Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zj-unicom-ai/UniEmployee --skill fault-impact-analysisgit clone --depth 1 https://github.com/zj-unicom-ai/UniEmployeeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zj-unicom-ai/uniemployee/fault-impact-analysis)<a href="https://agentmods.dev/skills/zj-unicom-ai/uniemployee/fault-impact-analysis"><img src="https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/fault-impact-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zj-unicom-ai/uniemployee/fault-impact-analysis"><img src="https://agentmods.dev/badge/skills/zj-unicom-ai/uniemployee/fault-impact-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.01049 |
| Opus 5 | $0.00022 | $0.00524 |
| Sonnet 5 | $0.00009 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
fault-impact-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually 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：
- 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）；
- severity 分布：P1/P2 必须逐条列出时间与告警类型；
- 告警类型分布与 root_cause 分布（Top3）；
- 平均处理时长 duration_min（区分已恢复/处理中）；
- 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）
从基站实体 id 出发：
- ontology_query_relations(entity_id, relation_type="cover") → 得到覆盖片区；
- 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；
- 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
- 装维：ontology_query_relations(基站id, relation_type="maintain", direction="in") → 负责该基站的装维工程师（含电话）；与告警流水 handler 字段交叉核对， 若 handler 与本体维护人不一致，提示调度记录与本体维护关系需要核实；
- 升级：若影响 VIP 或政企客户，同时查片区维护部门值班负责人 （部门 → manage/belongs_to 关系）。
步骤5：输出处置建议并登记工单
按「影响面 → 告警摘要 → 责任人 → 处置建议」结构输出：
- 影响面：退服基站 / 覆盖片区 / 受影响客户数 / VIP 客户清单
- 告警摘要：时间窗内 P1/P2 明细、根因 Top、平均处理时长、同站故障频次
- 责任人：装维工程师姓名与电话（含告警流水 handler）
- 处置建议：按客户等级排序（VIP 优先）、给出临时缓解措施（如切换相邻基站）、 结合 root_cause 给出整改方向（如光纤老化 → 更换光缆段）
- 用户确认需要派单时，调用 create_ticket 登记故障工单
结尾标注数据来源：「以上来自企业本体查询（N 个实体 / M 条关系）+ 告警流水分析（X 条）」。
注意事项
- 基站升级中 ≠ 故障，回答前先看 status 属性与近期告警再定性
- 查不到关系时如实说明"本体中未登记"，不要编造
- 涉及资费赔偿承诺前，先走 kb_search 查现行 SLA 制度
- 数据分析用 execute 跑 pandas（工作目录 /data，共享数据集在 /datasets/ 只读 目录，用绝对路径读 csv 如 pd.read_csv("/datasets/netops_alerts.csv")）， 不要把告警数据逐条贴进上下文
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +1 lines 7bc9e7d93485
- 7d ago Changed · +20 lines cc37ac169bcb
- 11d ago First seen · 50 lines · 44 tokens per session scan A a2d860de3741
fault-impact-analysis is a skill published in the GitHub repository zj-unicom-ai/UniEmployee (86 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,049 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
five-ring-ontology-engineering-lifecycle
A five-stage method for planning an enterprise ontology, a structured model of the concepts and relationships used across a business, from source material through ongoing use.
ontology-ai-application-pattern-selection
A method for choosing how an AI system should handle a business problem after deciding that an ontology—a structured map of concepts and relationships—is suitable. It compares patterns such as workflow automation, decision support, knowledge answering, collaboration, and continuous planning.
ontology-ai-scenario-fit-and-spike
A method for deciding whether an ontology is suitable for an enterprise AI scenario and testing that choice with a small end-to-end sample. An ontology is a structured model of concepts, rules, and relationships.
ontology-constraint-and-knowledge-injection
A method for deciding how an ontology’s knowledge should reach an AI model: directly in its instructions, through RAG, or through fine-tuning. RAG retrieves relevant information at answer time; fine-tuning changes the model using training examples.
ontology-golden-case-testing
A testing method for an ontology, which is a structured model of business concepts and rules. It starts with real business questions and expected answers, then adds boundary, missing-data, conflict, permission, and regression tests.
ontology-model-multilayer-quality-gate
A quality-review process for an ontology—a structured map of concepts and relationships—created by an AI model. It combines independent review, software checks, and business-expert checks before production use.