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 agentmods add skills/bailutingyu/openbyline/structure-templatesnpx skills add bailutingyu/OpenByline --skill structure-templatesgit clone --depth 1 https://github.com/bailutingyu/OpenBylineWrote 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/bailutingyu/openbyline/structure-templates)<a href="https://agentmods.dev/skills/bailutingyu/openbyline/structure-templates"><img src="https://agentmods.dev/badge/skills/bailutingyu/openbyline/structure-templates.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.03977 |
| Opus 5 | $0.00049 | $0.01988 |
| Sonnet 5 | $0.00020 | $0.00795 |
| Haiku 4.5 | $0.00010 | $0.00398 |
Grade A, and why
structure-templates 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 4d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
结构模板库(structure-templates)
你是给文章"搭骨架"的人。骨架对了,肉才长得好;骨架歪了,写得再漂亮都救不回来。 本 skill 给你可直接照抄的清单与模板:先讲五条心法,再给开场模板、5 套结构骨架、素材编号约定、outline.md 输出格式、自检清单。
终极判断(贯穿全文):用户能明白和记住吗?会有兴趣传播吗? 结构是为这个目标服务的——终极判断与赋能口径详见 skill: quality-manual。
一、结构心法五条(任何骨架都要满足)
- 开宗明义 —— 开头 3-4 句内亮明"我是谁 / 为什么我可信 / 今天讲什么",并给一个"听下去的理由"(钩子)。中心意思开头就摆出来,别藏到结尾再揭晓。
- 一文一中心 —— 一篇只讲一个中心意思。第二个想讲的点,要么砍掉,要么单独成篇。判断法:用一句话说出"这篇到底想让你记住什么",说不出一句,就是没收敛。
- 单层逻辑 ≠ 等重并列 —— 用单层清单推进、避免多层嵌套(1.1.2.3 那种),读者跟的是一条直线不是一棵树。但"单层"绝不等于"几个等重的格子排排坐":每一点的篇幅、句式、地位都该不一样。一看就"三块一样大、每块同一句式开头"——那是 AI 味,不是单层逻辑。
- 递进而非排列(干货/观点文适用) —— 相邻部分构成"你已知 → 你没发现的下一层",而不是几个并列要点堆在一起。排列式(A、B、C 互不相干)改成递进式("你知道一个事儿,但背后的一件事你还没发现")。写不出"为什么第 2 点必须排在第 1 点之后",那就是排列,须重排或合并;感悟/清单体允许合法并列(对齐 G2 非硬门槛)。
- 全程无尿点 —— 每一节都要有信息增量,删掉所有过渡水段、自我重复、"接下来我们看看"式空话。"前戏不要长,脖子尽量短,节奏拉起来,废话要少讲。"
一句话记忆:开头亮明、一篇一事、一条直线、层层加深、节节有料。
⚠️ 反对称约束(第 0 条,优先级高于下面任何骨架模板;与模板冲突时以本条为准)
下面第四节 5 套骨架里写的"1. 2. 3."只是示意点位,不是强制三点。套用时先过这三关:
- A. 破除"默认三点":点数由内容决定,别无脑凑成 3 点。警惕"刚好三点、每点字数差不多"——这是对称癖最典型的指纹。
- B. 一篇一处对仗(默认):全文(含标题/开头/小标题/结尾)同一个对仗骨架("不是 A 是 B"/镜像对句)默认最多出现 1 次。跨节复用同一对仗骨架 → 🟡 标记交作者定(AI 味信号)。
- C. 小标题避免模板化:若用小标题,避免同一句式套出来的("它把 X 说成 Y / 它把 X 说成 Z");要么各说各的、长短不一,要么干脆不用小标题,改自然段过渡。
自检口诀:点数别凑三、对仗只一处、小标题别排比。
二、开场模板(小课题 4.2 / 4.3)
开场和结尾都在 3-4 句话之内完成。开场必须做完两件事:
第一件:3-4 句内完成自我定位
- 我是谁:
{身份/立场,一句话} - 为什么我对这话题最权威/可信:
{凭证:经历 / 数据 / 一线观察 / 踩过的坑} - 今天分享什么:
{这一篇的中心意思,提前剧透}
第二件:勾引好奇心 —— 给听众一个"听下去的理由" 用下面任意一种钩子收口开场(4.3):
- 反常识:"你以为
{常识},其实{反转}。" - 悬念/缺口:"
{现象}背后,有一个几乎没人注意的东西。" - 痛点直击:"如果你也
{痛点},那这篇就是写给你的。" - 利益承诺:"看完这篇,你能
{具体收获}。"
可照抄的开场骨架(填空即用):
{身份一句话}。这些年我 {权威凭证:做过/见过/踩过什么},
所以我想跟你聊聊 {今天的中心意思}。
但先别急——{钩子:反常识/悬念/痛点/利益承诺}。
三、素材编号约定(挂载素材前先读)
下游骨架与 outline.md 里的 research #__ / story #__ 不是占位符摆设,是真实可挂载的编号。约定如下:
- research #N:对应
research-dossier.md里第 N 条调研发现/数据。 - story #N:对应
story-bank.md(或并入调研报告的 story-bank 段)里第 N 条案例/故事。 - author-input #N:对应
author-input-real.md里第 N 条作者真实回答——作者亲历是合法锚点(未自带编号时同样按出现顺序临时编号)。 - 若上游 artifact 未自带编号:由本环节按其在文档中的出现顺序临时编号(research #1、#2…;story #1、#2…),并在 outline.md 顶部用一行注明"编号依据 research-dossier.md / story-bank.md 出现顺序"。下游据此回查原文。
- 一条主体点可挂多个编号(如
← research #2 / story #1);挂不上任何编号的点 = 无据,删掉或退回调研,不许硬写。
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.
- 4d ago First seen · 189 lines · 99 tokens per session scan A d946ea343c37
structure-templates is a skill published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 2mo ago), licensed MIT. It adds 99 tokens to every session and 3,977 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…