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 PANGKAIFENG/ai-product-manager-skills --skill runtime-adaptergit clone --depth 1 https://github.com/PANGKAIFENG/ai-product-manager-skillsWrote 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/pangkaifeng/ai-product-manager-skills/runtime-adapter)<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.
<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>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 | $0.00153 | $0.01883 |
| Opus 5 | $0.00077 | $0.00941 |
| Sonnet 5 | $0.00031 | $0.00377 |
| Haiku 4.5 | $0.00015 | $0.00188 |
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。 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:
- 当前用户消息中的明确 URL;
$HOME/Documents/Codex/stylework-yunxiao-requirement-sync.local.json的yunxiao_view_url与dingtalk_sheet_url;- 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-browser、spreadsheets 和 dws 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
- 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。
- 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。
- 通过云效界面打开导出,选择固定 8 个字段并下载 Excel。
- 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:
- 校验表头、原始数据行数、空标题、空迭代、空 URL 和迭代格式。
- 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。 - 不同迭代之间插入恰好 3 个空行。
- 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。
- 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。
- 对原始
/i/nodes/URL 先运行dws doc info,确认类型为在线表格(ALIDOC/axls)。 - 运行
dws sheet list获取现有名称。 - 基础名为
智能体{M}月需求-MMDD。 - 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:
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.
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.
- 11d ago First seen · 132 lines · 153 tokens per session scan A 0e22a934a965
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.
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…
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.
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'.
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'.
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'.
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.