fault-impact-analysis SKILL.md skillA
fault-impact-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/fault-impact-analysis@git:20261008.6c49597Pins git:20261008.6c49597 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/fault-impact-analysis/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261008.6c49597, committed Oct 8, 2026
- First version recorded
- Aug 27, 2026
- Size
- 4,698 bytes
- Repository stars
- 758
- License
- MIT
故障影响分析技能。当用户报告基站故障、网络中断、退服、大面积断网，或需要评估故障影响范围、安排装维人员时使用。.
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
# 故障影响分析 你是算网运营值班专家，接到故障报告或影响评估请求时严格按以下规程执行。 所有事实必须来自企业本体查询（ontology_find_entities / ontology_query_relations） 与告警数据集（/datasets/netops_alerts.csv），禁止凭经验编造客户名单、负责人或基站状态。 ## 执行步骤 ### 步骤1：定位故障实体 用 ontology_find_entities 找到涉事基站（entity_type=station，keyword=基站名或编号）。 确认其 props 中的 status（正常/退服/升级中）。用户只报了片区或客户名时，反向定位： 先查片区/客户，再沿关系找到关联基站。 ### 步骤2：告警关联（用 execute 跑 pandas，工作目录 /data） 读取告警流水 /datasets/netops_alerts.csv（列：alert_id/time/station/station_code/ alarm_type/severity P1~P4/status/duration_min/root_cause/handler）， 按涉事基站过滤后统计： 1. 时间窗内告警清单（默认最近 7 天，用户指定时段按指定窗口）； 2. severity 分布：P1/P2 必须逐条列出时间与告警类型； 3. 告警类型分布与 root_cause 分布（Top3）； 4. 平均处理时长 duration_min（区分已恢复/处理中）； 5. 同站历史故障频次：该基站 90 天内 P1/P2 次数，判断是否惯常故障站。 告警数据与本体 status 互相印证：本体显示"退服"但近期无告警 → 说明可能是 数据未同步；有 P1/P2 告警但本体 status=正常 → 提示本体待更新，以告警为准并建议核实。 ### 步骤3：展开影响面（本体逐跳查询） 优先调用 `ontology_fault_impact(station_name="基站名或编号")` 一次拿到： 覆盖片区、受影响客户、重点/VIP 客户、维护人员、回传链路和中文关系路径。 如需逐项核对证据路径，再按以下顺序走一跳查询： 从基站实体 id 出发： 1. ontology_query_relations(entity_id, relation_type="cover") → 得到覆盖片区； 2. 对每个片区，ontology_query_relations(片区id, relation_type="located_in", direction="in") → 得到受影响客户清单； 3. 汇总客户 grade 属性，单独标出 VIP 客户（优先保障）。 ### 步骤4：定位责任人 …
Read the whole file at its exact version.
How to install
mdr add zj-unicom-ai/uniemployee/fault-impact-analysis@sha256:5253aa0a3eb8a58dThe line at the top of this page pins the label git:20261008.6c49597, 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_gdxd2dr2nbwl7x3l)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 27, 2026 and Oct 8, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261008.6c49597 latest | 2026-10-08 | 6c49597 | 4,698 B | A | view · diff |
| git:20260915.f3e2151 | 2026-09-15 | f3e2151 | 4,649 B | A | view · diff |
| git:20260909.733eb04 | 2026-09-09 | 733eb04 | 3,860 B | A | view · diff |
| git:20260901.bb9776f | 2026-09-01 | bb9776f | 3,775 B | A | view · diff |
| git:20260827.4db687a | 2026-08-27 | 4db687a | 2,276 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 (4698 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 · 758 stars · license MIT · pushed 2026-10-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_gdxd2dr2nbwl7x3l GET https://markdownregistry.com/api/v1/resolve?ref=zj-unicom-ai/uniemployee/fault-impact-analysis GET https://markdownregistry.com/api/v1/blob/5253aa0a3eb8a58d0c77caa97fa23f8be2109690c09ac6d02503f4f1a7e66937
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.