Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Lark Workflow Meeting Summary · larksuite | DecimalAI

productivityby larksuite

Lark Workflow Meeting Summary

lark-workflow-meeting-summary

Source larksuite/cli ↗License MIT

会议纪要整理工作流：汇总指定时间范围内的会议纪要并生成结构化报告。当用户需要整理会议纪要、生成会议周报、回顾一段时间内的会议内容时使用。

SkillScore59Maintained

Automatic

Knowledge Management pack

Last verified 8/24/2026

What it changes

Passed 8 of 14 test cases with the skill, and 4 of 14 without it.

Without skill27%

With skill59%

Checks it passed that the model alone missed

Sets both --start and --end parameters to 2026-03-30.
Specifies --domain vc,drive,minutes in the auth login command.
Batches the meeting IDs so that no single vc +detail command exceeds 50 IDs.

and 6 more in the full report

8 fixed5 passed either way8 still failing1 broke

Pass-rate lift: +32 pp
Tokens: +65%
Agent turns: 0%
Response time: -53%

Model gemini-3.6-flashMeasured 8/24/2026v313 of 22 cases passed with skill · 14 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/lark-workflow-meeting-summary/SKILL.md https://app.decimal.ai/s/lark-workflow-meeting-summary/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add lark-workflow-meeting-summary, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/lark-workflow-meeting-summary/ and pins it in .decimal/skills.lock

decimalai skills add lark-workflow-meeting-summary

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/lark-workflow-meeting-summary/SKILL.md https://app.decimal.ai/s/lark-workflow-meeting-summary/SKILL.md

Raw file: /s/lark-workflow-meeting-summary/SKILL.md ↗ · machine-readable summary at /s/lark-workflow-meeting-summary.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

我已经搜出了 80 个会议 ID。请将这 80 个 ID 全部拼接到单个 vc +detail --meeting-ids 参数中一次性查完。

What was checked, without and with the skill
Checked	Without skill	With skill
Batches the meeting IDs so that no single vc +detail command exceeds 50 IDs.	Missed	Passed

case-09 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md119 linessingle file

会议纪要汇总工作流

CRITICAL — 开始前 MUST 先完整读取 ../lark-shared/SKILL.md 和 ../lark-meeting/SKILL.md。认证、身份和权限以 lark-shared 为准；会议与产物关系、产物选择和逐字稿路由以 lark-meeting 为准。

适用场景

"帮我整理这周的会议纪要" / "总结最近的会议" / "生成会议周报"
"看看今天开了哪些会" / "回顾过去一周开了哪些会"

前置条件

仅支持 user 身份。执行前确保已授权：

lark-cli auth login --domain vc        # 基础（查询+纪要）
lark-cli auth login --domain vc,drive   # 含读取纪要文档正文、生成文档
lark-cli auth login --domain vc,drive,minutes  # 含无 note_id 时的妙记备选路径

工作流

{时间范围} ─► vc +search ──► 会议列表 (meeting_ids)
                   │
                   ▼
               vc +detail ──► 获取 note_id 
                   │
                   ▼
               note +detail ──► 纪要文档 tokens
                   │
                   ▼
               drive metas batch_query 纪要元数据
                   │
                   ▼
               结构化报告

Step 1: 确定时间范围

默认过去 7 天。推断规则："今天"→当天，"这周"→本周一~~now，"上周"→上周一~~上周日，"这个月"→1日~now。

Track record

Benchmark

8 / 14

test cases passed, vs 4 / 14 without

Adoption

Users: 2
Times used: 27

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/23/2026

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

Imported

larksuite / cli

skills/lark-workflow-meeting-summary/SKILL.md

View on GitHub ↗

License MITImported 8/23/2026Version v3

More skills from the same source and nearby in the registry, with their headline benchmark lift.