Best fit
- 使用此技能可防止在生产系统上工作或自主运行代理时进行破坏性操作。
affaan-m/ECC
safety-guard
使用此技能可防止在生产系统上工作或自主运行代理时进行破坏性操作。
59Collecting
See how to use itView GitHub source
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/safety-guard"Automated source guide
Source checked Jul 28, 2026·Refresh due Oct 26, 2026
Reorganized from the pinned upstream SKILL.md
Turn safety-guard's source instructions into a guide you can follow
According to the pinned SKILL.md from affaan-m/ECC: 使用此技能可防止在生产系统上工作或自主运行代理时进行破坏性操作。
npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/safety-guard"Bring this context
- A concrete task that matches the documented purpose of safety-guard.
- The files, examples, or context the task depends on.
- Your constraints, target environment, and definition of done.
Expected outputs
- A result that follows the pinned safety-guard instructions.
- A concise record of assumptions, inputs used, and unresolved questions.
- A final check against the source workflow and relevant permission signals.
Key source sections
Read safety-guard through these 5 source sections
Sections are extracted automatically from the pinned SKILL.md and link back to the source.
使用场景
在生产系统上工作时 代理以全自动模式运行时 希望将编辑限制在特定目录时 敏感操作期间（迁移、部署、数据变更）
在生产系统上工作时代理以全自动模式运行时希望将编辑限制在特定目录时
工作原理
检测到时：显示命令功能、请求确认、建议更安全的替代方案。
检测到时：显示命令功能、请求确认、建议更安全的替代方案。任何在 src/components/ 之外的写入/编辑操作都会被阻止并附带说明。适用于希望代理专注于某个区域而不触及无关代码的场景。代理可读取任何内容，但仅能写入 src/api/。破坏性命令在所有位置均被阻止。
模式 1：谨慎模式
检测到时：显示命令功能、请求确认、建议更安全的替代方案。
检测到时：显示命令功能、请求确认、建议更安全的替代方案。
模式 2：冻结模式
任何在 src/components/ 之外的写入/编辑操作都会被阻止并附带说明。适用于希望代理专注于某个区域而不触及无关代码的场景。
任何在 src/components/ 之外的写入/编辑操作都会被阻止并附带说明。适用于希望代理专注于某个区域而不触及无关代码的场景。
模式 3：守护模式（谨慎+冻结组合）
代理可读取任何内容，但仅能写入 src/api/。破坏性命令在所有位置均被阻止。
代理可读取任何内容，但仅能写入 src/api/。破坏性命令在所有位置均被阻止。
SkillSignal prompt templates
Provide the task, context, and acceptance criteria
These prompts were written by SkillSignal from the source structure; they are not upstream text.
Task-start prompt
Confirm source fit, inputs, and outputs before acting.
Use safety-guard to help me with: [specific task]. Context: [files, data, or background]. Constraints: [environment, scope, and prohibited actions]. Before acting, check the pinned SKILL.md and explain which sections apply, what inputs are still missing, and what you will deliver.
Source-guided execution
Make the Agent explicitly follow the key extracted sections.
Apply the pinned safety-guard source to [task]. Pay particular attention to these source sections: “使用场景”, “工作原理”, “模式 1：谨慎模式”, “模式 2：冻结模式”, “模式 3：守护模式（谨慎+冻结组合）”. Preserve the important decision at each step. Mark facts not covered by the source as “needs confirmation” instead of inventing them. Then verify the result against my acceptance criteria: [criteria].
Result-review prompt
Check omissions, permissions, and source drift before delivery.
Review the current safety-guard result: (1) does it satisfy the original task; (2) were any applicable steps or limits in the pinned SKILL.md missed; (3) did it perform any unauthorized file, command, network, or data action; and (4) which conclusions remain unverified? List issues first, then fix only what the source or user authorization supports.
Output checklist
Verify each item before delivery
The task matches the purpose documented in the SKILL.md.
The source section “使用场景” has been checked.
The source section “工作原理” has been checked.
The source section “模式 1：谨慎模式” has been checked.
The source section “模式 2：冻结模式” has been checked.
Inputs, constraints, and acceptance criteria are explicit.
Unverified facts, compatibility, and outcome claims are clearly marked.
Any file, command, network, or data action has been reviewed.
Choose a different workflow
When another Skill is the better fit
safety-guard
Use this skill to prevent destructive operations when working on production systems or running agents autonomously.
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailsafety-guard
本番システムでの作業時や、エージェントを自律的に実行する際に破壊的な操作を防ぐためにこのスキルを使用してください。
A separate implementation from affaan-m/ECC; compare its source, maintenance signals, and permission requirements.
Open source detailab-testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
A separate implementation from coreyhaines31/marketingskills; compare its source, maintenance signals, and permission requirements.
Open source detailFAQ
What does safety-guard do?
使用此技能可防止在生产系统上工作或自主运行代理时进行破坏性操作。
How do I start using safety-guard?
The catalog detected this source-specific install command: npx skills add https://github.com/affaan-m/ECC --skill "docs/zh-CN/skills/safety-guard". Inspect the command and pinned source before running it.
Which Agent platforms does it declare?
No dedicated Agent platform is declared in the pinned source record.
Repository stars
234,327
Repository forks
35,711
Quality
59/100
Source repository last pushed
Quality breakdown
Based on traceable docs and repository signals; stars are not treated as quality.
Documentation15/30
Specificity7/25
Maintenance20/20
Trust signals17/25
Compare before choosing
Related Agent Skills and source variants
These links are selected from shared tasks, functions, stacks, platforms, and same-name variants. Compare the source owner, documentation, permissions, and maintenance signals.
safety-guard by affaan-m
Use this skill to prevent destructive operations when working on production systems or running agents autonomously.
safety-guard by affaan-m
本番システムでの作業時や、エージェントを自律的に実行する際に破壊的な操作を防ぐためにこのスキルを使用してください。
ab-testing by coreyhaines31
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
churn-prevention by coreyhaines31
When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when the user mentions 'churn,' 'cancel flow,' 'offboarding,' 'save offer,' 'dunning,' 'failed payment recovery,' 'win-back,' 'retention,' 'exit survey,' 'pause subscription,' 'involuntary churn,' 'people keep canceling,' 'churn rate is too high,' 'how do I keep users,' or 'customers are leaving.' Use this whenever someone is losing subscribers o
design-intelligence by event4u-app
Grounded design brief from the adopted corpus — style, WCAG-checked color tokens, typography, layout pattern, anti-patterns. Use on ui-design-brief or any which-style/palette/font/chart decision.
View original Skill.mdThis page is parsed directly from the repository SKILL.md without editorial rewriting. Collected: Jul 28, 2026 · about 1 min
安全防护 — 防止破坏性操作
使用场景
- 在生产系统上工作时
- 代理以全自动模式运行时
- 希望将编辑限制在特定目录时
- 敏感操作期间（迁移、部署、数据变更）
工作原理
三种保护模式：
模式 1：谨慎模式
在执行破坏性命令前进行拦截并发出警告：
已监控的模式：
- rm -rf（特别是 /、~ 或项目根目录）
- git push --force
- git reset --hard
- git checkout .（丢弃所有更改）
- DROP TABLE / DROP DATABASE
- docker system prune
- kubectl delete
- chmod 777
- sudo rm
- npm publish（意外发布）
- 任何带有 --no-verify 的命令
检测到时：显示命令功能、请求确认、建议更安全的替代方案。
模式 2：冻结模式
将文件编辑锁定到特定目录树：
/safety-guard freeze src/components/
任何在 src/components/ 之外的写入/编辑操作都会被阻止并附带说明。适用于希望代理专注于某个区域而不触及无关代码的场景。
模式 3：守护模式（谨慎+冻结组合）
双重保护同时生效。为自主代理提供最高安全性。
/safety-guard guard --dir src/api/ --allow-read-all
代理可读取任何内容，但仅能写入 src/api/。破坏性命令在所有位置均被阻止。
解锁
/safety-guard off
实现方式
通过 PreToolUse 钩子拦截 Bash、Write、Edit 和 MultiEdit 工具调用。在执行前根据活动规则检查命令/路径。
集成方案
- 默认在
codex -a never会话中启用 - 配合 ECC 2.0 的可观测性风险评分
- 所有被阻止的操作记录至
~/.claude/safety-guard.log
- Source repo
- affaan-m/ECC
- Skill path
- docs/zh-CN/skills/safety-guard/SKILL.md
- Commit SHA
- 4e973d3eaf92
- Repository license
- MIT
- Data collected