Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aaronartistzhang-afk/DailyWork --skill lark-comment-loopgit clone --depth 1 https://github.com/aaronartistzhang-afk/DailyWorkWrote 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/aaronartistzhang-afk/dailywork/lark-comment-loop)<a href="https://agentmods.dev/skills/aaronartistzhang-afk/dailywork/lark-comment-loop"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/lark-comment-loop/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/aaronartistzhang-afk/dailywork/lark-comment-loop"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/lark-comment-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00166 | $0.02277 |
| Opus 5 | $0.00083 | $0.01138 |
| Sonnet 5 | $0.00033 | $0.00455 |
| Haiku 4.5 | $0.00017 | $0.00228 |
Grade A, and why
lark-comment-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
飞书文档评论闭环(lark-comment-loop)
拉一篇 docx 的未解决评论 → 按时间过滤到"今天的" → 归类 → 编号 propose 等确认 → 确认后逐条最小半径落改 → 逐条回复说明改法 → 按模式决定是否 resolve → 大改提议新版本。
两条线规矩相反,别弄反:
- PRD 迭代线 = 改完 resolve(模式
resolve;writing-prds 委托本 skill 时显式传)。 - 数据报告线 = 只回复不 resolve(模式
reply-only,本 skill 默认——更安全)。
铁律:propose-first——落改前一律先出编号清单等用户确认,绝不确认前动文档。
关键前置事实
- 飞书评论 API 无服务端时间过滤:
file.comments list不接受 since/until 参数, "只看今天"必须拉全量后客户端按create_time过滤(本 skill 的核心新增逻辑)。 create_time是 epoch 秒(字符串)。"今天 0 点"按本机时区算。- 编辑 docx 正文的机制与坑(相对路径 @file、整表 block_replace、@人 cite)见
~/.claude/skills/writing-prds/lark-editing.md——本 skill 只管评论回路,正文落改照那份。 - lark-cli 版本注记:1.0.52 skills 与 1.0.60 binary 不同步、1.0.65 可升——本波不升级,
遇命令行为异常先核
lark-cli skills read lark-doc拿当前 schema,不要自行升级。
七步流程
1. 输入解析
- 文档:接受 docx
token或完整 URL(URL 取/docx/后那段 token)。file_type固定docx。 --since:默认今天 0 点(本机时区)。用户给别的("这周""昨天起")就换算成 epoch 秒。 取今天 0 点 epoch:SINCE=$(date -v0H -v0M -v0S +%s) # macOS BSD date;本机时区- 模式:
resolve | reply-only,默认reply-only。writing-prds 场景显式传resolve。 - 可选
--verify:跑完派 codex 逐条核对闭环(见第 7 步)。
2. 拉取 + 客户端时间过滤
# 拉全部未解决评论(分页拉全)
lark-cli drive file.comments list \
--params '{"file_token":"<docx_token>","file_type":"docx","is_solved":false}' \
--page-all
拉回后客户端按 create_time >= SINCE 过滤(API 无服务端过滤):
# 上一条命令的 JSON 存为 comments.json,SINCE 为今天 0 点 epoch
jq --arg since "$SINCE" \
'[.data.items[] | select((.create_time|tonumber) >= ($since|tonumber))]' \
comments.json
create_time是 epoch 秒。实测(2026-07-05,docxfile.comments list)返回的是 JSON 数字(如1781763012),并非字符串——故上面的tonumber是防御性写法(对数字幂等,对字符串也生效),两种类型都能正确比较,保留即可。分页路径.data.items[]已实测一致;返回结构为{code,msg,data:{items[],has_more,page_token}}。- 过滤后 0 条 → 直接汇报"今天无新评论",结束,不进后续步骤。
- 每条评论保留
comment_id与最新一条 reply 的正文/quote(定位文中位置)。
3. 归类
把过滤出的评论逐条归入四类(只决定风险标注,不决定是否跳过确认——四类全部进第 4 步统一 propose,确认后才落改):
- 术语:改名、字段名口径统一 → 标注"低风险"。
- 格式:排版、表格列、双语并列、导航标签 → 标注"低风险"。
- 内容精度:公式、显示规则、跳转预填、数字口径 → 标注"改前核对",不确定先问。
- 新需求:评论提了新范围/新模块 → 标注"可能大改",进第 6 步提议新版本。
What ships with it
1 file 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.
- 10d ago First seen · 120 lines · 166 tokens per session scan A 064f0fc37590
lark-comment-loop is a skill published in the GitHub repository aaronartistzhang-afk/DailyWork (1 stars, last pushed 12d ago), licensed MIT. It adds 166 tokens to every session and 2,277 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
context-bundler
Interactively creates targeted code, design, and documentation bundles for external review (Markdown or ZIP). Includes a comprehensive library of review & delegation persona templates (Adversarial Security, Plan Critique, Refactoring Quality, Sub-Agent Task Handoff, Documentation Synthesis, Architecture, Compliance…
convert-mermaid
Translate .mmd diagram files into PNG images with configurable resolution (retina/HQ/scale), supporting rasterization (raster, rasterize, rasterization). V2 includes L5 Delegated Constraint Verification via verifypng for strict binary linting and Puppeteer-based rendering.
stylework-yunxiao-requirement-sync
A workflow for exporting selected requirements from Yunxiao, a project-management service, into a new sheet in an existing DingTalk online spreadsheet. It formats the result into a fixed set of columns and groups it by iteration.
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify…
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify…
docx
Word document manipulation with python-docx - handling split placeholders, headers/footers, nested tables.