yuki-aigc/pomeloclaw/aliyun-tag-inference

Claude Code and agent skill by yuki-aigc/pomeloclaw

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

标签智能推断引擎 — 基于启发式规则和拓扑分析推断标签归属。触发词:智能推断标签、自动识别标签、标签建议

Install

npx vskill@latest install yuki-aigc/pomeloclaw/aliyun-tag-inference

SKILL.md

aliyun-tag-inference — 标签智能推断引擎

标签智能推断引擎技能,基于启发式规则和拓扑分析推断标签归属。通过正则模式匹配、VPC 拓扑继承、创建者信息等方式智能推断资源应该具有的标签。

核心能力

  1. 名称模式推断 — 根据资源名称正则匹配推断 env 标签
  2. VPC 拓扑推断 — 根据 VPC 归属关系推断 team 标签
  3. 创建者推断 — 根据资源创建者推断 owner 标签
  4. 批量推断 — 对给定资源执行所有适用的推断方法
  5. 推断审核 — 人工审核推断结果后应用

推断方法和置信度

推断方法标签键置信度范围说明
名称模式匹配env0.8-0.9`prodproductionprd` → prod
VPC 自身标签继承team0.9VPC 有 team 标签,子资源继承
VPC 安全组关联team0.75通过安全组间接推断
创建者映射owner0.8创建者用户名映射

功能列表

操作工具函数风险等级说明
名称推断 envtagi_infer_env_from_nameLOW正则模式矩阵推断 env 标签
VPC 推断 teamtagi_infer_team_from_vpcLOWVPC 拓扑推断 team 标签
创建者推断 ownertagi_infer_owner_from_creatorLOW创建者映射推断 owner 标签
批量推断tagi_batch_inferLOW对给定资源执行所有推断方法
查询推断tagi_review_inferencesLOW查询待审核推断列表
应用推断tagi_apply_inferencesMEDIUM确认或拒绝推断结果

典型使用流程

1. 执行智能推断
→ tagi_infer_env_from_name(
resource_types=["ACS::ECS::Instance"],
regions=["cn-hangzhou"]
)
根据名称模式推断 env 标签
→ tagi_infer_team_from_vpc(
vpc_ids=["vpc-xxx", "vpc-yyy"],
region="cn-hangzhou"
)
根据 VPC 拓扑推断 team 标签
2. 审核推断结果
→ tagi_review_inferences(min_confidence=0.8, status="pending")
查询高置信度的待审核推断
→ tagi_apply_inferences(
inference_ids=["inf-xxx", "inf-yyy"],
action="approve"
)
确认并应用推断结果
3. 批量推断
→ tagi_batch_infer(
resource_arns=["arn:acs:ecs:..."],
tag_keys=["env", "team", "owner"]
)
对指定资源执行所有适用的推断方法

推断结果数据模型

json
{
"inference_id": "inf-xxx",
"resource_arn": "arn:acs:ecs:cn-hangzhou:123456:instance/i-xxx",
"resource_name": "prod-web-server-01",
"inferred_tags": {
"env": "prod"
},
"confidence": 0.9,
"method": "name_pattern_match",
"evidence": "名称匹配模式: prod|production|prd",
"status": "pending",
"created_at": "2024-01-01T00:00:00"
}

持久化文件

推断结果存储:~/.copaw/data/tag_inferences.json

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
58
Repository forks
3
7-day trend score
20

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 5 Jul 2026, 4 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/yuki-aigc/pomeloclaw/aliyun-tag-inference/badge)](https://verified-skill.com/skills/yuki-aigc/pomeloclaw/aliyun-tag-inference)

Something wrong with this skill or its page? Tell us.