orchestrator-core SKILL.md skillA
orchestrator-core from martin1847/evolab is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add martin1847/evolab/orchestrator-core@v0.2.4Pins v0.2.4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- martin1847/evolab
- Path
skills/orchestrator-core/SKILL.md- Versions recorded
- 7
- Latest version
- v0.2.4, committed Oct 29, 2026
- First version recorded
- Aug 5, 2026
- Size
- 12,640 bytes
- Repository stars
- 7
- License
- MIT
多智能体编排的领域无关内核。适用于抽象编排模式、创建新领域编排者，或设计多智能体架构。实际软件交付编排使用 cto-orchestration。不用于单 agent 一次性小任务或纯文档初始化。.
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
# Orchestrator Core — 编排内核（领域无关） > **这是内核，不是编排者。** 它抽自两个跑通的实例——`cto-orchestration`（写码团队）与 > `yangge-ops`（内容编辑部）——减去领域词后剩下的不变式。任何新领域编排者 = 本内核 + 一张薄皮。 > 造 CEO / 销售 / 研究编排者，别新建一套，**贴皮**（§10）。 > 复杂度守恒：内核没消灭编排的复杂度，它把复杂度从每个领域的 worker 上下文，压进了**契约**和**合并**两处（§3/§5）。 ## 0. 内核的一句话 **先编排，再工作**——编排是 agent 的操作系统：任务进来先过「派 or 不派」判据（§2），亲手执行是调度的一种结果，不是默认姿态。 **编排者持有判断，不持有产物；持有薄的萃取上下文，不持有脏数据；把复杂度压进契约与合并，把简单留给主 session。** 分层不变式一句：**Deterministic workflow outside, bounded intelligence inside, evidence at the boundary — and intelligence periodically attacks the workflow.**（确定性 workflow 在外， 受约束的智能在内，边界用证据交接——智能定期反攻 workflow。）流程、状态、验收、重试写成 确定性机制；判断力只花在编不出来的地方；层与层用证据交接、不用信任交接；机制本身会静默 腐坏，须由智能定期以异源变异攻击。 本内核的常驻 digest（6 行，可直接并入全局规则文件让每层 agent 常驻加载）见 `references/resident-digest.md`。 --- ## 1. 铁律一：编排者不亲手做领域产物 编排者的产出是**契约、调度、裁决、状态落盘**，不是领域产物本身。 - CTO 皮：不写产品代码。｜总编皮：不写正文。｜未来皮：CEO 不亲手谈单、研究编排者不亲手读论文。 - 判据不是「能不能做」，是「做了会不会占掉编排位的稀缺性 + 污染主上下文」。**你能做，恰恰是最该派的信号。** ## 2. 铁律二：切分轴是「要不要主上下文」，不是耗时 派 or 不派，只问一句：**这活需不需要贴着我此刻这摊上下文才能干？** - **不需要**（自包含、可蒸馏、脏数据密集）→ 派出去，越并行越好。哪怕它只要 10 秒（读 170KB digest 找三条＝该派，因为它污染主上下文）。 - **需要**（要贴着主线反复迭代、共享假设）→ 留在主 session，哪怕它要一小时（贴着确认门写正文＝不派，派出去 worker 拿残缺假设各干各的，合并全是冲突）。 …
Read the whole file at its exact version.
How to install
mdr add martin1847/evolab/orchestrator-core@sha256:8006353866cb18eeThe line at the top of this page pins the label v0.2.4, 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_ewgjrycl3a2cg7gs)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 7 versions of this file, between Aug 5, 2026 and Oct 29, 2026, about one every 14 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.2.4 latest | 2026-10-29 | 8b44fa3 | 12,640 B | A | view · diff |
| v0.2.3 | 2026-10-29 | 7345c25 | 12,640 B | A | view · diff |
| v0.2.3 | 2026-08-17 | 5238f2c | 13,125 B | A | view · diff |
| v0.2.3 | 2026-08-17 | 929054a | 13,010 B | A | view · diff |
| v0.2.3 | 2026-08-17 | 5b5ceef | 12,777 B | A | view · diff |
| v0.2.2 | 2026-08-12 | ac37a77 | 12,985 B | A | view · diff |
| v0.2.1 | 2026-08-05 | c40c3ab | 12,222 B | A | view |
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 (12640 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
martin1847/evolab · 7 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ewgjrycl3a2cg7gs GET https://markdownregistry.com/api/v1/resolve?ref=martin1847/evolab/orchestrator-core GET https://markdownregistry.com/api/v1/blob/8006353866cb18eefccd9a069a5302cab309bce095b4ef63fb74263ccd8c49bf
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.