CtrlK
BlogDocsLog inGet started
Tessl Logo

tencent-meeting-mcp

腾讯会议:会议管理与音视频协作助手。预约/创建/修改/取消会议、查询会议详情与会议号转换、查看参会成员/受邀人/等候室成员、查询用户会议列表(即将开始/进行中/已结束)、查询录制列表与下载地址、获取转写全文/段落/搜索、获取AI智能纪要(支持多语言翻译)、录制权限申请(预览+提交两步流程)、时间转换与版本检查、Agent意见箱反馈上报。当用户需要预约或管理腾讯会议、查看参会人员、查询会议录制或转写内容、获取智能纪要时使用;当用户访问录制相关内容(下载地址/转写/智能纪要)出现无权限错误时,自动发起录制权限申请流程;当Agent遇到以下任何情况时必须立即触发submit_feedback:工具缺失(功能不存在)、工具报错(返回错误码)、能力不足(参数/功能限制)、结果不符预期(数据异常)、改进建议(功能优化);如果用户提供的是9位会议号而非meeting_id,优先使用get_meeting_by_code转换后再操作。不要在以下场景触发:日程管理(非腾讯会议日程)、即时通讯/聊天、腾讯文档操作、企业微信审批流程、电话/PSTN拨号、视频剪辑或视频编辑、其他视频会议平台(Zoom/Teams/飞书/钉钉)。

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable orchestration skill body with clear sequenced workflows, explicit validation checkpoints on destructive operations, and clean one-level-deep progressive disclosure. The main drag is mild redundancy from re-stating the mandatory-feedback rule and from the summary sections.

Suggestions

Consolidate the mandatory-feedback trigger into a single authoritative statement (场景7) and have other sections reference it, to tighten conciseness.

Inline one or two concrete example tool-call argument payloads (e.g. a schedule_meeting or get_records_list call) for the most common scenarios to close the actionability gap.

Consider merging the standalone 不触发场景 section into the description's negative-trigger list to avoid duplication.

DimensionReasoningScore

Conciseness

Dense operational guidance that assumes Claude's competence and avoids explaining basics, but the mandatory-feedback trigger is restated in 概述, 核心规范-错误处理, and 场景7, and the 不触发场景 list + tool-index table partially duplicate the description/scenarios.

4 / 5

Actionability

Concrete tool sequences and explicit parameter constraints (page_token/page_size, has_more/next_page_token, urlencode, 31-day/1-year bounds, prepare→commit two-step), but full executable argument payloads are deferred to references/api_references.md rather than shown inline, leaving minor gaps.

4 / 5

Workflow Clarity

Each of the 8 scenarios has numbered 处理流程 steps; destructive/sensitive ops (cancel, modify, record-permission commit, submit_feedback) carry explicit 二次确认 validation, and the error→error_dictionary→submit_feedback loop provides a clear recovery feedback loop.

5 / 5

Progressive Disclosure

Overview body points via a clear blockquote to five real one-level-deep references (api_references, error_dictionary, version_management, privacy_policy, feedback_rules), with inline '详见' signals at relevant points and a tool-index table for navigation; verified reference files contain no nested .md references.

5 / 5

Total

18

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, complete, and distinctive description that clearly states capabilities, explicit use-conditions, and explicit non-triggers. Its main weakness is verbosity from embedding internal tool names and procedural detail alongside the natural trigger terms.

Suggestions

Move internal tool names (get_meeting_by_code, submit_feedback, etc.) out of the trigger phrasing and keep the 'Use when...' clause focused on natural user language to lift trigger_term_quality.

Trim the duplicated mandatory-feedback trigger enumeration — state it once and reference 场景7 — to reduce length without losing the what/when coverage.

Consider adding natural synonyms users say (e.g. '开会', '会议纪要', '录音') to round out keyword coverage.

DimensionReasoningScore

Specificity

Lists many concrete actions comprehensively — '预约/创建/修改/取消会议', '查询会议详情与会议号转换', '查看参会成员/受邀人/等候室成员', '获取转写全文/段落/搜索', '获取AI智能纪要', '录制权限申请(预览+提交两步流程)'.

5 / 5

Completeness

Explicitly answers both what (full capability enumeration) and when ('当用户需要预约或管理腾讯会议...时使用'), plus auto-trigger and mandatory-trigger clauses with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural user-facing triggers ('预约或管理腾讯会议、查看参会人员、查询会议录制或转写内容、获取智能纪要') plus positive, auto- and negative-trigger lists, but the description is heavily intermixed with internal tool-name jargon (get_meeting_by_code, submit_feedback) that dilutes the natural-term density.

4 / 5

Distinctiveness Conflict Risk

Clear niche (腾讯会议) with an explicit anti-trigger list ruling out 日程管理、即时通讯、腾讯文档、企业微信审批、电话/PSTN、视频剪辑 and rival platforms (Zoom/Teams/飞书/钉钉), minimizing conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
UnicomAI/wanwu
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.