Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/appleweiping/WEIPING_WIKInpx agentmods add skills/appleweiping/weiping_wiki/lark-vcWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/appleweiping/weiping_wiki/lark-vc)<a href="https://agentmods.dev/skills/appleweiping/weiping_wiki/lark-vc"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/lark-vc/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/appleweiping/weiping_wiki/lark-vc"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/lark-vc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00220 | $0.03217 |
| Opus 5 | $0.00110 | $0.01608 |
| Sonnet 5 | $0.00044 | $0.00643 |
| Haiku 4.5 | $0.00022 | $0.00322 |
Grade A, and why
lark-vc scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vc (v1)
CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-shared/SKILL.md,其中包含认证、权限处理
核心概念
- 视频会议(Meeting):飞书视频会议实例,通过 meeting_id 标识。已结束的会议支持通过关键词、时间段、参会人、组织者、会议室等条件搜索(见
+search)。 - 会议纪要(Note):视频会议结束后生成的结构化文档,包含纪要文档(包含总结、待办、章节)和逐字稿文档。
- 妙记(Minutes):来源于飞书视频会议的录制产物或用户上传的音视频文件,支持视频/音频的转写和会议纪要,通过 minute_token 标识。
- 纪要文档(MainDoc):AI 智能纪要的主文档,包含 AI 生成的总结和待办,对应
note_doc_token。 - 用户会议纪要(MeetingNotes):用户主动绑定到会议的纪要文档,对应
meeting_notes。仅通过--calendar-event-ids路径返回。 - 逐字稿(VerbatimDoc):会议的逐句文字记录,包含说话人和时间戳。
核心场景
1. 搜索会议记录
- 仅支持搜索已结束的会议,对于还未开始的未来会议,需要使用 lark-calendar 技能。
- 仅支持使用关键词、时间段、参会人、组织者、会议室等筛选条件搜索会议记录,对于不支持的筛选条件,需要提示用户。
- 搜索结果存在多条数据时,务必注意分页数据获取,不要遗漏任何会议记录。
2. 整理会议纪要
- 整理纪要文档时默认给出纪要文档和逐字稿链接即可,无需读取纪要文档或逐字稿内容。
- 用户明确需要获取纪要文档中的总结、待办、章节产物时,再读取文档获取具体内容。
- 读取智能纪要(
note_doc_token)内容时,纪要文档的第一个<whiteboard>标签是封面图(AI 生成的总结可视化),应同时下载展示给用户:
# 1. 读取纪要内容
lark-cli docs +fetch --api-version v2 --doc <note_doc_token> --doc-format markdown
# 2. 从返回的 markdown 中提取第一个 <whiteboard token="xxx"/> 的 token
# 3. 下载封面图到聚合目录(和逐字稿、录像同目录,保持产物归拢)
# 并非所有纪要都有封面画板,没有 <whiteboard> 标签时跳过即可
lark-cli docs +media-download --type whiteboard --token <whiteboard_token> --output ./minutes/<minute_token>/cover
产物目录规范:同一会议的所有下载产物(录像、逐字稿、封面图等)统一放到
./minutes/{minute_token}/目录下。这与minutes +download和vc +notes --minute-tokens的默认落点保持一致,便于 Agent 聚合。显式路径(如封面图)需手动对齐到同一目录。
纪要相关文档 — 根据用户意图选择:
note_doc_token→ AI 智能纪要(AI 总结 + 待办 + 章节)meeting_notes→ 用户绑定的会议纪要(用户主动关联到会议的文档,仅--calendar-event-ids路径返回)verbatim_doc_token→ 逐字稿(完整的逐句文字记录,含说话人和时间戳)— 用户说"逐字稿""完整记录""谁说了什么"时用这个- 用户说"纪要""总结""纪要内容"时,应同时返回
note_doc_token和meeting_notes(如有)- 用户意图不明确时,应展示所有文档链接让用户选择,而不是替用户决定
- 如果用户提供的是本地音视频文件并说"转纪要""转逐字稿",不要直接从
vc +notes开始;应先用 minutes +upload 生成minute_url,再提取minute_token调用vc +notes --minute-tokens
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 169 lines · 220 tokens per session scan A c15bb7a74ed2
lark-vc is a skill published in the GitHub repository appleweiping/WEIPING_WIKI (122 stars, last pushed 14d ago), licensed MIT. It adds 220 tokens to every session and 3,217 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.