00-core
SAEBase / OpenResearch 的最小全局行为与权限边界。
Install / Use
npx skills add OpenSAE/SAEBaseInstalls into whichever agent you are using.
Cursor Rules
Cursor IDE rules (v2)
Quality Score
Category
Education & ResearchSupported Platforms
Tags
Our assessment of 00-core
00-core scores 38/100 on our quality scale, 444th of 449 Education & Research skills we index.
Its Cursor Rules is 1.6 KB long, lightly structured (2 headings) and no code examples: moderately detailed.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- We could not determine when the repository was last updated.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
00-core compared with similar skills
All 4 of these similar skills score higher than 00-core; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| 00-core (this skill)by OpenSAE | 38 | 0 | — | Cursor Rules |
| app-store-optimizationby sickn33 | 100 | 47.9k | 8d ago | SKILL.md |
| arborby K-Dense-AI | 100 | 46.4k | 36d ago | SKILL.md |
| clinical-reportsby K-Dense-AI | 100 | 46.4k | 36d ago | SKILL.md |
| lab-hardware-cadby K-Dense-AI | 100 | 46.4k | 36d ago | SKILL.md |
Frequently asked questions
- How do I install 00-core?
- Run
npx skills add OpenSAE/SAEBase. The install tabs above show the steps for each supported agent. - Which AI agents does 00-core work with?
- It is written for Cursor, as a Cursor Rules file. Other agents that read the same format can often use it too.
- Is 00-core safe to use?
- It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is 00-core still maintained?
- We could not determine when the repository was last updated.
Skill content
View source on GitHubdescription: SAEBase / OpenResearch 的最小全局行为与权限边界。 alwaysApply: true
SAEBase / OpenResearch 全局约束
- 本仓库保留 SAEBase v0.5.0 的独立 API、模型注册、研究工具和发布流程,同时加入 OpenResearch 的 DLBase 与 Harness。先辨认变更属于 dlbase、datasets、models、tasks、conf 或 Harness。
- 真实运行契约以源码、注册表与 Hydra 配置为准;Agent 规则和工作流程以 .cursor/ 为准。README 只负责对人介绍仓库,不能作为 Agent 的强制规范来源。
- 修改前阅读受影响模块、入口、现有注册与配置;必要时使用 .cursor/skills/ 下对应 Skill。
- 未经用户明确批准,不修改 dlbase/ 的通用语义。修改权限由 .cursor/hooks/guard_paths.py 和 .cursor/policy.json 的额外防护共同约束;不得通过绕过检查达成修改。
- 维护现有训练与评测语义。不能因重构、修复或验证而静默改变数据划分、指标、默认超参、checkpoint 或输出。
- 保留 SAEBase 已有的 docs、examples、apps、work_plan 与发布工具。新增科研运行使用 dlbase.train,原有 saebase 命令保持兼容。辅助脚本使用 scripts/,自动测试使用 tests/,Cursor Hook 自身留在 .cursor/hooks/。
- 新模型、数据集、任务必须经已有 Registry 和兼容性门控接入,不得绕过检查写隐藏分支。
- 如需批量实验或训练,先确认数据路径、GPU/时长预算及潜在产物覆盖风险;不得擅自执行长训练来代替快速测试。
- 修改后运行与变更相称的可执行验证;报告验证命令、结果、未验证的部分。不得把尚未运行的检查描述为已通过。
- 与用户交流和新增 Markdown 文档原则上使用中文;命令、Python 标识符、专有名词及引用可保留英文。
doc/knowledge/、doc/code/和harness/是按任务选择的上下文资料;严格遵守.cursor/rules/core/10-context-selection.mdc,普通开发不得主动全量浏览这些目录。
Agent 执行任务流程
- 接到外部
github_work_plan后先运行harness/core/agent_flow.py intake审计结构化节点清单,再用 Review HTML 向使用者显示红色预期变化。用户审核部署范围前禁止修改任务源文件。 - Agent 可通过
python -m harness.core.agent_flow inspect|scope|stage|observe|finalize读取审核范围和提出证据;不能通过脚本冒充人类 authorize/decide。 - Core Tree、
harness/core/、harness/visualization/、其他 Harness 治理文件、.cursor/均为 Agent 不可修改边界。该权限约束不授权 Agent 修改治理层本身。 - 不在当前授权任务范围内的任何 Node、源码或 Knowledge/Context 改动,必须先得到用户对新增范围的直接授权;不得自扩展 scope。
- Code、Environment、Knowledge、Context 可以按精确 ID/证据按需读取;Core 默认屏蔽。黄色表示代码审阅过但功能未验收,只有执行结果独立审计且人类核准才可以在 Review Overlay 绿化节点。
Related Skills
app-store-optimization
47.9kComplete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store
arbor
46.4kApplies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization.
clinical-reports
46.4kCreates safety-bounded draft structures and runs local deterministic checks for clinical case, diagnostic, trial, safety, and aggregate research reports. Use only with synthetic, de-identified, or aggregate inputs and verified source-fact manifests; every output requires qualified review.
lab-hardware-cad
46.4kDesigns custom laboratory hardware as parametric build123d models and exports fabrication artifacts as STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument f…
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
