stylework-yunxiao-requirement-sync

stylework-yunxiao-requirement-sync is a skill for Codex from PANGKAIFENG/ai-product-manager-skills. It costs 153 tokens per session (1,883 once invoked), scanned A, original, MIT.

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.

In plain words
What is it for?
Use it to export a specified month or batch of Yunxiao requirements, format them in Excel, and add them as a styled new sheet in an existing DingTalk workbook.
Why use it?
It reduces manual copying and keeps the exported table consistent. It also prevents the workflow from changing old sheets or writing data when the user has only requested a preview.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Good fit Use it to export a specified month or batch of Yunxiao requirements, format them in Excel, and add them as a styled new sheet in an existing DingTalk workbook.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pangkaifeng/ai-product-manager-skills/runtime-adapter
Install

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.

Any agent
npx skills add PANGKAIFENG/ai-product-manager-skills --skill runtime-adapter
Clone the repo
git clone --depth 1 https://github.com/PANGKAIFENG/ai-product-manager-skills

Made for: Codex.

Wrote 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.

agentmods badge for stylework-yunxiao-requirement-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/runtime-adapter/github.svg)](https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/runtime-adapter)
Your own site
<a href="https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/runtime-adapter"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/runtime-adapter/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.

agentmods 80×15 button for stylework-yunxiao-requirement-sync

Your own site · 80×15
<a href="https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/runtime-adapter"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/runtime-adapter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,883 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00153 $0.01883
Opus 5 $0.00077 $0.00941
Sonnet 5 $0.00031 $0.00377
Haiku 4.5 $0.00015 $0.00188

Measured 11d ago against content hash 0e22a934a965, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

stylework-yunxiao-requirement-sync scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- DWS 缺能力或失败时不得改用浏览器、`curl`、HTTP API、人工复制粘贴或其他写入方式绕过。
tools/automations/yunxiao-requirement-sheet-sync/runtime-adapter/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

StyleWork 云效需求同步

Overview

把用户指定的云效需求视图通过界面导出,转换成固定字段和迭代分组,再写入已有钉钉表格的一个新 Sheet。这个 Skill 有外部写入副作用,必须先完成本地预检,再创建 Sheet;不得覆盖或修改旧 Sheet。

Hard Boundaries

  • V1 只执行“云效 -> 钉钉”,不把钉钉内容写回云效。
  • 内置浏览器只负责云效页面、登录和 Excel 导出;不得自行抓取云效分页接口或私有 API 替代导出。
  • 钉钉文档探测、新建 Sheet、写入、设样式、冻结和置顶只能使用 dws
  • DWS 缺能力或失败时不得改用浏览器、curl、HTTP API、人工复制粘贴或其他写入方式绕过。
  • 不创建新的钉钉文件,只在用户给定的现有在线表格中新增 Sheet。
  • 用户未明确要求执行同步时,只给预检或说明,不产生外部写入。

Context Intake

按以下优先级取得云效视图 URL 和钉钉表格 URL:

  1. 当前用户消息中的明确 URL;
  2. $HOME/Documents/Codex/stylework-yunxiao-requirement-sync.local.jsonyunxiao_view_urldingtalk_sheet_url
  3. 缺少时各问一次,不猜测、不搜索历史浏览记录。

月份优先取用户明确指定的目标月份;否则从导出数据的迭代字段推断。存在多个月份且用户未指定时,在写入前询问一次。浏览器导出不可用时,接受用户给出的本地 Excel。

Fixed Field Contract

读取 references/field-contract.md。最终列顺序严格为:

标题、负责人、创建者、迭代、技术难度、优先级、客户名称、URL

  • 不包含 父ID
  • 不包含 描述
  • 创建者 不得改成 创建人
  • 不得去重、合并相似标题或擅自过滤行。
  • 缺失非关键值保持空白,不补造描述、难度、优先级、客户或负责人。

Workflow

1. Load tool contracts

执行前读取当前运行时的 browser:control-in-app-browserspreadsheetsdws Skill。实际浏览器自动化前必须读取内置浏览器的实时工具文档;不要依赖过期 selector 或截图坐标。

2. Export from Yunxiao

  1. 在内置浏览器打开目标视图并确认当前筛选范围与目标月份一致。
  2. 若登录失效,暂停并请用户在内置浏览器扫码;用户确认完成后继续当前步骤,不重启整套流程。
  3. 通过云效界面打开导出,选择固定 8 个字段并下载 Excel。
  4. 浏览器导出失败时报告原因,并切换为等待用户提供本地 Excel;不得私自调用云效 API。

3. Preflight and transform locally

用 Spreadsheets 能力读取 Excel,按 references/field-contract.md 生成一个只含 8 列的 CSV 中间文件:

  1. 校验表头、原始数据行数、空标题、空迭代、空 URL 和迭代格式。
  2. 解析 YY.M.W,按年份、月份、周次升序排序;同迭代内保持原始顺序。
  3. 不同迭代之间插入恰好 3 个空行。
  4. 未知迭代、目标月份外迭代或关键字段缺失时,不得静默放到末尾;先输出异常报告并等待用户决定。
  5. 输出写入预览:目标月份、8 个表头、源数据行数、各迭代数量、空行数量、预计写入范围和异常数。

只有预检无阻塞异常时才进入钉钉写入。

4. Probe DingTalk and select a new name

读取 references/sync-playbook.md 并严格使用其中的 DWS 命令。

  1. 对原始 /i/nodes/ URL 先运行 dws doc info,确认类型为在线表格(ALIDOC/axls)。
  2. 运行 dws sheet list 获取现有名称。
  3. 基础名为 智能体{M}月需求-MMDD
  4. 同名时改为 智能体{M}月需求-MMDD-HHmm;若仍冲突则停止,不覆盖、不删除旧 Sheet。

所有 DWS 调用必须带 --format json。命令失败时只允许增加 --verbose 原样重试一次;第二次仍失败即停止并报告。

5. Create, write, and style

按顺序执行:

Read the full file on GitHub · 132 lines

Files

What ships with it

7 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.

Changes

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.

  1. 11d ago First seen · 132 lines · 153 tokens per session scan A 0e22a934a965

Subscribe to this mod's changes

stylework-yunxiao-requirement-sync is a skill published in the GitHub repository PANGKAIFENG/ai-product-manager-skills (11 stars, last pushed 12d ago), licensed MIT. It adds 153 tokens to every session and 1,883 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

adjudication-sheets

Build human adjudication / hand-labeling sheets from LLM-pipeline data without evidence truncation. Use when: (1) preparing a CSV/Excel sheet for a human to rule on cases an LLM classifier or rater panel judged, (2) a labeler reports "there is no information to label from" or cells look empty in Excel, (3) excerpt…

kennethkhoocy/applied-micro-skills · 142 tokens

submittal-log-generator

Extract all submittal requirements from specification sections and generate a comprehensive submittal register in Excel. Triggers: 'submittal log', 'extract submittals', 'submittal register'. Requires /spec-splitter output.

dleerdefi/claude-code-construction · 55 tokens

schedule-extractor

Extract tabular schedule data from construction drawings — door, window, finish, fixture, panel schedules — and output to Excel. Triggers: 'door schedule', 'extract schedule', 'schedule to Excel', 'panel schedule'.

dleerdefi/claude-code-construction · 49 tokens

tag-audit-and-takeoff

Count-based quantity takeoff and tag completeness auditing for construction drawings. Vision + OCR reconciliation, sheet markup, Excel QTO output. Triggers: 'tag audit', 'quantity takeoff', 'QTO', 'count fixtures'.

dleerdefi/claude-code-construction · 54 tokens

bid-tabulator

Extract data from subcontractor bid PDFs and produce a comparison spreadsheet. Feeds into /bid-evaluator. Triggers: 'tabulate bids', 'bid comparison', 'compare bids', 'buyout analysis', 'bid tab'.

dleerdefi/claude-code-construction · 50 tokens

doa-quotation

An Excel and Python worksheet generator for traditional project quotes or agile task plans. It reuses client and project templates found in the current workspace.

medalsoftchina/workcopilot · 228 tokens