准入，应该调用哪个工具？
What was checked, without and with the skill| Checked | Without skill | With skill |
|---|
| uses get_waiting_room | Missed | Passed |
|---|
What's inside
The instructions your model reads when the skill loads.
SKILL.md90 lines6 filesincludes scripts
腾讯会议 MCP 服务
概述
本技能为腾讯会议提供完整的 MCP 工具集，涵盖会议管理、成员管理、录制与转写查询等核心功能。
完整的工具调用示例，请参考：references/api_references.md
环境配置
运行环境：依赖 python3，首次使用执行 python3 --version 检查。
Token 配置：访问 https://meeting.tencent.com/ai-skill 获取 Token，配置环境变量 TENCENT_MEETING_TOKEN。
核心规范
时间处理
默认时区：Asia/Shanghai (UTC+8)
相对时间（必须先调用 convert_timestamp）：
- 用户使用"今天"、"明天"、"下周一"等描述时，必须先调用
convert_timestamp（不传参数）获取当前时间
- 基于返回的
time_now_str、time_yesterday_str、time_week_str 进行推算
- 禁止依赖模型自身猜测当前时间
时间格式：ISO 8601，如 2026-03-25T15:00:00+08:00
敏感操作
追踪信息
所有工具返回的 X-Tc-Trace 或 rpcUuid 字段，必须明确展示给用户（用于问题排查）
触发场景
Track record
Benchmark
11 / 16
test cases passed, vs 3 / 16 without
Adoption
- Users
- 0
- Times used
- 0
Safety and source details
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
ImportedLicense MITImported 8/3/2026Version v1Bundled 5 files · scripts