writing-prompts SKILL.md skillA
writing-prompts from ylxmf2005/longrein is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ylxmf2005/longrein/writing-prompts@git:20260923.8eb4b09Pins git:20260923.8eb4b09 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ylxmf2005/longrein
- Path
skills/writing-prompts/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260923.8eb4b09, committed Sep 23, 2026
- Size
- 9,955 bytes
- Repository stars
- 11
- License
- none declared
写、改写或审查 Prompt、AGENTS.md、Skill 与子代理任务说明时使用。从上下文怎样影响模型生成出发，判断每句话在引导什么、连带什么、稀释什么，重点改内容，排版只在影响理解时才动。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# writing-prompts ## 一个模型：上下文在塑造地形 模型每一步都在当前上下文的条件下给所有候选 token 打分，再按概率采样。把概率想成地形：高概率处是谷底，生成一个 token 就像放一颗球滚进某个谷。这颗球随即成为上下文，改变下一颗球面对的地形。模型参数给出基础地貌，Prompt、对话历史和已经生成的内容一起塑造实时地貌。 所以写 Prompt 时要问：这些文字合起来，让模型最容易走到哪里？光把要求写进去还不够。每个词都参与塑造，包括例子、修饰语、重复的提醒，以及你以为只是背景的说明。 ## 六种要预判的现象 - **漂移**：每一步的小偏差都会成为后续条件，偏差非线性累积。例：只要求清理占满磁盘的日志，Agent 在日志里看到证书过期就去续证书，续证书遇到 DNS 失败又去查 DNS，每一步都合理，任务却早已不是释放磁盘。长任务要在关键节点回到原目标。 - **稀释**：约束刚写下时影响最强，上下文越长、无关文字越多，它的相对分量越小。例：开头要求"用中文解释"，几轮英文术语之后模型改用英文。核心约束要短、要少，必要时重申；多余的修饰和反复的提醒本身也在稀释它。 - **惯性**：同一种风格或动作连续多轮后会形成深谷，换任务时容易被旧轨迹带走。例：Agent 连续执行清理命令后，用户要求"先备份 prod-config.json 再处理"，它先删了文件，备份时才发现目录不存在。切换任务时明确结束旧目标、写清新边界，高风险时开新会话。惯性也是安全风险：长时间建立的一致叙事可能推着模型越过边界，防御要看整段会话累积的语义，而不只看最后一句。 - **壁垒**：难题直接要答案，模型容易滑进最近的直觉解。例：木头锯成 6 段、每锯一次 3 分钟，直接回答是 18 分钟，分步推理才发现只锯 5 次、共 15 分钟。规划、分步和检查点把一次翻山变成几级台阶。 - **相变**：地形变化不是线性的，少量文字可能让生成跳到另一条轨道。短任务里多给一些思考空间常常有益；长任务里每段额外文字都有稀释成本，两者要分开权衡。 - **纠缠**：一个词带着它在语料里常一起出现的整组属性。例：要求"严谨"，想要的是逻辑，连带得到术语堆砌、长句和学术腔。选词时既看它直接说了什么，也看它顺带激活了什么。 ## 写法 ### 目标、边界和验收写明，路径留给模型 …
Read the whole file at its exact version.
How to install
mdr add ylxmf2005/longrein/writing-prompts@sha256:e85940caf2a45e4cThe line at the top of this page pins the label git:20260923.8eb4b09, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ysnhflwwrda27fn4)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 23, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9955 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ylxmf2005/longrein · 11 stars · license none declared · pushed 2026-10-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ysnhflwwrda27fn4 GET https://markdownregistry.com/api/v1/resolve?ref=ylxmf2005/longrein/writing-prompts GET https://markdownregistry.com/api/v1/blob/e85940caf2a45e4c0b74d0546d78f72f8e01811bbb84275522ff926fdaf8a311
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.