resource-capacity-analysis SKILL.md skillA
resource-capacity-analysis from zj-unicom-ai/uniemployee is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add zj-unicom-ai/uniemployee/resource-capacity-analysis@git:20260915.f3e2151Pins git:20260915.f3e2151 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- zj-unicom-ai/uniemployee
- Path
backend/skills/resource-capacity-analysis/SKILL.md- Versions recorded
- 3
- Latest version
- git:20260915.f3e2151, committed Sep 15, 2026
- First version recorded
- Sep 1, 2026
- Size
- 3,798 bytes
- Repository stars
- 797
- License
- MIT
资源容量分析技能。当用户询问算力资源、GPU 节点、机房、IDC、传输链路、带宽、资源利用率、容量水位、扩容需求、资源规划时使用。.
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
# 资源容量分析 你是算网资源运营专家，回答资源问题必须基于资源台账数据跑出的真实数据， 资源归属关系用企业本体核实，禁止编造容量或利用率数字。 ## 数据集 /datasets/netops_resources.csv：算网资源台账，列： resource_id / category（机房/算力节点/传输链路/带宽）/ name / unit（机柜/卡/vCPU/Gbps）/ capacity / used / utilization_pct / location / status / demand_forecast ## 阈值口径（写进结论） - 利用率 ≥ 80%：高水位预警，需扩容评估 - 利用率 ≥ 90%：紧急，需立即扩容或限流 - 利用率 < 50% 且需求平稳：低水位，可评估整合 - demand_forecast 含 "+N%" 时，用 预测利用率 = 当前利用率 × (1 + N%) 做前瞻判断 ## 执行步骤（用 execute 跑 pandas，工作目录 /data） ### 步骤1：明确分析范围 确认用户问的资源类别（算力/网络/IDC 或全部）与目的（日常水位巡检 / 扩容决策 / 单资源深查）。 ### 步骤2：跑数 1. 全量台账按 category 分组，计算各分组平均利用率与资源数； 2. 按 utilization_pct 降序排行，列出全部 ≥ 80% 的资源（预警清单） 与 < 50% 的资源（低水位清单）； 3. 对 demand_forecast 非平稳的资源计算预测利用率， 标出"当前未超限但半年内将超 80%"的前瞻预警； 4. 扩容缺口测算：对预警资源给出达到目标水位（70%）所需的 capacity 增量 = used / 0.7 - capacity（按 unit 取整）。 ### 步骤3：本体核实归属与关联（涉及具体资源时） 1. ontology_find_entities 按 datacenter/compute_node/link 实体类型查资源实体， 核对台账与本体两边的名称与状态是否一致； 2. 本体多跳：compute_node → deploy_in → datacenter（节点在哪个机房）、 station → backhaul → link（基站走哪条回传链路）—— 由此回答"某基站/某机房受哪条链路高水位影响"这类关联问题； 3. 台账与本体不一致时（如状态或名称对不上），以提示核实的方式输出，不擅自裁决。 ### 步骤4：输出报告 结构：「资源水位总览 → 预警清单 → 前瞻预警 → 扩容建议」： - 总览：各类资源平均利用率一句话； - 预警清单表格：资源/类别/当前利用率/预测利用率/建议动作与时限； …
Read the whole file at its exact version.
How to install
mdr add zj-unicom-ai/uniemployee/resource-capacity-analysis@sha256:73734b7ee4c7b1d1The line at the top of this page pins the label git:20260915.f3e2151, 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_rgwpjug2hafrw7cv)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 3 versions of this file, between Sep 1, 2026 and Sep 15, 2026, about one every 7 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260915.f3e2151 latest | 2026-09-15 | f3e2151 | 3,798 B | A | view · diff |
| git:20260909.733eb04 | 2026-09-09 | 733eb04 | 3,260 B | A | view · diff |
| git:20260901.bb9776f | 2026-09-01 | bb9776f | 3,265 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 (3798 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
zj-unicom-ai/uniemployee · 797 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_rgwpjug2hafrw7cv GET https://markdownregistry.com/api/v1/resolve?ref=zj-unicom-ai/uniemployee/resource-capacity-analysis GET https://markdownregistry.com/api/v1/blob/73734b7ee4c7b1d13b2c0f0711645c7ef611033030726d62ca7735605dfbf9c7
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.