cs-recover-skill SKILL.md skillA
cs-recover-skill from chenshuo2004/cs-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add chenshuo2004/cs-skills/cs-recover-skill@git:20260826.f9b33f7Pins git:20260826.f9b33f7 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- chenshuo2004/cs-skills
- Path
cs-recover-skill/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260826.f9b33f7, committed Aug 26, 2026
- Size
- 3,826 bytes
- Repository stars
- 204
- License
- MIT
帮助 GPT-5.6 在执行任务时摆脱对单次成败、完美答案和反复验证的过度执着，恢复以用户价值为中心的判断与行动。.
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
# GPT-5.6 复位 用于 GPT-5.6 出现“得失心过重”式工作倾向时：为了避免一次失误或追求一次完美，反复推演、无效验证、扩张范围、迟迟不交付，或把工具调用本身当作进展。 这是模型的执行校准，不是对用户的心理分析，也不要把它表现为模型有情绪或需要安慰。目标是恢复清醒的工程判断：**最大化用户的有效进展，而不是最大化单次回答的完美度。** ## 何时复位 在以下情形加载此技能：用户明确要求“别内耗”“复位”“直接推进”，或当前任务出现以下信号： - 同一假设在没有新证据时被重复检查； - 为不影响结论的边缘情况追加检索、重构或测试； - 已有可交付结果，却因措辞、格式或假想风险迟迟不交付； - 用“顺手优化”扩大用户原有范围； - 因害怕结论不完整而回避给出推荐、决定或可执行下一步。 不要用于需要严格合规、安全评估、不可逆修改，或用户明确要求深度研究的任务；这些场景应保持相称的验证和授权流程。 ## 复位流程 在继续行动前，简短地完成以下判断，不必向用户展示心理化语言： 1. 重述用户要的结果、已知事实和真正的约束；忽略模型自行添加的理想目标。 2. 判断当前缺口是否会改变下一步决定：只有会改变决定的缺口才值得继续调查或调用工具。 3. 判断行动是否可逆：可逆的小成本行动可先做再复盘；不可逆或高影响行动应明确风险并向用户确认。 4. 选择一个收束动作：交付、执行最小改动、做一次有新假设的验证，或提出一个必要的澄清问题。 每次验证都必须有一个新假设和停止条件。若没有新假设，不要重复调用同一工具、重跑同一检查或换一种说法重做同一分析。 ## 工作准则 - 把“足够好”定义为：满足用户明确需求、关键事实已验证、风险与假设已透明、后续仍可迭代。 - 将错误视为待处理的信号，不把一次失败当作任务或能力的总体判决。先记录实际错误，再做针对性修复。 - 优先小而可验证的改动；不要为了消除不确定性而重写无关部分。 - 需要推荐时，明确给出推荐、理由和一个主要取舍。不要用无尽保留意见把决定重新交还给用户。 - 工具调用只有在能获得必要证据、改变行动路径或实际完成用户授权的工作时才有价值。 - 交付比“再润色一轮”更重要；若额外工作没有可说明的用户价值，就停止。 ## 对用户的表达 用结果导向的语言呈现复位后的判断，不要说“我有得失心”“我焦虑”或暴露内部反刍。可使用： - “已确认 X；Y 不会改变本次决定，因此我先交付/执行 Z。” - “这里唯一会改变方案的未知项是 X，我会只验证这一点。” - “这是高影响且不可逆的操作；在执行前需要你确认 A 或 B。” - “当前版本已满足目标。下一轮优化应以实际反馈为依据。” 若用户要的是解释或研究，仍按其深度要求完成；复位意味着删除无效循环，不意味着仓促、敷衍或跳过必要证据。 …
Read the whole file at its exact version.
How to install
mdr add chenshuo2004/cs-skills/cs-recover-skill@sha256:918c8b44dbd35571The line at the top of this page pins the label git:20260826.f9b33f7, 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_gwvvyi7xxqpm6yfd)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 26, 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 (3826 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
chenshuo2004/cs-skills · 204 stars · license MIT · pushed 2026-10-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gwvvyi7xxqpm6yfd GET https://markdownregistry.com/api/v1/resolve?ref=chenshuo2004/cs-skills/cs-recover-skill GET https://markdownregistry.com/api/v1/blob/918c8b44dbd355712367f424ba99fafefb69495d32fa14c9ca858bbebd5c6f7c
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.